github/v-firecrawl
github/v-firecrawl
0
Fork 0
Code Actions

Merge branch 'main' into feat/idempotency-key

Browse Source
This commit is contained in:
rafaelsideguide 2024-05-23 12:20:06 -03:00
commit 35927a65a5
69 changed files with 9115 additions and 615 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.github/workflows/ci.yml vendored
View File

@ -25,6 +25,9 @@ env:
SUPABASE_SERVICE_TOKEN: ${{ secrets.SUPABASE_SERVICE_TOKEN }} SUPABASE_SERVICE_TOKEN: ${{ secrets.SUPABASE_SERVICE_TOKEN }}
SUPABASE_URL: ${{ secrets.SUPABASE_URL }} SUPABASE_URL: ${{ secrets.SUPABASE_URL }}
TEST_API_KEY: ${{ secrets.TEST_API_KEY }} TEST_API_KEY: ${{ secrets.TEST_API_KEY }}
HYPERDX_API_KEY: ${{ secrets.HYPERDX_API_KEY }}
HDX_NODE_BETA_MODE: 1
jobs: jobs:
pre-deploy: pre-deploy:

39
.github/workflows/fly.yml vendored
View File

@ -58,10 +58,47 @@ jobs:
run: | run: |
npm run test:prod npm run test:prod
working-directory: ./apps/api working-directory: ./apps/api
pre-deploy-test-suite:
name: Test Suite
needs: pre-deploy
runs-on: ubuntu-latest
services:
redis:
image: redis
ports:
- 6379:6379
steps:
- uses: actions/checkout@v3
- name: Set up Node.js
uses: actions/setup-node@v3
with:
node-version: "20"
- name: Install pnpm
run: npm install -g pnpm
- name: Install dependencies
run: pnpm install
working-directory: ./apps/api
- name: Start the application
run: npm start &
working-directory: ./apps/api
id: start_app
- name: Start workers
run: npm run workers &
working-directory: ./apps/api
id: start_workers
- name: Install dependencies
run: pnpm install
working-directory: ./apps/test-suite
- name: Run E2E tests
run: |
npm run test
working-directory: ./apps/test-suite
deploy: deploy:
name: Deploy app name: Deploy app
runs-on: ubuntu-latest runs-on: ubuntu-latest
needs: pre-deploy needs: pre-deploy-test-suite
steps: steps:
- uses: actions/checkout@v3 - uses: actions/checkout@v3
- name: Change directory - name: Change directory

6
.gitignore vendored
View File

@ -8,3 +8,9 @@ dump.rdb
apps/js-sdk/node_modules/ apps/js-sdk/node_modules/
apps/api/.env.local apps/api/.env.local
apps/test-suite/node_modules/
apps/test-suite/.env
apps/test-suite/logs

798
LICENSE
View File

@ -1,201 +1,661 @@
Apache License GNU AFFERO GENERAL PUBLIC LICENSE
Version 2.0, January 2004 Version 3, 19 November 2007
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
1. Definitions. Preamble
"License" shall mean the terms and conditions for use, reproduction, The GNU Affero General Public License is a free, copyleft license for
and distribution as defined by Sections 1 through 9 of this document. software and other kinds of works, specifically designed to ensure
cooperation with the community in the case of network server software.
"Licensor" shall mean the copyright owner or entity authorized by The licenses for most software and other practical works are designed
the copyright owner that is granting the License. to take away your freedom to share and change the works. By contrast,
our General Public Licenses are intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users.
"Legal Entity" shall mean the union of the acting entity and all When we speak of free software, we are referring to freedom, not
other entities that control, are controlled by, or are under common price. Our General Public Licenses are designed to make sure that you
control with that entity. For the purposes of this definition, have the freedom to distribute copies of free software (and charge for
"control" means (i) the power, direct or indirect, to cause the them if you wish), that you receive source code or can get it if you
direction or management of such entity, whether by contract or want it, that you can change the software or use pieces of it in new
otherwise, or (ii) ownership of fifty percent (50%) or more of the free programs, and that you know you can do these things.
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity Developers that use our General Public Licenses protect your rights
exercising permissions granted by this License. with two steps: (1) assert copyright on the software, and (2) offer
you this License which gives you legal permission to copy, distribute
and/or modify the software.
"Source" form shall mean the preferred form for making modifications, A secondary benefit of defending all users' freedom is that
including but not limited to software source code, documentation improvements made in alternate versions of the program, if they
source, and configuration files. receive widespread use, become available for other developers to
incorporate. Many developers of free software are heartened and
encouraged by the resulting cooperation. However, in the case of
software used on network servers, this result may fail to come about.
The GNU General Public License permits making a modified version and
letting the public access it on a server without ever releasing its
source code to the public.
"Object" form shall mean any form resulting from mechanical The GNU Affero General Public License is designed specifically to
transformation or translation of a Source form, including but ensure that, in such cases, the modified source code becomes available
not limited to compiled object code, generated documentation, to the community. It requires the operator of a network server to
and conversions to other media types. provide the source code of the modified version running there to the
users of that server. Therefore, public use of a modified version, on
a publicly accessible server, gives the public access to the source
code of the modified version.
"Work" shall mean the work of authorship, whether in Source or An older license, called the Affero General Public License and
Object form, made available under the License, as indicated by a published by Affero, was designed to accomplish similar goals. This is
copyright notice that is included in or attached to the work a different license, not a version of the Affero GPL, but Affero has
(an example is provided in the Appendix below). released a new version of the Affero GPL which permits relicensing under
this license.
"Derivative Works" shall mean any work, whether in Source or Object The precise terms and conditions for copying, distribution and
form, that is based on (or derived from) the Work and for which the modification follow.
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including TERMS AND CONDITIONS
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity 0. Definitions.
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of "This License" refers to version 3 of the GNU Affero General Public License.
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of "Copyright" also means copyright-like laws that apply to other kinds of
this License, each Contributor hereby grants to You a perpetual, works, such as semiconductor masks.
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the "The Program" refers to any copyrightable work licensed under this
Work or Derivative Works thereof in any medium, with or without License. Each licensee is addressed as "you". "Licensees" and
modifications, and in Source or Object form, provided that You "recipients" may be individuals or organizations.
meet the following conditions:
(a) You must give any other recipients of the Work or To "modify" a work means to copy from or adapt all or part of the work
Derivative Works a copy of this License; and in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
(b) You must cause any modified files to carry prominent notices A "covered work" means either the unmodified Program or a work based
stating that You changed the files; and on the Program.
(c) You must retain, in the Source form of any Derivative Works To "propagate" a work means to do anything with it that, without
that You distribute, all copyright, patent, trademark, and permission, would make you directly or secondarily liable for
attribution notices from the Source form of the Work, infringement under applicable copyright law, except executing it on a
excluding those notices that do not pertain to any part of computer or modifying a private copy. Propagation includes copying,
the Derivative Works; and distribution (with or without modification), making available to the
public, and in some countries other activities as well.
(d) If the Work includes a "NOTICE" text file as part of its To "convey" a work means any kind of propagation that enables other
distribution, then any Derivative Works that You distribute must parties to make or receive copies. Mere interaction with a user through
include a readable copy of the attribution notices contained a computer network, with no transfer of a copy, is not conveying.
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and An interactive user interface displays "Appropriate Legal Notices"
may provide additional or different license terms and conditions to the extent that it includes a convenient and prominently visible
for use, reproduction, or distribution of Your modifications, or feature that (1) displays an appropriate copyright notice, and (2)
for any such Derivative Works as a whole, provided Your use, tells the user that there is no warranty for the work (except to the
reproduction, and distribution of the Work otherwise complies with extent that warranties are provided), that licensees may convey the
the conditions stated in this License. work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
5. Submission of Contributions. Unless You explicitly state otherwise, 1. Source Code.
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade The "source code" for a work means the preferred form of the work
names, trademarks, service marks, or product names of the Licensor, for making modifications to it. "Object code" means any non-source
except as required for reasonable and customary use in describing the form of a work.
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or A "Standard Interface" means an interface that either is an official
agreed to in writing, Licensor provides the Work (and each standard defined by a recognized standards body, or, in the case of
Contributor provides its Contributions) on an "AS IS" BASIS, interfaces specified for a particular programming language, one that
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or is widely used among developers working in that language.
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory, The "System Libraries" of an executable work include anything, other
whether in tort (including negligence), contract, or otherwise, than the work as a whole, that (a) is included in the normal form of
unless required by applicable law (such as deliberate and grossly packaging a Major Component, but which is not part of that Major
negligent acts) or agreed to in writing, shall any Contributor be Component, and (b) serves only to enable use of the work with that
liable to You for damages, including any direct, indirect, special, Major Component, or to implement a Standard Interface for which an
incidental, or consequential damages of any character arising as a implementation is available to the public in source code form. A
result of this License or out of the use or inability to use the "Major Component", in this context, means a major essential component
Work (including but not limited to damages for loss of goodwill, (kernel, window system, and so on) of the specific operating system
work stoppage, computer failure or malfunction, or any and all (if any) on which the executable work runs, or a compiler used to
other commercial damages or losses), even if such Contributor produce the work, or an object code interpreter used to run it.
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing The "Corresponding Source" for a work in object code form means all
the Work or Derivative Works thereof, You may choose to offer, the source code needed to generate, install, and (for an executable
and charge a fee for, acceptance of support, warranty, indemnity, work) run the object code and to modify the work, including scripts to
or other liability obligations and/or rights consistent with this control those activities. However, it does not include the work's
License. However, in accepting such obligations, You may act only System Libraries, or general-purpose tools or generally available free
on Your own behalf and on Your sole responsibility, not on behalf programs which are used unmodified in performing those activities but
of any other Contributor, and only if You agree to indemnify, which are not part of the work. For example, Corresponding Source
defend, and hold each Contributor harmless for any liability includes interface definition files associated with source files for
incurred by, or claims asserted against, such Contributor by reason the work, and the source code for shared libraries and dynamically
of your accepting any such warranty or additional liability. linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
END OF TERMS AND CONDITIONS The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
APPENDIX: How to apply the Apache License to your work. The Corresponding Source for a work in source code form is that
same work.
To apply the Apache License to your work, attach the following 2. Basic Permissions.
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright 2024 Firecrawl | Mendable.ai All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
Licensed under the Apache License, Version 2.0 (the "License"); You may make, run and propagate covered works that you do not
you may not use this file except in compliance with the License. convey, without conditions so long as your license otherwise remains
You may obtain a copy of the License at in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
http://www.apache.org/licenses/LICENSE-2.0 Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
Unless required by applicable law or agreed to in writing, software 3. Protecting Users' Legal Rights From Anti-Circumvention Law.
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. No covered work shall be deemed part of an effective technological
See the License for the specific language governing permissions and measure under any applicable law fulfilling obligations under article
limitations under the License. 11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Remote Network Interaction; Use with the GNU General Public License.
Notwithstanding any other provision of this License, if you modify the
Program, your modified version must prominently offer all users
interacting with it remotely through a computer network (if your version
supports such interaction) an opportunity to receive the Corresponding
Source of your version by providing access to the Corresponding Source
from a network server at no charge, through some standard or customary
means of facilitating copying of software. This Corresponding Source
shall include the Corresponding Source for any work covered by version 3
of the GNU General Public License that is incorporated pursuant to the
following paragraph.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the work with which it is combined will remain governed by version
3 of the GNU General Public License.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU Affero General Public License from time to time. Such new versions
will be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU Affero General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU Affero General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU Affero General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published
by the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If your software can interact with users remotely through a computer
network, you should also make sure that it provides a way for users to
get its source. For example, if your program is a web application, its
interface could display a "Source" link that leads users to an archive
of the code. There are many ways you could offer source, and different
solutions will be better for different programs; see section 13 for the
specific requirements.
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU AGPL, see
<https://www.gnu.org/licenses/>.

154
README.md
View File

@ -6,7 +6,7 @@ _This repository is in its early development stages. We are still merging custom
## What is Firecrawl? ## What is Firecrawl?
[Firecrawl](https://firecrawl.dev?ref=github) is an API service that takes a URL, crawls it, and converts it into clean markdown. We crawl all accessible subpages and give you clean markdown for each. No sitemap required. [Firecrawl](https://firecrawl.dev?ref=github) is an API service that takes a URL, crawls it, and converts it into clean markdown or structured data. We crawl all accessible subpages and give you clean data for each. No sitemap required.
_Pst. hey, you, join our stargazers :)_ _Pst. hey, you, join our stargazers :)_
@ -114,7 +114,7 @@ Response:
### Search (Beta) ### Search (Beta)
Used to search the web, get the most relevant results, scrap each page and return the markdown. Used to search the web, get the most relevant results, scrape each page and return the markdown.
```bash ```bash
curl -X POST https://api.firecrawl.dev/v0/search \ curl -X POST https://api.firecrawl.dev/v0/search \
@ -215,8 +215,6 @@ curl -X POST https://api.firecrawl.dev/v0/scrape \
``` ```
Coming soon to the Langchain and LLama Index integrations.
## Using Python SDK ## Using Python SDK
### Installing Python SDK ### Installing Python SDK
@ -248,6 +246,32 @@ url = 'https://example.com'
scraped_data = app.scrape_url(url) scraped_data = app.scrape_url(url)
``` ```
### Extracting structured data from a URL
With LLM extraction, you can easily extract structured data from any URL. We support pydanti schemas to make it easier for you too. Here is how you to use it:
```python
class ArticleSchema(BaseModel):
title: str
points: int
by: str
commentsURL: str
class TopArticlesSchema(BaseModel):
top: List[ArticleSchema] = Field(..., max_items=5, description="Top 5 stories")
data = app.scrape_url('https://news.ycombinator.com', {
'extractorOptions': {
'extractionSchema': TopArticlesSchema.model_json_schema(),
'mode': 'llm-extraction'
},
'pageOptions':{
'onlyMainContent': True
}
})
print(data["llm_extraction"])
```
### Search for a query ### Search for a query
Performs a web search, retrieve the top results, extract data from each page, and returns their markdown. Performs a web search, retrieve the top results, extract data from each page, and returns their markdown.
@ -257,6 +281,128 @@ query = 'What is Mendable?'
search_result = app.search(query) search_result = app.search(query)
``` ```
## Using the Node SDK
### Installation
To install the Firecrawl Node SDK, you can use npm:
```bash
npm install @mendable/firecrawl-js
```
### Usage
1. Get an API key from [firecrawl.dev](https://firecrawl.dev)
2. Set the API key as an environment variable named `FIRECRAWL_API_KEY` or pass it as a parameter to the `FirecrawlApp` class.
### Scraping a URL
To scrape a single URL with error handling, use the `scrapeUrl` method. It takes the URL as a parameter and returns the scraped data as a dictionary.
```js
try {
const url = 'https://example.com';
const scrapedData = await app.scrapeUrl(url);
console.log(scrapedData);
} catch (error) {
console.error(
'Error occurred while scraping:',
error.message
);
}
```
### Crawling a Website
To crawl a website with error handling, use the `crawlUrl` method. It takes the starting URL and optional parameters as arguments. The `params` argument allows you to specify additional options for the crawl job, such as the maximum number of pages to crawl, allowed domains, and the output format.
```js
const crawlUrl = 'https://example.com';
const params = {
crawlerOptions: {
excludes: ['blog/'],
includes: [], // leave empty for all pages
limit: 1000,
},
pageOptions: {
onlyMainContent: true
}
};
const waitUntilDone = true;
const timeout = 5;
const crawlResult = await app.crawlUrl(
crawlUrl,
params,
waitUntilDone,
timeout
);
```
### Checking Crawl Status
To check the status of a crawl job with error handling, use the `checkCrawlStatus` method. It takes the job ID as a parameter and returns the current status of the crawl job.
```js
const status = await app.checkCrawlStatus(jobId);
console.log(status);
```
### Extracting structured data from a URL
With LLM extraction, you can easily extract structured data from any URL. We support zod schema to make it easier for you too. Here is how you to use it:
```js
import FirecrawlApp from "@mendable/firecrawl-js";
import { z } from "zod";
const app = new FirecrawlApp({
apiKey: "fc-YOUR_API_KEY",
});
// Define schema to extract contents into
const schema = z.object({
top: z
.array(
z.object({
title: z.string(),
points: z.number(),
by: z.string(),
commentsURL: z.string(),
})
)
.length(5)
.describe("Top 5 stories on Hacker News"),
});
const scrapeResult = await app.scrapeUrl("https://news.ycombinator.com", {
extractorOptions: { extractionSchema: schema },
});
console.log(scrapeResult.data["llm_extraction"]);
```
### Search for a query
With the `search` method, you can search for a query in a search engine and get the top results along with the page content for each result. The method takes the query as a parameter and returns the search results.
```js
const query = 'what is mendable?';
const searchResults = await app.search(query, {
pageOptions: {
fetchPageContent: true // Fetch the page content for each search result
}
});
```
## Contributing ## Contributing
We love contributions! Please read our [contributing guide](CONTRIBUTING.md) before submitting a pull request. We love contributions! Please read our [contributing guide](CONTRIBUTING.md) before submitting a pull request.

27
SELF_HOST.md
View File

@ -1,6 +1,31 @@
# Self-hosting Firecrawl # Self-hosting Firecrawl
*We're currently working on a more in-depth guide on how to self-host, but in the meantime, here is a simplified version.*
Refer to [CONTRIBUTING.md](https://github.com/mendableai/firecrawl/blob/main/CONTRIBUTING.md) for instructions on how to run it locally. Refer to [CONTRIBUTING.md](https://github.com/mendableai/firecrawl/blob/main/CONTRIBUTING.md) for instructions on how to run it locally.
*This repository is currently in its early stages of development. We are in the process of merging custom modules into this mono repository. The primary objective is to enhance the accuracy of LLM responses by utilizing clean data. It is not ready for full self-host yet - we're working on it* ## Getting Started
First, clone this repository and copy the example env file from api folder `.env.example` to `.env`.
```bash
git clone https://github.com/mendableai/firecrawl.git
cd firecrawl
cp ./apps/api/.env.example ./.env
```
For running the simplest version of FireCrawl, edit the `USE_DB_AUTHENTICATION` on `.env` to not use the database authentication.
```yml
USE_DB_AUTHENTICATION=false
```
Update the Redis URL in the .env file to align with the Docker configuration:
```yml
REDIS_URL=redis://redis:6379
```
Once that's complete, you can simply run the following commands to get started:
```bash
docker compose up
```
This will run a local instance of Firecrawl which can be accessed at `http://localhost:3002`.

11
apps/api/.env.example
View File

@ -3,6 +3,7 @@ NUM_WORKERS_PER_QUEUE=8
PORT=3002 PORT=3002
HOST=0.0.0.0 HOST=0.0.0.0
REDIS_URL=redis://localhost:6379 REDIS_URL=redis://localhost:6379
PLAYWRIGHT_MICROSERVICE_URL=http://playwright-service:3000
## To turn on DB authentication, you need to set up supabase. ## To turn on DB authentication, you need to set up supabase.
USE_DB_AUTHENTICATION=true USE_DB_AUTHENTICATION=true
@ -16,14 +17,22 @@ SUPABASE_SERVICE_TOKEN=
# Other Optionals # Other Optionals
TEST_API_KEY= # use if you've set up authentication and want to test with a real API key TEST_API_KEY= # use if you've set up authentication and want to test with a real API key
RATE_LIMIT_TEST_API_KEY_SCRAPE= # set if you'd like to test the scraping rate limit
RATE_LIMIT_TEST_API_KEY_CRAWL= # set if you'd like to test the crawling rate limit
SCRAPING_BEE_API_KEY= #Set if you'd like to use scraping Be to handle JS blocking SCRAPING_BEE_API_KEY= #Set if you'd like to use scraping Be to handle JS blocking
OPENAI_API_KEY= # add for LLM dependednt features (image alt generation, etc.) OPENAI_API_KEY= # add for LLM dependednt features (image alt generation, etc.)
BULL_AUTH_KEY= # BULL_AUTH_KEY= #
LOGTAIL_KEY= # Use if you're configuring basic logging with logtail LOGTAIL_KEY= # Use if you're configuring basic logging with logtail
PLAYWRIGHT_MICROSERVICE_URL= # set if you'd like to run a playwright fallback
LLAMAPARSE_API_KEY= #Set if you have a llamaparse key you'd like to use to parse pdfs LLAMAPARSE_API_KEY= #Set if you have a llamaparse key you'd like to use to parse pdfs
SERPER_API_KEY= #Set if you have a serper key you'd like to use as a search api SERPER_API_KEY= #Set if you have a serper key you'd like to use as a search api
SLACK_WEBHOOK_URL= # set if you'd like to send slack server health status messages SLACK_WEBHOOK_URL= # set if you'd like to send slack server health status messages
POSTHOG_API_KEY= # set if you'd like to send posthog events like job logs POSTHOG_API_KEY= # set if you'd like to send posthog events like job logs
POSTHOG_HOST= # set if you'd like to send posthog events like job logs POSTHOG_HOST= # set if you'd like to send posthog events like job logs
STRIPE_PRICE_ID_STANDARD=
STRIPE_PRICE_ID_SCALE=
HYPERDX_API_KEY=
HDX_NODE_BETA_MODE=1
FIRE_ENGINE_BETA_URL= # set if you'd like to use the fire engine closed beta

173
apps/api/openapi.json
View File

@ -18,8 +18,8 @@
"paths": { "paths": {
"/scrape": { "/scrape": {
"post": { "post": {
"summary": "Scrape a single URL", "summary": "Scrape a single URL and optionally extract information using an LLM",
"operationId": "scrapeSingleUrl", "operationId": "scrapeAndExtractFromUrl",
"tags": ["Scraping"], "tags": ["Scraping"],
"security": [ "security": [
{ {
@ -45,8 +45,43 @@
"type": "boolean", "type": "boolean",
"description": "Only return the main content of the page excluding headers, navs, footers, etc.", "description": "Only return the main content of the page excluding headers, navs, footers, etc.",
"default": false "default": false
},
"includeHtml": {
"type": "boolean",
"description": "Include the raw HTML content of the page. Will output a html key in the response.",
"default": false
} }
} }
},
"extractorOptions": {
"type": "object",
"description": "Options for LLM-based extraction of structured information from the page content",
"properties": {
"mode": {
"type": "string",
"enum": ["llm-extraction"],
"description": "The extraction mode to use, currently supports 'llm-extraction'"
},
"extractionPrompt": {
"type": "string",
"description": "A prompt describing what information to extract from the page"
},
"extractionSchema": {
"type": "object",
"additionalProperties": true,
"description": "The schema for the data to be extracted",
"required": [
"company_mission",
"supports_sso",
"is_open_source"
]
}
}
},
"timeout": {
"type": "integer",
"description": "Timeout in milliseconds for the request",
"default": 30000
} }
}, },
"required": ["url"] "required": ["url"]
@ -126,9 +161,20 @@
"description": "If true, returns only the URLs as a list on the crawl status. Attention: the return response will be a list of URLs inside the data, not a list of documents.", "description": "If true, returns only the URLs as a list on the crawl status. Attention: the return response will be a list of URLs inside the data, not a list of documents.",
"default": false "default": false
}, },
"maxDepth": {
"type": "integer",
"description": "Maximum depth to crawl. Depth 1 is the base URL, depth 2 is the base URL and its direct children, and so on."
},
"mode": {
"type": "string",
"enum": ["default", "fast"],
"description": "The crawling mode to use. Fast mode crawls 4x faster websites without sitemap, but may not be as accurate and shouldn't be used in heavy js-rendered websites.",
"default": "default"
},
"limit": { "limit": {
"type": "integer", "type": "integer",
"description": "Maximum number of pages to crawl" "description": "Maximum number of pages to crawl",
"default": 10000
} }
} }
}, },
@ -139,6 +185,11 @@
"type": "boolean", "type": "boolean",
"description": "Only return the main content of the page excluding headers, navs, footers, etc.", "description": "Only return the main content of the page excluding headers, navs, footers, etc.",
"default": false "default": false
},
"includeHtml": {
"type": "boolean",
"description": "Include the raw HTML content of the page. Will output a html key in the response.",
"default": false
} }
} }
} }
@ -191,7 +242,7 @@
"query": { "query": {
"type": "string", "type": "string",
"format": "uri", "format": "uri",
"description": "The URL to scrape" "description": "The query to search for"
}, },
"pageOptions": { "pageOptions": {
"type": "object", "type": "object",
@ -205,6 +256,11 @@
"type": "boolean", "type": "boolean",
"description": "Fetch the content of each page. If false, defaults to a basic fast serp API.", "description": "Fetch the content of each page. If false, defaults to a basic fast serp API.",
"default": true "default": true
},
"includeHtml": {
"type": "boolean",
"description": "Include the raw HTML content of the page. Will output a html key in the response.",
"default": false
} }
} }
}, },
@ -298,9 +354,66 @@
"data": { "data": {
"type": "array", "type": "array",
"items": { "items": {
"$ref": "#/components/schemas/ScrapeResponse" "$ref": "#/components/schemas/CrawlStatusResponseObj"
}, },
"description": "Data returned from the job (null when it is in progress)" "description": "Data returned from the job (null when it is in progress)"
},
"partial_data": {
"type": "array",
"items": {
"$ref": "#/components/schemas/CrawlStatusResponseObj"
},
"description": "Partial documents returned as it is being crawls (streaming). When a page is ready it will append to the parial_data array - so no need to wait for all the website to be crawled."
}
}
}
}
}
},
"402": {
"description": "Payment required"
},
"429": {
"description": "Too many requests"
},
"500": {
"description": "Server error"
}
}
}
},
"/crawl/cancel/{jobId}": {
"delete": {
"tags": ["Crawl"],
"summary": "Cancel a crawl job",
"operationId": "cancelCrawlJob",
"security": [
{
"bearerAuth": []
}
],
"parameters": [
{
"name": "jobId",
"in": "path",
"description": "ID of the crawl job",
"required": true,
"schema": {
"type": "string"
}
}
],
"responses": {
"200": {
"description": "Successful response",
"content": {
"application/json": {
"schema": {
"type": "object",
"properties": {
"status": {
"type": "string",
"description": "Returns cancelled."
} }
} }
} }
@ -343,6 +456,11 @@
"content": { "content": {
"type": "string" "type": "string"
}, },
"html": {
"type": "string",
"nullable": true,
"description": "Raw HTML content of the page if `includeHtml` is true"
},
"metadata": { "metadata": {
"type": "object", "type": "object",
"properties": { "properties": {
@ -361,6 +479,51 @@
"format": "uri" "format": "uri"
} }
} }
},
"llm_extraction": {
"type": "object",
"description": "Displayed when using LLM Extraction. Extracted data from the page following the schema defined.",
"nullable": true
},
"warning": {
"type": "string",
"nullable": true,
"description": "Can be displayed when using LLM Extraction. Warning message will let you know any issues with the extraction."
}
}
}
}
},
"CrawlStatusResponseObj": {
"type": "object",
"properties": {
"markdown": {
"type": "string"
},
"content": {
"type": "string"
},
"html": {
"type": "string",
"nullable": true,
"description": "Raw HTML content of the page if `includeHtml` is true"
},
"metadata": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"description": {
"type": "string"
},
"language": {
"type": "string",
"nullable": true
},
"sourceURL": {
"type": "string",
"format": "uri"
} }
} }
} }

2
apps/api/package.json
View File

@ -33,6 +33,7 @@
"express": "^4.18.2", "express": "^4.18.2",
"jest": "^29.6.3", "jest": "^29.6.3",
"jest-fetch-mock": "^3.0.3", "jest-fetch-mock": "^3.0.3",
"mammoth": "^1.7.2",
"nodemon": "^2.0.20", "nodemon": "^2.0.20",
"supabase": "^1.77.9", "supabase": "^1.77.9",
"supertest": "^6.3.3", "supertest": "^6.3.3",
@ -47,6 +48,7 @@
"@bull-board/express": "^5.8.0", "@bull-board/express": "^5.8.0",
"@devil7softwares/pos": "^1.0.2", "@devil7softwares/pos": "^1.0.2",
"@dqbd/tiktoken": "^1.0.13", "@dqbd/tiktoken": "^1.0.13",
"@hyperdx/node-opentelemetry": "^0.7.0",
"@logtail/node": "^0.4.12", "@logtail/node": "^0.4.12",
"@nangohq/node": "^0.36.33", "@nangohq/node": "^0.36.33",
"@sentry/node": "^7.48.0", "@sentry/node": "^7.48.0",

1583
apps/api/pnpm-lock.yaml
View File

File diff suppressed because it is too large Load Diff

582
apps/api/src/__tests__/e2e_withAuth/index.test.ts
View File

@ -82,7 +82,7 @@ describe("E2E Tests for API Routes", () => {
expect(response.body.data).toHaveProperty("markdown"); expect(response.body.data).toHaveProperty("markdown");
expect(response.body.data).toHaveProperty("metadata"); expect(response.body.data).toHaveProperty("metadata");
expect(response.body.data).not.toHaveProperty("html"); expect(response.body.data).not.toHaveProperty("html");
expect(response.body.data.content).toContain("🔥 FireCrawl"); expect(response.body.data.content).toContain("🔥 Firecrawl");
}, 30000); // 30 seconds timeout }, 30000); // 30 seconds timeout
it("should return a successful response with a valid API key and includeHtml set to true", async () => { it("should return a successful response with a valid API key and includeHtml set to true", async () => {
@ -100,10 +100,40 @@ describe("E2E Tests for API Routes", () => {
expect(response.body.data).toHaveProperty("markdown"); expect(response.body.data).toHaveProperty("markdown");
expect(response.body.data).toHaveProperty("html"); expect(response.body.data).toHaveProperty("html");
expect(response.body.data).toHaveProperty("metadata"); expect(response.body.data).toHaveProperty("metadata");
expect(response.body.data.content).toContain("🔥 FireCrawl"); expect(response.body.data.content).toContain("🔥 Firecrawl");
expect(response.body.data.markdown).toContain("🔥 FireCrawl"); expect(response.body.data.markdown).toContain("🔥 Firecrawl");
expect(response.body.data.html).toContain("<h1"); expect(response.body.data.html).toContain("<h1");
}, 30000); // 30 seconds timeout }, 30000); // 30 seconds timeout
it('should return a successful response for a valid scrape with PDF file', async () => {
const response = await request(TEST_URL)
.post('/v0/scrape')
.set('Authorization', `Bearer ${process.env.TEST_API_KEY}`)
.set('Content-Type', 'application/json')
.send({ url: 'https://arxiv.org/pdf/astro-ph/9301001.pdf' });
await new Promise((r) => setTimeout(r, 6000));
expect(response.statusCode).toBe(200);
expect(response.body).toHaveProperty('data');
expect(response.body.data).toHaveProperty('content');
expect(response.body.data).toHaveProperty('metadata');
expect(response.body.data.content).toContain('We present spectrophotometric observations of the Broad Line Radio Galaxy');
}, 60000); // 60 seconds
it('should return a successful response for a valid scrape with PDF file without explicit .pdf extension', async () => {
const response = await request(TEST_URL)
.post('/v0/scrape')
.set('Authorization', `Bearer ${process.env.TEST_API_KEY}`)
.set('Content-Type', 'application/json')
.send({ url: 'https://arxiv.org/pdf/astro-ph/9301001' });
await new Promise((r) => setTimeout(r, 6000));
expect(response.statusCode).toBe(200);
expect(response.body).toHaveProperty('data');
expect(response.body.data).toHaveProperty('content');
expect(response.body.data).toHaveProperty('metadata');
expect(response.body.data.content).toContain('We present spectrophotometric observations of the Broad Line Radio Galaxy');
}, 60000); // 60 seconds
}); });
describe("POST /v0/crawl", () => { describe("POST /v0/crawl", () => {
@ -171,7 +201,274 @@ describe("E2E Tests for API Routes", () => {
expect(secondResponse.body.error).toBe('Idempotency key already used'); expect(secondResponse.body.error).toBe('Idempotency key already used');
}); });
// Additional tests for insufficient credits? it("should return a successful response with a valid API key and valid includes option", async () => {
const crawlResponse = await request(TEST_URL)
.post("/v0/crawl")
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
.set("Content-Type", "application/json")
.send({
url: "https://mendable.ai",
limit: 10,
crawlerOptions: {
includes: ["blog/*"],
},
});
let response;
let isFinished = false;
while (!isFinished) {
response = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(response.statusCode).toBe(200);
expect(response.body).toHaveProperty("status");
isFinished = response.body.status === "completed";
if (!isFinished) {
await new Promise((resolve) => setTimeout(resolve, 1000)); // Wait for 1 second before checking again
}
}
const completedResponse = response;
const urls = completedResponse.body.data.map(
(item: any) => item.metadata?.sourceURL
);
expect(urls.length).toBeGreaterThan(5);
urls.forEach((url: string) => {
console.log({url})
expect(url.startsWith("https://www.mendable.ai/blog/")).toBeTruthy();
});
expect(completedResponse.statusCode).toBe(200);
expect(completedResponse.body).toHaveProperty("status");
expect(completedResponse.body.status).toBe("completed");
expect(completedResponse.body).toHaveProperty("data");
expect(completedResponse.body.data[0]).toHaveProperty("content");
expect(completedResponse.body.data[0]).toHaveProperty("markdown");
expect(completedResponse.body.data[0]).toHaveProperty("metadata");
expect(completedResponse.body.data[0].content).toContain("Mendable");
}, 60000); // 60 seconds
it("should return a successful response with a valid API key and valid excludes option", async () => {
const crawlResponse = await request(TEST_URL)
.post("/v0/crawl")
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
.set("Content-Type", "application/json")
.send({
url: "https://mendable.ai",
limit: 10,
crawlerOptions: {
excludes: ["blog/*"],
},
});
let isFinished = false;
let response;
while (!isFinished) {
response = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(response.statusCode).toBe(200);
expect(response.body).toHaveProperty("status");
isFinished = response.body.status === "completed";
if (!isFinished) {
await new Promise((resolve) => setTimeout(resolve, 1000)); // Wait for 1 second before checking again
}
}
const completedResponse = response;
const urls = completedResponse.body.data.map(
(item: any) => item.metadata?.sourceURL
);
expect(urls.length).toBeGreaterThan(5);
urls.forEach((url: string) => {
expect(url.startsWith("https://wwww.mendable.ai/blog/")).toBeFalsy();
});
}, 90000); // 90 seconds
it("should return a successful response with a valid API key and limit to 3", async () => {
const crawlResponse = await request(TEST_URL)
.post("/v0/crawl")
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
.set("Content-Type", "application/json")
.send({
url: "https://mendable.ai",
crawlerOptions: { limit: 3 },
});
let isFinished = false;
let response;
while (!isFinished) {
response = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(response.statusCode).toBe(200);
expect(response.body).toHaveProperty("status");
isFinished = response.body.status === "completed";
if (!isFinished) {
await new Promise((resolve) => setTimeout(resolve, 1000)); // Wait for 1 second before checking again
}
}
const completedResponse = response;
expect(completedResponse.statusCode).toBe(200);
expect(completedResponse.body).toHaveProperty("status");
expect(completedResponse.body.status).toBe("completed");
expect(completedResponse.body).toHaveProperty("data");
expect(completedResponse.body.data.length).toBe(3);
expect(completedResponse.body.data[0]).toHaveProperty("content");
expect(completedResponse.body.data[0]).toHaveProperty("markdown");
expect(completedResponse.body.data[0]).toHaveProperty("metadata");
expect(completedResponse.body.data[0].content).toContain("Mendable");
}, 60000); // 60 seconds
it("should return a successful response with max depth option for a valid crawl job", async () => {
const crawlResponse = await request(TEST_URL)
.post("/v0/crawl")
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
.set("Content-Type", "application/json")
.send({
url: "https://www.scrapethissite.com",
crawlerOptions: { maxDepth: 2 },
});
expect(crawlResponse.statusCode).toBe(200);
const response = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(response.statusCode).toBe(200);
expect(response.body).toHaveProperty("status");
expect(response.body.status).toBe("active");
// wait for 60 seconds
await new Promise((r) => setTimeout(r, 60000));
const completedResponse = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(completedResponse.statusCode).toBe(200);
expect(completedResponse.body).toHaveProperty("status");
expect(completedResponse.body.status).toBe("completed");
expect(completedResponse.body).toHaveProperty("data");
expect(completedResponse.body.data[0]).toHaveProperty("content");
expect(completedResponse.body.data[0]).toHaveProperty("markdown");
expect(completedResponse.body.data[0]).toHaveProperty("metadata");
const urls = completedResponse.body.data.map(
(item: any) => item.metadata?.sourceURL
);
expect(urls.length).toBeGreaterThan(1);
// Check if all URLs have a maximum depth of 1
urls.forEach((url: string) => {
const depth = new URL(url).pathname.split("/").filter(Boolean).length;
expect(depth).toBeLessThanOrEqual(1);
});
}, 120000);
// it("should return a successful response with a valid API key and valid limit option", async () => {
// const crawlResponse = await request(TEST_URL)
// .post("/v0/crawl")
// .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
// .set("Content-Type", "application/json")
// .send({
// url: "https://mendable.ai",
// crawlerOptions: { limit: 10 },
// });
// const response = await request(TEST_URL)
// .get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
// .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
// expect(response.statusCode).toBe(200);
// expect(response.body).toHaveProperty("status");
// expect(response.body.status).toBe("active");
// let isCompleted = false;
// while (!isCompleted) {
// const statusCheckResponse = await request(TEST_URL)
// .get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
// .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
// expect(statusCheckResponse.statusCode).toBe(200);
// isCompleted = statusCheckResponse.body.status === "completed";
// if (!isCompleted) {
// await new Promise((resolve) => setTimeout(resolve, 1000)); // Wait for 1 second before checking again
// }
// }
// const completedResponse = await request(TEST_URL)
// .get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
// .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
// expect(completedResponse.statusCode).toBe(200);
// expect(completedResponse.body).toHaveProperty("status");
// expect(completedResponse.body.status).toBe("completed");
// expect(completedResponse.body).toHaveProperty("data");
// expect(completedResponse.body.data.length).toBe(10);
// expect(completedResponse.body.data[0]).toHaveProperty("content");
// expect(completedResponse.body.data[0]).toHaveProperty("markdown");
// expect(completedResponse.body.data[0]).toHaveProperty("metadata");
// expect(completedResponse.body.data[0].content).toContain("Mendable");
// expect(completedResponse.body.data[0].content).not.toContain("main menu");
// }, 60000); // 60 seconds
it("should return a successful response for a valid crawl job with includeHtml set to true option", async () => {
const crawlResponse = await request(TEST_URL)
.post("/v0/crawl")
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
.set("Content-Type", "application/json")
.send({
url: "https://firecrawl.dev",
pageOptions: { includeHtml: true },
});
expect(crawlResponse.statusCode).toBe(200);
const response = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(response.statusCode).toBe(200);
expect(response.body).toHaveProperty("status");
expect(response.body.status).toBe("active");
let isCompleted = false;
while (!isCompleted) {
const statusCheckResponse = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(statusCheckResponse.statusCode).toBe(200);
isCompleted = statusCheckResponse.body.status === "completed";
if (!isCompleted) {
await new Promise((resolve) => setTimeout(resolve, 1000)); // Wait for 1 second before checking again
}
}
const completedResponse = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(completedResponse.statusCode).toBe(200);
expect(completedResponse.body).toHaveProperty("status");
expect(completedResponse.body.status).toBe("completed");
expect(completedResponse.body).toHaveProperty("data");
expect(completedResponse.body.data[0]).toHaveProperty("content");
expect(completedResponse.body.data[0]).toHaveProperty("markdown");
expect(completedResponse.body.data[0]).toHaveProperty("metadata");
// 120 seconds
expect(completedResponse.body.data[0]).toHaveProperty("html");
expect(completedResponse.body.data[0]).toHaveProperty("metadata");
expect(completedResponse.body.data[0].content).toContain("🔥 Firecrawl");
expect(completedResponse.body.data[0].markdown).toContain("Firecrawl");
expect(completedResponse.body.data[0].html).toContain("<h1");
}, 60000);
}); });
describe("POST /v0/crawlWebsitePreview", () => { describe("POST /v0/crawlWebsitePreview", () => {
@ -201,6 +498,16 @@ describe("E2E Tests for API Routes", () => {
// expect(response.body.error).toContain("Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it."); // expect(response.body.error).toContain("Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it.");
// }); // });
it("should return a timeout error when scraping takes longer than the specified timeout", async () => {
const response = await request(TEST_URL)
.post("/v0/scrape")
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
.set("Content-Type", "application/json")
.send({ url: "https://firecrawl.dev", timeout: 1000 });
expect(response.statusCode).toBe(408);
}, 3000);
it("should return a successful response with a valid API key", async () => { it("should return a successful response with a valid API key", async () => {
const response = await request(TEST_URL) const response = await request(TEST_URL)
.post("/v0/crawlWebsitePreview") .post("/v0/crawlWebsitePreview")
@ -263,7 +570,7 @@ describe("E2E Tests for API Routes", () => {
expect(response.statusCode).toBe(404); expect(response.statusCode).toBe(404);
}); });
it("should return a successful response for a valid crawl job", async () => { it("should return a successful crawl status response for a valid crawl job", async () => {
const crawlResponse = await request(TEST_URL) const crawlResponse = await request(TEST_URL)
.post("/v0/crawl") .post("/v0/crawl")
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`) .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
@ -271,27 +578,67 @@ describe("E2E Tests for API Routes", () => {
.send({ url: "https://firecrawl.dev" }); .send({ url: "https://firecrawl.dev" });
expect(crawlResponse.statusCode).toBe(200); expect(crawlResponse.statusCode).toBe(200);
const response = await request(TEST_URL) let isCompleted = false;
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`) let completedResponse;
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(response.statusCode).toBe(200);
expect(response.body).toHaveProperty("status");
expect(response.body.status).toBe("active");
// wait for 30 seconds while (!isCompleted) {
await new Promise((r) => setTimeout(r, 30000)); const response = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(response.statusCode).toBe(200);
expect(response.body).toHaveProperty("status");
const completedResponse = await request(TEST_URL) if (response.body.status === "completed") {
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`) isCompleted = true;
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`); completedResponse = response;
expect(completedResponse.statusCode).toBe(200); } else {
await new Promise((r) => setTimeout(r, 1000)); // Wait for 1 second before checking again
}
}
expect(completedResponse.body).toHaveProperty("status"); expect(completedResponse.body).toHaveProperty("status");
expect(completedResponse.body.status).toBe("completed"); expect(completedResponse.body.status).toBe("completed");
expect(completedResponse.body).toHaveProperty("data"); expect(completedResponse.body).toHaveProperty("data");
expect(completedResponse.body.data[0]).toHaveProperty("content"); expect(completedResponse.body.data[0]).toHaveProperty("content");
expect(completedResponse.body.data[0]).toHaveProperty("markdown"); expect(completedResponse.body.data[0]).toHaveProperty("markdown");
expect(completedResponse.body.data[0]).toHaveProperty("metadata"); expect(completedResponse.body.data[0]).toHaveProperty("metadata");
expect(completedResponse.body.data[0].content).toContain("🔥 FireCrawl"); expect(completedResponse.body.data[0].content).toContain("🔥 Firecrawl");
}, 60000); // 60 seconds
it('should return a successful response for a valid crawl job with PDF files without explicit .pdf extension', async () => {
const crawlResponse = await request(TEST_URL)
.post('/v0/crawl')
.set('Authorization', `Bearer ${process.env.TEST_API_KEY}`)
.set('Content-Type', 'application/json')
.send({ url: 'https://arxiv.org/pdf/astro-ph/9301001', crawlerOptions: { limit: 10, excludes: [ 'list/*', 'login', 'abs/*', 'static/*', 'about/*', 'archive/*' ] }});
expect(crawlResponse.statusCode).toBe(200);
let isCompleted = false;
let completedResponse;
while (!isCompleted) {
const response = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set('Authorization', `Bearer ${process.env.TEST_API_KEY}`);
expect(response.statusCode).toBe(200);
expect(response.body).toHaveProperty('status');
if (response.body.status === 'completed') {
isCompleted = true;
completedResponse = response;
} else {
await new Promise((r) => setTimeout(r, 1000)); // Wait for 1 second before checking again
}
}
expect(completedResponse.body.status).toBe('completed');
expect(completedResponse.body).toHaveProperty('data');
expect(completedResponse.body.data.length).toEqual(1);
expect(completedResponse.body.data).toEqual(
expect.arrayContaining([
expect.objectContaining({
content: expect.stringContaining('asymmetries might represent, for instance, preferred source orientations to our line of sight.')
})
])
);
}, 60000); // 60 seconds }, 60000); // 60 seconds
it("should return a successful response with max depth option for a valid crawl job", async () => { it("should return a successful response with max depth option for a valid crawl job", async () => {
@ -305,18 +652,21 @@ describe("E2E Tests for API Routes", () => {
}); });
expect(crawlResponse.statusCode).toBe(200); expect(crawlResponse.statusCode).toBe(200);
const response = await request(TEST_URL) let isCompleted = false;
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`) let completedResponse;
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(response.statusCode).toBe(200);
expect(response.body).toHaveProperty("status");
expect(response.body.status).toBe("active");
// wait for 60 seconds
await new Promise((r) => setTimeout(r, 60000));
const completedResponse = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
while (!isCompleted) {
const response = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(response.statusCode).toBe(200);
expect(response.body).toHaveProperty("status");
if (response.body.status === "completed") {
isCompleted = true;
completedResponse = response;
}
}
expect(completedResponse.statusCode).toBe(200); expect(completedResponse.statusCode).toBe(200);
expect(completedResponse.body).toHaveProperty("status"); expect(completedResponse.body).toHaveProperty("status");
expect(completedResponse.body.status).toBe("completed"); expect(completedResponse.body.status).toBe("completed");
@ -372,8 +722,8 @@ describe("E2E Tests for API Routes", () => {
// 120 seconds // 120 seconds
expect(completedResponse.body.data[0]).toHaveProperty("html"); expect(completedResponse.body.data[0]).toHaveProperty("html");
expect(completedResponse.body.data[0]).toHaveProperty("metadata"); expect(completedResponse.body.data[0]).toHaveProperty("metadata");
expect(completedResponse.body.data[0].content).toContain("🔥 FireCrawl"); expect(completedResponse.body.data[0].content).toContain("🔥 Firecrawl");
expect(completedResponse.body.data[0].markdown).toContain("FireCrawl"); expect(completedResponse.body.data[0].markdown).toContain("Firecrawl");
expect(completedResponse.body.data[0].html).toContain("<h1"); expect(completedResponse.body.data[0].html).toContain("<h1");
}, 60000); }, 60000);
}); // 60 seconds }); // 60 seconds
@ -386,10 +736,8 @@ describe("E2E Tests for API Routes", () => {
.send({ url: "https://jestjs.io" }); .send({ url: "https://jestjs.io" });
expect(crawlResponse.statusCode).toBe(200); expect(crawlResponse.statusCode).toBe(200);
// wait for 30 seconds // wait for 30 seconds
await new Promise((r) => setTimeout(r, 10000)); await new Promise((r) => setTimeout(r, 20000));
const response = await request(TEST_URL) const response = await request(TEST_URL)
.delete(`/v0/crawl/cancel/${crawlResponse.body.jobId}`) .delete(`/v0/crawl/cancel/${crawlResponse.body.jobId}`)
@ -398,7 +746,7 @@ describe("E2E Tests for API Routes", () => {
expect(response.body).toHaveProperty("status"); expect(response.body).toHaveProperty("status");
expect(response.body.status).toBe("cancelled"); expect(response.body.status).toBe("cancelled");
await new Promise((r) => setTimeout(r, 20000)); await new Promise((r) => setTimeout(r, 10000));
const completedResponse = await request(TEST_URL) const completedResponse = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`) .get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
@ -415,8 +763,6 @@ describe("E2E Tests for API Routes", () => {
}, 60000); // 60 seconds }, 60000); // 60 seconds
describe("POST /v0/scrape with LLM Extraction", () => { describe("POST /v0/scrape with LLM Extraction", () => {
it("should extract data using LLM extraction mode", async () => { it("should extract data using LLM extraction mode", async () => {
const response = await request(TEST_URL) const response = await request(TEST_URL)
@ -526,6 +872,107 @@ describe("E2E Tests for API Routes", () => {
// }, 120000); // 120 secs // }, 120000); // 120 secs
// }); // });
describe("POST /v0/crawl with fast mode", () => {
it("should complete the crawl under 20 seconds", async () => {
const startTime = Date.now();
const crawlResponse = await request(TEST_URL)
.post("/v0/crawl")
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
.set("Content-Type", "application/json")
.send({
url: "https://flutterbricks.com",
crawlerOptions: {
mode: "fast"
}
});
expect(crawlResponse.statusCode).toBe(200);
const jobId = crawlResponse.body.jobId;
let statusResponse;
let isFinished = false;
while (!isFinished) {
statusResponse = await request(TEST_URL)
.get(`/v0/crawl/status/${jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(statusResponse.statusCode).toBe(200);
isFinished = statusResponse.body.status === "completed";
if (!isFinished) {
await new Promise((resolve) => setTimeout(resolve, 1000)); // Wait for 1 second before checking again
}
}
const endTime = Date.now();
const timeElapsed = (endTime - startTime) / 1000; // Convert to seconds
console.log(`Time elapsed: ${timeElapsed} seconds`);
expect(statusResponse.body.status).toBe("completed");
expect(statusResponse.body).toHaveProperty("data");
expect(statusResponse.body.data[0]).toHaveProperty("content");
expect(statusResponse.body.data[0]).toHaveProperty("markdown");
const results = statusResponse.body.data;
// results.forEach((result, i) => {
// console.log(result.metadata.sourceURL);
// });
expect(results.length).toBeGreaterThanOrEqual(10);
expect(results.length).toBeLessThanOrEqual(15);
}, 20000);
// it("should complete the crawl in more than 10 seconds", async () => {
// const startTime = Date.now();
// const crawlResponse = await request(TEST_URL)
// .post("/v0/crawl")
// .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
// .set("Content-Type", "application/json")
// .send({
// url: "https://flutterbricks.com",
// });
// expect(crawlResponse.statusCode).toBe(200);
// const jobId = crawlResponse.body.jobId;
// let statusResponse;
// let isFinished = false;
// while (!isFinished) {
// statusResponse = await request(TEST_URL)
// .get(`/v0/crawl/status/${jobId}`)
// .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
// expect(statusResponse.statusCode).toBe(200);
// isFinished = statusResponse.body.status === "completed";
// if (!isFinished) {
// await new Promise((resolve) => setTimeout(resolve, 1000)); // Wait for 1 second before checking again
// }
// }
// const endTime = Date.now();
// const timeElapsed = (endTime - startTime) / 1000; // Convert to seconds
// console.log(`Time elapsed: ${timeElapsed} seconds`);
// expect(statusResponse.body.status).toBe("completed");
// expect(statusResponse.body).toHaveProperty("data");
// expect(statusResponse.body.data[0]).toHaveProperty("content");
// expect(statusResponse.body.data[0]).toHaveProperty("markdown");
// const results = statusResponse.body.data;
// // results.forEach((result, i) => {
// // console.log(result.metadata.sourceURL);
// // });
// expect(results.length).toBeGreaterThanOrEqual(10);
// expect(results.length).toBeLessThanOrEqual(15);
// }, 50000);// 15 seconds timeout to account for network delays
});
describe("GET /is-production", () => { describe("GET /is-production", () => {
it("should return the production status", async () => { it("should return the production status", async () => {
const response = await request(TEST_URL).get("/is-production"); const response = await request(TEST_URL).get("/is-production");
@ -533,4 +980,65 @@ describe("E2E Tests for API Routes", () => {
expect(response.body).toHaveProperty("isProduction"); expect(response.body).toHaveProperty("isProduction");
}); });
}); });
describe("Rate Limiter", () => {
it("should return 429 when rate limit is exceeded for preview token", async () => {
for (let i = 0; i < 5; i++) {
const response = await request(TEST_URL)
.post("/v0/scrape")
.set("Authorization", `Bearer this_is_just_a_preview_token`)
.set("Content-Type", "application/json")
.send({ url: "https://www.scrapethissite.com" });
expect(response.statusCode).toBe(200);
}
const response = await request(TEST_URL)
.post("/v0/scrape")
.set("Authorization", `Bearer this_is_just_a_preview_token`)
.set("Content-Type", "application/json")
.send({ url: "https://www.scrapethissite.com" });
expect(response.statusCode).toBe(429);
}, 60000);
});
// it("should return 429 when rate limit is exceeded for API key", async () => {
// for (let i = 0; i < parseInt(process.env.RATE_LIMIT_TEST_API_KEY_SCRAPE); i++) {
// const response = await request(TEST_URL)
// .post("/v0/scrape")
// .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
// .set("Content-Type", "application/json")
// .send({ url: "https://www.scrapethissite.com" });
// expect(response.statusCode).toBe(200);
// }
// const response = await request(TEST_URL)
// .post("/v0/scrape")
// .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
// .set("Content-Type", "application/json")
// .send({ url: "https://www.scrapethissite.com" });
// expect(response.statusCode).toBe(429);
// }, 60000);
// it("should return 429 when rate limit is exceeded for API key", async () => {
// for (let i = 0; i < parseInt(process.env.RATE_LIMIT_TEST_API_KEY_CRAWL); i++) {
// const response = await request(TEST_URL)
// .post("/v0/crawl")
// .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
// .set("Content-Type", "application/json")
// .send({ url: "https://www.scrapethissite.com" });
// expect(response.statusCode).toBe(200);
// }
// const response = await request(TEST_URL)
// .post("/v0/crawl")
// .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
// .set("Content-Type", "application/json")
// .send({ url: "https://www.scrapethissite.com" });
// expect(response.statusCode).toBe(429);
// }, 60000);
}); });

137
apps/api/src/controllers/auth.ts
View File

@ -1,14 +1,25 @@
import { parseApi } from "../../src/lib/parseApi"; import { parseApi } from "../../src/lib/parseApi";
import { getRateLimiter } from "../../src/services/rate-limiter"; import { getRateLimiter, } from "../../src/services/rate-limiter";
import { AuthResponse, RateLimiterMode } from "../../src/types"; import { AuthResponse, RateLimiterMode } from "../../src/types";
import { supabase_service } from "../../src/services/supabase"; import { supabase_service } from "../../src/services/supabase";
import { withAuth } from "../../src/lib/withAuth"; import { withAuth } from "../../src/lib/withAuth";
import { RateLimiterRedis } from "rate-limiter-flexible";
import { setTraceAttributes } from '@hyperdx/node-opentelemetry';
export async function authenticateUser(req, res, mode?: RateLimiterMode) : Promise<AuthResponse> { export async function authenticateUser(req, res, mode?: RateLimiterMode) : Promise<AuthResponse> {
return withAuth(supaAuthenticateUser)(req, res, mode); return withAuth(supaAuthenticateUser)(req, res, mode);
} }
function setTrace(team_id: string, api_key: string) {
try {
setTraceAttributes({
team_id,
api_key
});
} catch (error) {
console.error('Error setting trace attributes:', error);
}
}
export async function supaAuthenticateUser( export async function supaAuthenticateUser(
req, req,
res, res,
@ -19,7 +30,6 @@ export async function supaAuthenticateUser(
error?: string; error?: string;
status?: number; status?: number;
}> { }> {
const authHeader = req.headers.authorization; const authHeader = req.headers.authorization;
if (!authHeader) { if (!authHeader) {
return { success: false, error: "Unauthorized", status: 401 }; return { success: false, error: "Unauthorized", status: 401 };
@ -33,13 +43,87 @@ export async function supaAuthenticateUser(
}; };
} }
const incomingIP = (req.headers["x-forwarded-for"] ||
req.socket.remoteAddress) as string;
const iptoken = incomingIP + token;
let rateLimiter: RateLimiterRedis;
let subscriptionData: { team_id: string, plan: string } | null = null;
let normalizedApi: string;
if (token == "this_is_just_a_preview_token") {
rateLimiter = getRateLimiter(RateLimiterMode.Preview, token);
} else {
normalizedApi = parseApi(token);
const { data, error } = await supabase_service.rpc(
'get_key_and_price_id_2', { api_key: normalizedApi }
);
// get_key_and_price_id_2 rpc definition:
// create or replace function get_key_and_price_id_2(api_key uuid)
// returns table(key uuid, team_id uuid, price_id text) as $$
// begin
// if api_key is null then
// return query
// select null::uuid as key, null::uuid as team_id, null::text as price_id;
// end if;
// return query
// select ak.key, ak.team_id, s.price_id
// from api_keys ak
// left join subscriptions s on ak.team_id = s.team_id
// where ak.key = api_key;
// end;
// $$ language plpgsql;
if (error) {
console.error('Error fetching key and price_id:', error);
} else {
// console.log('Key and Price ID:', data);
}
if (error || !data || data.length === 0) {
return {
success: false,
error: "Unauthorized: Invalid token",
status: 401,
};
}
const team_id = data[0].team_id;
const plan = getPlanByPriceId(data[0].price_id);
// HyperDX Logging
setTrace(team_id, normalizedApi);
subscriptionData = {
team_id: team_id,
plan: plan
}
switch (mode) {
case RateLimiterMode.Crawl:
rateLimiter = getRateLimiter(RateLimiterMode.Crawl, token, subscriptionData.plan);
break;
case RateLimiterMode.Scrape:
rateLimiter = getRateLimiter(RateLimiterMode.Scrape, token, subscriptionData.plan);
break;
case RateLimiterMode.CrawlStatus:
rateLimiter = getRateLimiter(RateLimiterMode.CrawlStatus, token);
break;
case RateLimiterMode.Search:
rateLimiter = getRateLimiter(RateLimiterMode.Search, token);
break;
case RateLimiterMode.Preview:
rateLimiter = getRateLimiter(RateLimiterMode.Preview, token);
break;
default:
rateLimiter = getRateLimiter(RateLimiterMode.Crawl, token);
break;
// case RateLimiterMode.Search:
// rateLimiter = await searchRateLimiter(RateLimiterMode.Search, token);
// break;
}
}
try { try {
const incomingIP = (req.headers["x-forwarded-for"] || await rateLimiter.consume(iptoken);
req.socket.remoteAddress) as string;
const iptoken = incomingIP + token;
await getRateLimiter(
token === "this_is_just_a_preview_token" ? RateLimiterMode.Preview : mode
).consume(iptoken);
} catch (rateLimiterRes) { } catch (rateLimiterRes) {
console.error(rateLimiterRes); console.error(rateLimiterRes);
return { return {
@ -66,19 +150,36 @@ export async function supaAuthenticateUser(
// return { success: false, error: "Unauthorized: Invalid token", status: 401 }; // return { success: false, error: "Unauthorized: Invalid token", status: 401 };
} }
const normalizedApi = parseApi(token);
// make sure api key is valid, based on the api_keys table in supabase // make sure api key is valid, based on the api_keys table in supabase
const { data, error } = await supabase_service if (!subscriptionData) {
normalizedApi = parseApi(token);
const { data, error } = await supabase_service
.from("api_keys") .from("api_keys")
.select("*") .select("*")
.eq("key", normalizedApi); .eq("key", normalizedApi);
if (error || !data || data.length === 0) {
return { if (error || !data || data.length === 0) {
success: false, return {
error: "Unauthorized: Invalid token", success: false,
status: 401, error: "Unauthorized: Invalid token",
}; status: 401,
};
}
subscriptionData = data[0];
} }
return { success: true, team_id: data[0].team_id }; return { success: true, team_id: subscriptionData.team_id };
}
function getPlanByPriceId(price_id: string) {
switch (price_id) {
case process.env.STRIPE_PRICE_ID_STANDARD:
return 'standard';
case process.env.STRIPE_PRICE_ID_SCALE:
return 'scale';
default:
return 'starter';
}
} }

28
apps/api/src/controllers/scrape.ts
View File

@ -15,6 +15,7 @@ export async function scrapeHelper(
crawlerOptions: any, crawlerOptions: any,
pageOptions: PageOptions, pageOptions: PageOptions,
extractorOptions: ExtractorOptions, extractorOptions: ExtractorOptions,
timeout: number
): Promise<{ ): Promise<{
success: boolean; success: boolean;
error?: string; error?: string;
@ -30,7 +31,6 @@ export async function scrapeHelper(
return { success: false, error: "Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it.", returnCode: 403 }; return { success: false, error: "Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it.", returnCode: 403 };
} }
const a = new WebScraperDataProvider(); const a = new WebScraperDataProvider();
await a.setOptions({ await a.setOptions({
mode: "single_urls", mode: "single_urls",
@ -42,7 +42,19 @@ export async function scrapeHelper(
extractorOptions: extractorOptions, extractorOptions: extractorOptions,
}); });
const docs = await a.getDocuments(false); const timeoutPromise = new Promise<{ success: boolean; error?: string; returnCode: number }>((_, reject) =>
setTimeout(() => reject({ success: false, error: "Request timed out. Increase the timeout by passing `timeout` param to the request.", returnCode: 408 }), timeout)
);
const docsPromise = a.getDocuments(false);
let docs;
try {
docs = await Promise.race([docsPromise, timeoutPromise]);
} catch (error) {
return error;
}
// make sure doc.content is not empty // make sure doc.content is not empty
const filteredDocs = docs.filter( const filteredDocs = docs.filter(
(doc: { content?: string }) => doc.content && doc.content.trim().length > 0 (doc: { content?: string }) => doc.content && doc.content.trim().length > 0
@ -51,12 +63,11 @@ export async function scrapeHelper(
return { success: true, error: "No page found", returnCode: 200 }; return { success: true, error: "No page found", returnCode: 200 };
} }
let creditsToBeBilled = filteredDocs.length;
let creditsToBeBilled = filteredDocs.length;
const creditsPerLLMExtract = 5; const creditsPerLLMExtract = 5;
if (extractorOptions.mode === "llm-extraction"){ if (extractorOptions.mode === "llm-extraction") {
creditsToBeBilled = creditsToBeBilled + (creditsPerLLMExtract * filteredDocs.length) creditsToBeBilled = creditsToBeBilled + (creditsPerLLMExtract * filteredDocs.length);
} }
const billingResult = await billTeam( const billingResult = await billTeam(
@ -95,7 +106,11 @@ export async function scrapeController(req: Request, res: Response) {
const extractorOptions = req.body.extractorOptions ?? { const extractorOptions = req.body.extractorOptions ?? {
mode: "markdown" mode: "markdown"
} }
if (extractorOptions.mode === "llm-extraction") {
pageOptions.onlyMainContent = true;
}
const origin = req.body.origin ?? "api"; const origin = req.body.origin ?? "api";
const timeout = req.body.timeout ?? 30000; // Default timeout of 30 seconds
try { try {
const { success: creditsCheckSuccess, message: creditsCheckMessage } = const { success: creditsCheckSuccess, message: creditsCheckMessage } =
@ -114,6 +129,7 @@ export async function scrapeController(req: Request, res: Response) {
crawlerOptions, crawlerOptions,
pageOptions, pageOptions,
extractorOptions, extractorOptions,
timeout
); );
const endTime = new Date().getTime(); const endTime = new Date().getTime();
const timeTakenInSeconds = (endTime - startTime) / 1000; const timeTakenInSeconds = (endTime - startTime) / 1000;

7
apps/api/src/index.ts
View File

@ -5,6 +5,8 @@ import "dotenv/config";
import { getWebScraperQueue } from "./services/queue-service"; import { getWebScraperQueue } from "./services/queue-service";
import { redisClient } from "./services/rate-limiter"; import { redisClient } from "./services/rate-limiter";
import { v0Router } from "./routes/v0"; import { v0Router } from "./routes/v0";
import { initSDK } from '@hyperdx/node-opentelemetry';
const { createBullBoard } = require("@bull-board/api"); const { createBullBoard } = require("@bull-board/api");
const { BullAdapter } = require("@bull-board/api/bullAdapter"); const { BullAdapter } = require("@bull-board/api/bullAdapter");
const { ExpressAdapter } = require("@bull-board/express"); const { ExpressAdapter } = require("@bull-board/express");
@ -47,6 +49,11 @@ const DEFAULT_PORT = process.env.PORT ?? 3002;
const HOST = process.env.HOST ?? "localhost"; const HOST = process.env.HOST ?? "localhost";
redisClient.connect(); redisClient.connect();
// HyperDX OpenTelemetry
if(process.env.ENV === 'production') {
initSDK({ consoleCapture: true, additionalInstrumentations: []});
}
export function startServer(port = DEFAULT_PORT) { export function startServer(port = DEFAULT_PORT) {
const server = app.listen(Number(port), HOST, () => { const server = app.listen(Number(port), HOST, () => {

26
apps/api/src/lib/LLM-extraction/models.ts
View File

@ -1,30 +1,43 @@
import OpenAI from "openai"; import OpenAI from "openai";
import { Document } from "../../lib/entities"; import { Document } from "../../lib/entities";
import { numTokensFromString } from "./helpers";
export type ScraperCompletionResult = { export type ScraperCompletionResult = {
data: any | null; data: any | null;
url: string; url: string;
}; };
const maxTokens = 32000;
const modifier = 4;
const defaultPrompt = const defaultPrompt =
"You are a professional web scraper. Extract the contents of the webpage"; "You are a professional web scraper. Extract the contents of the webpage";
function prepareOpenAIDoc( function prepareOpenAIDoc(
document: Document document: Document
): OpenAI.Chat.Completions.ChatCompletionContentPart[] { ): [OpenAI.Chat.Completions.ChatCompletionContentPart[], number] {
// Check if the markdown content exists in the document let markdown = document.markdown;
if (!document.markdown) {
// Check if the markdown content exists in the document
if (!markdown) {
throw new Error( throw new Error(
"Markdown content is missing in the document. This is likely due to an error in the scraping process. Please try again or reach out to help@mendable.ai" "Markdown content is missing in the document. This is likely due to an error in the scraping process. Please try again or reach out to help@mendable.ai"
); );
} }
return [{ type: "text", text: document.markdown }]; // count number of tokens
const numTokens = numTokensFromString(document.markdown, "gpt-4");
if (numTokens > maxTokens) {
// trim the document to the maximum number of tokens, tokens != characters
markdown = markdown.slice(0, (maxTokens * modifier));
}
return [[{ type: "text", text: markdown }], numTokens];
} }
export async function generateOpenAICompletions({ export async function generateOpenAICompletions({
client, client,
model = "gpt-4-turbo", model = "gpt-4o",
document, document,
schema, //TODO - add zod dynamic type checking schema, //TODO - add zod dynamic type checking
prompt = defaultPrompt, prompt = defaultPrompt,
@ -38,7 +51,7 @@ export async function generateOpenAICompletions({
temperature?: number; temperature?: number;
}): Promise<Document> { }): Promise<Document> {
const openai = client as OpenAI; const openai = client as OpenAI;
const content = prepareOpenAIDoc(document); const [content, numTokens] = prepareOpenAIDoc(document);
const completion = await openai.chat.completions.create({ const completion = await openai.chat.completions.create({
model, model,
@ -72,6 +85,7 @@ export async function generateOpenAICompletions({
return { return {
...document, ...document,
llm_extraction: llmExtraction, llm_extraction: llmExtraction,
warning: numTokens > maxTokens ? `Page was trimmed to fit the maximum token limit defined by the LLM model (Max: ${maxTokens} tokens, Attemped: ${numTokens} tokens). If results are not good, email us at help@mendable.ai so we can help you.` : undefined,
}; };
} }

2
apps/api/src/lib/entities.ts
View File

@ -44,6 +44,7 @@ export type WebScraperOptions = {
limit?: number; limit?: number;
generateImgAltText?: boolean; generateImgAltText?: boolean;
replaceAllPathsWithAbsolutePaths?: boolean; replaceAllPathsWithAbsolutePaths?: boolean;
mode?: "default" | "fast"; // have a mode of some sort
}; };
pageOptions?: PageOptions; pageOptions?: PageOptions;
extractorOptions?: ExtractorOptions; extractorOptions?: ExtractorOptions;
@ -71,6 +72,7 @@ export class Document {
}; };
childrenLinks?: string[]; childrenLinks?: string[];
provider?: string; provider?: string;
warning?: string;
constructor(data: Partial<Document>) { constructor(data: Partial<Document>) {
if (!data.content) { if (!data.content) {

42
apps/api/src/lib/load-testing-example.ts Normal file
View File

@ -0,0 +1,42 @@
import { scrapWithFireEngine } from "../../src/scraper/WebScraper/single_url";
const delay = (ms: number) => new Promise((resolve) => setTimeout(resolve, ms));
const scrapInBatches = async (
urls: string[],
batchSize: number,
delayMs: number
) => {
let successCount = 0;
let errorCount = 0;
for (let i = 0; i < urls.length; i += batchSize) {
const batch = urls
.slice(i, i + batchSize)
.map((url) => scrapWithFireEngine(url));
try {
const results = await Promise.all(batch);
results.forEach((data, index) => {
if (data.trim() === "") {
errorCount++;
} else {
successCount++;
console.log(
`Scraping result ${i + index + 1}:`,
data.trim().substring(0, 20) + "..."
);
}
});
} catch (error) {
console.error("Error during scraping:", error);
}
await delay(delayMs);
}
console.log(`Total successful scrapes: ${successCount}`);
console.log(`Total errored scrapes: ${errorCount}`);
};
function run() {
const urls = Array.from({ length: 200 }, () => "https://scrapethissite.com");
scrapInBatches(urls, 10, 1000);
}

23
apps/api/src/main/runWebScraper.ts
View File

@ -17,8 +17,10 @@ export async function startWebScraperPipeline({
crawlerOptions: job.data.crawlerOptions, crawlerOptions: job.data.crawlerOptions,
pageOptions: job.data.pageOptions, pageOptions: job.data.pageOptions,
inProgress: (progress) => { inProgress: (progress) => {
partialDocs.push(progress.currentDocument); if (progress.currentDocument) {
job.progress({...progress, partialDocs: partialDocs}); partialDocs.push(progress.currentDocument);
job.progress({ ...progress, partialDocs: partialDocs });
}
}, },
onSuccess: (result) => { onSuccess: (result) => {
job.moveToCompleted(result); job.moveToCompleted(result);
@ -27,7 +29,7 @@ export async function startWebScraperPipeline({
job.moveToFailed(error); job.moveToFailed(error);
}, },
team_id: job.data.team_id, team_id: job.data.team_id,
bull_job_id: job.id.toString() bull_job_id: job.id.toString(),
})) as { success: boolean; message: string; docs: Document[] }; })) as { success: boolean; message: string; docs: Document[] };
} }
export async function runWebScraper({ export async function runWebScraper({
@ -63,26 +65,25 @@ export async function runWebScraper({
urls: [url], urls: [url],
crawlerOptions: crawlerOptions, crawlerOptions: crawlerOptions,
pageOptions: pageOptions, pageOptions: pageOptions,
bullJobId: bull_job_id bullJobId: bull_job_id,
}); });
} else { } else {
await provider.setOptions({ await provider.setOptions({
mode: mode, mode: mode,
urls: url.split(","), urls: url.split(","),
crawlerOptions: crawlerOptions, crawlerOptions: crawlerOptions,
pageOptions: pageOptions pageOptions: pageOptions,
}); });
} }
const docs = (await provider.getDocuments(false, (progress: Progress) => { const docs = (await provider.getDocuments(false, (progress: Progress) => {
inProgress(progress); inProgress(progress);
})) as Document[]; })) as Document[];
if (docs.length === 0) { if (docs.length === 0) {
return { return {
success: true, success: true,
message: "No pages found", message: "No pages found",
docs: [] docs: [],
}; };
} }
@ -95,18 +96,14 @@ export async function runWebScraper({
}) })
: docs.filter((doc) => doc.content.trim().length > 0); : docs.filter((doc) => doc.content.trim().length > 0);
const billingResult = await billTeam(team_id, filteredDocs.length);
const billingResult = await billTeam(
team_id,
filteredDocs.length
);
if (!billingResult.success) { if (!billingResult.success) {
// throw new Error("Failed to bill team, no subscription was found"); // throw new Error("Failed to bill team, no subscription was found");
return { return {
success: false, success: false,
message: "Failed to bill team, no subscription was found", message: "Failed to bill team, no subscription was found",
docs: [] docs: [],
}; };
} }

159
apps/api/src/scraper/WebScraper/crawler.ts
View File

@ -4,7 +4,7 @@ import { URL } from "url";
import { getLinksFromSitemap } from "./sitemap"; import { getLinksFromSitemap } from "./sitemap";
import async from "async"; import async from "async";
import { Progress } from "../../lib/entities"; import { Progress } from "../../lib/entities";
import { scrapWithScrapingBee } from "./single_url"; import { scrapSingleUrl, scrapWithScrapingBee } from "./single_url";
import robotsParser from "robots-parser"; import robotsParser from "robots-parser";
export class WebCrawler { export class WebCrawler {
@ -15,7 +15,7 @@ export class WebCrawler {
private maxCrawledLinks: number; private maxCrawledLinks: number;
private maxCrawledDepth: number; private maxCrawledDepth: number;
private visited: Set<string> = new Set(); private visited: Set<string> = new Set();
private crawledUrls: Set<string> = new Set(); private crawledUrls: Map<string, string> = new Map();
private limit: number; private limit: number;
private robotsTxtUrl: string; private robotsTxtUrl: string;
private robots: any; private robots: any;
@ -25,7 +25,7 @@ export class WebCrawler {
initialUrl, initialUrl,
includes, includes,
excludes, excludes,
maxCrawledLinks, maxCrawledLinks = 10000,
limit = 10000, limit = 10000,
generateImgAltText = false, generateImgAltText = false,
maxCrawledDepth = 10, maxCrawledDepth = 10,
@ -51,7 +51,6 @@ export class WebCrawler {
this.generateImgAltText = generateImgAltText ?? false; this.generateImgAltText = generateImgAltText ?? false;
} }
private filterLinks(sitemapLinks: string[], limit: number, maxDepth: number): string[] { private filterLinks(sitemapLinks: string[], limit: number, maxDepth: number): string[] {
return sitemapLinks return sitemapLinks
.filter((link) => { .filter((link) => {
@ -77,9 +76,22 @@ export class WebCrawler {
// Check if the link matches the include patterns, if any are specified // Check if the link matches the include patterns, if any are specified
if (this.includes.length > 0 && this.includes[0] !== "") { if (this.includes.length > 0 && this.includes[0] !== "") {
return this.includes.some((includePattern) => if (!this.includes.some((includePattern) =>
new RegExp(includePattern).test(path) new RegExp(includePattern).test(path)
); )) {
return false;
}
}
// Normalize the initial URL and the link to account for www and non-www versions
const normalizedInitialUrl = new URL(this.initialUrl);
const normalizedLink = new URL(link);
const initialHostname = normalizedInitialUrl.hostname.replace(/^www\./, '');
const linkHostname = normalizedLink.hostname.replace(/^www\./, '');
// Ensure the protocol and hostname match, and the path starts with the initial URL's path
if (linkHostname !== initialHostname || !normalizedLink.pathname.startsWith(normalizedInitialUrl.pathname)) {
return false;
} }
const isAllowed = this.robots.isAllowed(link, "FireCrawlAgent") ?? true; const isAllowed = this.robots.isAllowed(link, "FireCrawlAgent") ?? true;
@ -99,19 +111,21 @@ export class WebCrawler {
concurrencyLimit: number = 5, concurrencyLimit: number = 5,
limit: number = 10000, limit: number = 10000,
maxDepth: number = 10 maxDepth: number = 10
): Promise<string[]> { ): Promise<{ url: string, html: string }[]> {
// Fetch and parse robots.txt // Fetch and parse robots.txt
try { try {
const response = await axios.get(this.robotsTxtUrl); const response = await axios.get(this.robotsTxtUrl);
this.robots = robotsParser(this.robotsTxtUrl, response.data); this.robots = robotsParser(this.robotsTxtUrl, response.data);
} catch (error) { } catch (error) {
console.error(`Failed to fetch robots.txt from ${this.robotsTxtUrl}`); console.log(`Failed to fetch robots.txt from ${this.robotsTxtUrl}`);
} }
const sitemapLinks = await this.tryFetchSitemapLinks(this.initialUrl); const sitemapLinks = await this.tryFetchSitemapLinks(this.initialUrl);
if (sitemapLinks.length > 0) { if (sitemapLinks.length > 0) {
const filteredLinks = this.filterLinks(sitemapLinks, limit, maxDepth); let filteredLinks = this.filterLinks(sitemapLinks, limit, maxDepth);
return filteredLinks; return filteredLinks.map(link => ({ url: link, html: "" }));
} }
const urls = await this.crawlUrls( const urls = await this.crawlUrls(
@ -123,43 +137,58 @@ export class WebCrawler {
urls.length === 0 && urls.length === 0 &&
this.filterLinks([this.initialUrl], limit, this.maxCrawledDepth).length > 0 this.filterLinks([this.initialUrl], limit, this.maxCrawledDepth).length > 0
) { ) {
return [this.initialUrl]; return [{ url: this.initialUrl, html: "" }];
} }
// make sure to run include exclude here again // make sure to run include exclude here again
return this.filterLinks(urls, limit, this.maxCrawledDepth); const filteredUrls = this.filterLinks(urls.map(urlObj => urlObj.url), limit, this.maxCrawledDepth);
return filteredUrls.map(url => ({ url, html: urls.find(urlObj => urlObj.url === url)?.html || "" }));
} }
private async crawlUrls( private async crawlUrls(
urls: string[], urls: string[],
concurrencyLimit: number, concurrencyLimit: number,
inProgress?: (progress: Progress) => void inProgress?: (progress: Progress) => void,
): Promise<string[]> { ): Promise<{ url: string, html: string }[]> {
const queue = async.queue(async (task: string, callback) => { const queue = async.queue(async (task: string, callback) => {
if (this.crawledUrls.size >= this.maxCrawledLinks) { if (this.crawledUrls.size >= Math.min(this.maxCrawledLinks, this.limit)) {
if (callback && typeof callback === "function") { if (callback && typeof callback === "function") {
callback(); callback();
} }
return; return;
} }
const newUrls = await this.crawl(task); const newUrls = await this.crawl(task);
newUrls.forEach((url) => this.crawledUrls.add(url)); // add the initial url if not already added
// if (this.visited.size === 1) {
// let normalizedInitial = this.initialUrl;
// if (!normalizedInitial.endsWith("/")) {
// normalizedInitial = normalizedInitial + "/";
// }
// if (!newUrls.some(page => page.url === this.initialUrl)) {
// newUrls.push({ url: this.initialUrl, html: "" });
// }
// }
newUrls.forEach((page) => this.crawledUrls.set(page.url, page.html));
if (inProgress && newUrls.length > 0) { if (inProgress && newUrls.length > 0) {
inProgress({ inProgress({
current: this.crawledUrls.size, current: this.crawledUrls.size,
total: this.maxCrawledLinks, total: Math.min(this.maxCrawledLinks, this.limit),
status: "SCRAPING", status: "SCRAPING",
currentDocumentUrl: newUrls[newUrls.length - 1], currentDocumentUrl: newUrls[newUrls.length - 1].url,
}); });
} else if (inProgress) { } else if (inProgress) {
inProgress({ inProgress({
current: this.crawledUrls.size, current: this.crawledUrls.size,
total: this.maxCrawledLinks, total: Math.min(this.maxCrawledLinks, this.limit),
status: "SCRAPING", status: "SCRAPING",
currentDocumentUrl: task, currentDocumentUrl: task,
}); });
} }
await this.crawlUrls(newUrls, concurrencyLimit, inProgress); await this.crawlUrls(newUrls.map((p) => p.url), concurrencyLimit, inProgress);
if (callback && typeof callback === "function") { if (callback && typeof callback === "function") {
callback(); callback();
} }
@ -175,34 +204,48 @@ export class WebCrawler {
} }
); );
await queue.drain(); await queue.drain();
return Array.from(this.crawledUrls); return Array.from(this.crawledUrls.entries()).map(([url, html]) => ({ url, html }));
} }
async crawl(url: string): Promise<string[]> { async crawl(url: string): Promise<{url: string, html: string}[]> {
if (this.visited.has(url) || !this.robots.isAllowed(url, "FireCrawlAgent")) if (this.visited.has(url) || !this.robots.isAllowed(url, "FireCrawlAgent")){
return []; return [];
}
this.visited.add(url); this.visited.add(url);
if (!url.startsWith("http")) { if (!url.startsWith("http")) {
url = "https://" + url; url = "https://" + url;
} }
if (url.endsWith("/")) { if (url.endsWith("/")) {
url = url.slice(0, -1); url = url.slice(0, -1);
} }
if (this.isFile(url) || this.isSocialMediaOrEmail(url)) { if (this.isFile(url) || this.isSocialMediaOrEmail(url)) {
return []; return [];
} }
try { try {
let content; let content : string = "";
// If it is the first link, fetch with scrapingbee // If it is the first link, fetch with single url
if (this.visited.size === 1) { if (this.visited.size === 1) {
content = await scrapWithScrapingBee(url, "load"); const page = await scrapSingleUrl(url, {includeHtml: true});
content = page.html ?? ""
} else { } else {
const response = await axios.get(url); const response = await axios.get(url);
content = response.data; content = response.data ?? "";
} }
const $ = load(content); const $ = load(content);
let links: string[] = []; let links: {url: string, html: string}[] = [];
// Add the initial URL to the list of links
if(this.visited.size === 1)
{
links.push({url, html: content});
}
$("a").each((_, element) => { $("a").each((_, element) => {
const href = $(element).attr("href"); const href = $(element).attr("href");
@ -215,7 +258,6 @@ export class WebCrawler {
const path = url.pathname; const path = url.pathname;
if ( if (
// fullUrl.startsWith(this.initialUrl) && // this condition makes it stop crawling back the url
this.isInternalLink(fullUrl) && this.isInternalLink(fullUrl) &&
this.matchesPattern(fullUrl) && this.matchesPattern(fullUrl) &&
this.noSections(fullUrl) && this.noSections(fullUrl) &&
@ -223,12 +265,16 @@ export class WebCrawler {
!this.matchesExcludes(path) && !this.matchesExcludes(path) &&
this.robots.isAllowed(fullUrl, "FireCrawlAgent") this.robots.isAllowed(fullUrl, "FireCrawlAgent")
) { ) {
links.push(fullUrl); links.push({url: fullUrl, html: content});
} }
} }
}); });
return links.filter((link) => !this.visited.has(link)); if(this.visited.size === 1){
return links;
}
// Create a new list to return to avoid modifying the visited list
return links.filter((link) => !this.visited.has(link.url));
} catch (error) { } catch (error) {
return []; return [];
} }
@ -275,9 +321,15 @@ export class WebCrawler {
".mp4", ".mp4",
".mp3", ".mp3",
".pptx", ".pptx",
".docx", // ".docx",
".xlsx", ".xlsx",
".xml", ".xml",
".avi",
".flv",
".woff",
".ttf",
".woff2",
".webp"
]; ];
return fileExtensions.some((ext) => url.endsWith(ext)); return fileExtensions.some((ext) => url.endsWith(ext));
} }
@ -294,18 +346,57 @@ export class WebCrawler {
return socialMediaOrEmail.some((ext) => url.includes(ext)); return socialMediaOrEmail.some((ext) => url.includes(ext));
} }
//
private async tryFetchSitemapLinks(url: string): Promise<string[]> { private async tryFetchSitemapLinks(url: string): Promise<string[]> {
const normalizeUrl = (url: string) => {
url = url.replace(/^https?:\/\//, "").replace(/^www\./, "");
if (url.endsWith("/")) {
url = url.slice(0, -1);
}
return url;
};
const sitemapUrl = url.endsWith("/sitemap.xml") const sitemapUrl = url.endsWith("/sitemap.xml")
? url ? url
: `${url}/sitemap.xml`; : `${url}/sitemap.xml`;
let sitemapLinks: string[] = [];
try { try {
const response = await axios.get(sitemapUrl); const response = await axios.get(sitemapUrl);
if (response.status === 200) { if (response.status === 200) {
return await getLinksFromSitemap(sitemapUrl); sitemapLinks = await getLinksFromSitemap(sitemapUrl);
} }
} catch (error) { } catch (error) {
// Error handling for failed sitemap fetch // Error handling for failed sitemap fetch
// console.error(`Failed to fetch sitemap from ${sitemapUrl}: ${error}`);
} }
return [];
if (sitemapLinks.length === 0) {
// If the first one doesn't work, try the base URL
const baseUrlSitemap = `${this.baseUrl}/sitemap.xml`;
try {
const response = await axios.get(baseUrlSitemap);
if (response.status === 200) {
sitemapLinks = await getLinksFromSitemap(baseUrlSitemap);
}
} catch (error) {
// Error handling for failed base URL sitemap fetch
// console.error(`Failed to fetch sitemap from ${baseUrlSitemap}: ${error}`);
}
}
// Normalize and check if the URL is present in any of the sitemaps
const normalizedUrl = normalizeUrl(url);
const normalizedSitemapLinks = sitemapLinks.map(link => normalizeUrl(link));
// has to be greater than 0 to avoid adding the initial URL to the sitemap links, and preventing crawler to crawl
if (!normalizedSitemapLinks.includes(normalizedUrl) && sitemapLinks.length > 0) {
// do not push the normalized url
sitemapLinks.push(url);
}
return sitemapLinks;
} }
} }

103
apps/api/src/scraper/WebScraper/index.ts
View File

@ -17,6 +17,7 @@ import {
} from "./utils/replacePaths"; } from "./utils/replacePaths";
import { generateCompletions } from "../../lib/LLM-extraction"; import { generateCompletions } from "../../lib/LLM-extraction";
import { getWebScraperQueue } from "../../../src/services/queue-service"; import { getWebScraperQueue } from "../../../src/services/queue-service";
import { fetchAndProcessDocx } from "./utils/docxProcessor";
export class WebScraperDataProvider { export class WebScraperDataProvider {
private bullJobId: string; private bullJobId: string;
@ -35,6 +36,7 @@ export class WebScraperDataProvider {
private replaceAllPathsWithAbsolutePaths?: boolean = false; private replaceAllPathsWithAbsolutePaths?: boolean = false;
private generateImgAltTextModel: "gpt-4-turbo" | "claude-3-opus" = private generateImgAltTextModel: "gpt-4-turbo" | "claude-3-opus" =
"gpt-4-turbo"; "gpt-4-turbo";
private crawlerMode: string = "default";
authorize(): void { authorize(): void {
throw new Error("Method not implemented."); throw new Error("Method not implemented.");
@ -46,7 +48,8 @@ export class WebScraperDataProvider {
private async convertUrlsToDocuments( private async convertUrlsToDocuments(
urls: string[], urls: string[],
inProgress?: (progress: Progress) => void inProgress?: (progress: Progress) => void,
allHtmls?: string[]
): Promise<Document[]> { ): Promise<Document[]> {
const totalUrls = urls.length; const totalUrls = urls.length;
let processedUrls = 0; let processedUrls = 0;
@ -56,7 +59,12 @@ export class WebScraperDataProvider {
const batchUrls = urls.slice(i, i + this.concurrentRequests); const batchUrls = urls.slice(i, i + this.concurrentRequests);
await Promise.all( await Promise.all(
batchUrls.map(async (url, index) => { batchUrls.map(async (url, index) => {
const result = await scrapSingleUrl(url, this.pageOptions); const existingHTML = allHtmls ? allHtmls[i + index] : "";
const result = await scrapSingleUrl(
url,
this.pageOptions,
existingHTML
);
processedUrls++; processedUrls++;
if (inProgress) { if (inProgress) {
inProgress({ inProgress({
@ -127,9 +135,30 @@ export class WebScraperDataProvider {
} }
} }
private async cleanIrrelevantPath(links: string[]) {
return links.filter((link) => {
const normalizedInitialUrl = new URL(this.urls[0]);
const normalizedLink = new URL(link);
// Normalize the hostname to account for www and non-www versions
const initialHostname = normalizedInitialUrl.hostname.replace(
/^www\./,
""
);
const linkHostname = normalizedLink.hostname.replace(/^www\./, "");
// Ensure the protocol and hostname match, and the path starts with the initial URL's path
return (
linkHostname === initialHostname &&
normalizedLink.pathname.startsWith(normalizedInitialUrl.pathname)
);
});
}
private async handleCrawlMode( private async handleCrawlMode(
inProgress?: (progress: Progress) => void inProgress?: (progress: Progress) => void
): Promise<Document[]> { ): Promise<Document[]> {
const crawler = new WebCrawler({ const crawler = new WebCrawler({
initialUrl: this.urls[0], initialUrl: this.urls[0],
includes: this.includes, includes: this.includes,
@ -139,19 +168,38 @@ export class WebScraperDataProvider {
limit: this.limit, limit: this.limit,
generateImgAltText: this.generateImgAltText, generateImgAltText: this.generateImgAltText,
}); });
let links = await crawler.start(inProgress, 5, this.limit, this.maxCrawledDepth);
let links = await crawler.start(
inProgress,
5,
this.limit,
this.maxCrawledDepth
);
let allLinks = links.map((e) => e.url);
const allHtmls = links.map((e) => e.html);
if (this.returnOnlyUrls) { if (this.returnOnlyUrls) {
return this.returnOnlyUrlsResponse(links, inProgress); return this.returnOnlyUrlsResponse(allLinks, inProgress);
} }
let documents = await this.processLinks(links, inProgress); let documents = [];
return this.cacheAndFinalizeDocuments(documents, links); // check if fast mode is enabled and there is html inside the links
if (this.crawlerMode === "fast" && links.some((link) => link.html)) {
documents = await this.processLinks(allLinks, inProgress, allHtmls);
} else {
documents = await this.processLinks(allLinks, inProgress);
}
return this.cacheAndFinalizeDocuments(documents, allLinks);
} }
private async handleSingleUrlsMode( private async handleSingleUrlsMode(
inProgress?: (progress: Progress) => void inProgress?: (progress: Progress) => void
): Promise<Document[]> { ): Promise<Document[]> {
let documents = await this.processLinks(this.urls, inProgress); const links = this.urls;
let documents = await this.processLinks(links, inProgress);
return documents; return documents;
} }
@ -159,6 +207,8 @@ export class WebScraperDataProvider {
inProgress?: (progress: Progress) => void inProgress?: (progress: Progress) => void
): Promise<Document[]> { ): Promise<Document[]> {
let links = await getLinksFromSitemap(this.urls[0]); let links = await getLinksFromSitemap(this.urls[0]);
links = await this.cleanIrrelevantPath(links);
if (this.returnOnlyUrls) { if (this.returnOnlyUrls) {
return this.returnOnlyUrlsResponse(links, inProgress); return this.returnOnlyUrlsResponse(links, inProgress);
} }
@ -187,16 +237,26 @@ export class WebScraperDataProvider {
private async processLinks( private async processLinks(
links: string[], links: string[],
inProgress?: (progress: Progress) => void inProgress?: (progress: Progress) => void,
allHtmls?: string[]
): Promise<Document[]> { ): Promise<Document[]> {
let pdfLinks = links.filter((link) => link.endsWith(".pdf")); const pdfLinks = links.filter(link => link.endsWith(".pdf"));
let pdfDocuments = await this.fetchPdfDocuments(pdfLinks); const docLinks = links.filter(link => link.endsWith(".doc") || link.endsWith(".docx"));
links = links.filter((link) => !link.endsWith(".pdf"));
let documents = await this.convertUrlsToDocuments(links, inProgress); const pdfDocuments = await this.fetchPdfDocuments(pdfLinks);
const docxDocuments = await this.fetchDocxDocuments(docLinks);
links = links.filter(link => !pdfLinks.includes(link) && !docLinks.includes(link));
let documents = await this.convertUrlsToDocuments(
links,
inProgress,
allHtmls
);
documents = await this.getSitemapData(this.urls[0], documents); documents = await this.getSitemapData(this.urls[0], documents);
documents = this.applyPathReplacements(documents); documents = this.applyPathReplacements(documents);
documents = await this.applyImgAltText(documents); // documents = await this.applyImgAltText(documents);
if ( if (
this.extractorOptions.mode === "llm-extraction" && this.extractorOptions.mode === "llm-extraction" &&
@ -204,7 +264,7 @@ export class WebScraperDataProvider {
) { ) {
documents = await generateCompletions(documents, this.extractorOptions); documents = await generateCompletions(documents, this.extractorOptions);
} }
return documents.concat(pdfDocuments); return documents.concat(pdfDocuments).concat(docxDocuments);
} }
private async fetchPdfDocuments(pdfLinks: string[]): Promise<Document[]> { private async fetchPdfDocuments(pdfLinks: string[]): Promise<Document[]> {
@ -219,6 +279,18 @@ export class WebScraperDataProvider {
}) })
); );
} }
private async fetchDocxDocuments(docxLinks: string[]): Promise<Document[]> {
return Promise.all(
docxLinks.map(async (p) => {
const docXDocument = await fetchAndProcessDocx(p);
return {
content: docXDocument,
metadata: { sourceURL: p },
provider: "web-scraper",
};
})
);
}
private applyPathReplacements(documents: Document[]): Document[] { private applyPathReplacements(documents: Document[]): Document[] {
return this.replaceAllPathsWithAbsolutePaths return this.replaceAllPathsWithAbsolutePaths
@ -395,8 +467,9 @@ export class WebScraperDataProvider {
this.pageOptions = options.pageOptions ?? { onlyMainContent: false, includeHtml: false }; this.pageOptions = options.pageOptions ?? { onlyMainContent: false, includeHtml: false };
this.extractorOptions = options.extractorOptions ?? {mode: "markdown"} this.extractorOptions = options.extractorOptions ?? {mode: "markdown"}
this.replaceAllPathsWithAbsolutePaths = options.crawlerOptions?.replaceAllPathsWithAbsolutePaths ?? false; this.replaceAllPathsWithAbsolutePaths = options.crawlerOptions?.replaceAllPathsWithAbsolutePaths ?? false;
//! @nicolas, for some reason this was being injected and breakign everything. Don't have time to find source of the issue so adding this check //! @nicolas, for some reason this was being injected and breaking everything. Don't have time to find source of the issue so adding this check
this.excludes = this.excludes.filter((item) => item !== ""); this.excludes = this.excludes.filter((item) => item !== "");
this.crawlerMode = options.crawlerOptions?.mode ?? "default";
// make sure all urls start with https:// // make sure all urls start with https://
this.urls = this.urls.map((url) => { this.urls = this.urls.map((url) => {

221
apps/api/src/scraper/WebScraper/single_url.ts
View File

@ -6,9 +6,19 @@ import { Document, PageOptions } from "../../lib/entities";
import { parseMarkdown } from "../../lib/html-to-markdown"; import { parseMarkdown } from "../../lib/html-to-markdown";
import { excludeNonMainTags } from "./utils/excludeTags"; import { excludeNonMainTags } from "./utils/excludeTags";
import { urlSpecificParams } from "./utils/custom/website_params"; import { urlSpecificParams } from "./utils/custom/website_params";
import { fetchAndProcessPdf } from "./utils/pdfProcessor";
dotenv.config(); dotenv.config();
const baseScrapers = [
"fire-engine",
"scrapingBee",
"playwright",
"scrapingBeeLoad",
"fetch",
] as const;
export async function generateRequestParams( export async function generateRequestParams(
url: string, url: string,
wait_browser: string = "domcontentloaded", wait_browser: string = "domcontentloaded",
@ -21,7 +31,7 @@ export async function generateRequestParams(
}; };
try { try {
const urlKey = new URL(url).hostname; const urlKey = new URL(url).hostname.replace(/^www\./, "");
if (urlSpecificParams.hasOwnProperty(urlKey)) { if (urlSpecificParams.hasOwnProperty(urlKey)) {
return { ...defaultParams, ...urlSpecificParams[urlKey] }; return { ...defaultParams, ...urlSpecificParams[urlKey] };
} else { } else {
@ -32,15 +42,39 @@ export async function generateRequestParams(
return defaultParams; return defaultParams;
} }
} }
export async function scrapWithCustomFirecrawl( export async function scrapWithFireEngine(
url: string, url: string,
options?: any options?: any
): Promise<string> { ): Promise<string> {
try { try {
// TODO: merge the custom firecrawl scraper into mono-repo when ready const reqParams = await generateRequestParams(url);
return null; const wait_playwright = reqParams["params"]?.wait ?? 0;
const response = await fetch(process.env.FIRE_ENGINE_BETA_URL+ "/scrape", {
method: "POST",
headers: {
"Content-Type": "application/json",
},
body: JSON.stringify({ url: url, wait: wait_playwright }),
});
if (!response.ok) {
console.error(
`[Fire-Engine] Error fetching url: ${url} with status: ${response.status}`
);
return "";
}
const contentType = response.headers['content-type'];
if (contentType && contentType.includes('application/pdf')) {
return fetchAndProcessPdf(url);
} else {
const data = await response.json();
const html = data.content;
return html ?? "";
}
} catch (error) { } catch (error) {
console.error(`Error scraping with custom firecrawl-scraper: ${error}`); console.error(`[Fire-Engine][c] Error fetching url: ${url} -> ${error}`);
return ""; return "";
} }
} }
@ -62,48 +96,114 @@ export async function scrapWithScrapingBee(
if (response.status !== 200 && response.status !== 404) { if (response.status !== 200 && response.status !== 404) {
console.error( console.error(
`Scraping bee error in ${url} with status code ${response.status}` `[ScrapingBee] Error fetching url: ${url} with status code ${response.status}`
); );
return ""; return "";
} }
const decoder = new TextDecoder();
const text = decoder.decode(response.data); const contentType = response.headers['content-type'];
return text; if (contentType && contentType.includes('application/pdf')) {
return fetchAndProcessPdf(url);
} else {
const decoder = new TextDecoder();
const text = decoder.decode(response.data);
return text;
}
} catch (error) { } catch (error) {
console.error(`Error scraping with Scraping Bee: ${error}`); console.error(`[ScrapingBee][c] Error fetching url: ${url} -> ${error}`);
return ""; return "";
} }
} }
export async function scrapWithPlaywright(url: string): Promise<string> { export async function scrapWithPlaywright(url: string): Promise<string> {
try { try {
const reqParams = await generateRequestParams(url);
const wait_playwright = reqParams["params"]?.wait ?? 0;
const response = await fetch(process.env.PLAYWRIGHT_MICROSERVICE_URL, { const response = await fetch(process.env.PLAYWRIGHT_MICROSERVICE_URL, {
method: "POST", method: "POST",
headers: { headers: {
"Content-Type": "application/json", "Content-Type": "application/json",
}, },
body: JSON.stringify({ url: url }), body: JSON.stringify({ url: url, wait: wait_playwright }),
}); });
if (!response.ok) { if (!response.ok) {
console.error( console.error(
`Error fetching w/ playwright server -> URL: ${url} with status: ${response.status}` `[Playwright] Error fetching url: ${url} with status: ${response.status}`
); );
return ""; return "";
} }
const data = await response.json(); const contentType = response.headers['content-type'];
const html = data.content; if (contentType && contentType.includes('application/pdf')) {
return html ?? ""; return fetchAndProcessPdf(url);
} else {
const data = await response.json();
const html = data.content;
return html ?? "";
}
} catch (error) { } catch (error) {
console.error(`Error scraping with Puppeteer: ${error}`); console.error(`[Playwright][c] Error fetching url: ${url} -> ${error}`);
return ""; return "";
} }
} }
export async function scrapWithFetch(url: string): Promise<string> {
try {
const response = await fetch(url);
if (!response.ok) {
console.error(
`[Fetch] Error fetching url: ${url} with status: ${response.status}`
);
return "";
}
const contentType = response.headers['content-type'];
if (contentType && contentType.includes('application/pdf')) {
return fetchAndProcessPdf(url);
} else {
const text = await response.text();
return text;
}
} catch (error) {
console.error(`[Fetch][c] Error fetching url: ${url} -> ${error}`);
return "";
}
}
/**
* Get the order of scrapers to be used for scraping a URL
* If the user doesn't have envs set for a specific scraper, it will be removed from the order.
* @param defaultScraper The default scraper to use if the URL does not have a specific scraper order defined
* @returns The order of scrapers to be used for scraping a URL
*/
function getScrapingFallbackOrder(defaultScraper?: string) {
const availableScrapers = baseScrapers.filter(scraper => {
switch (scraper) {
case "scrapingBee":
case "scrapingBeeLoad":
return !!process.env.SCRAPING_BEE_API_KEY;
case "fire-engine":
return !!process.env.FIRE_ENGINE_BETA_URL;
case "playwright":
return !!process.env.PLAYWRIGHT_MICROSERVICE_URL;
default:
return true;
}
});
const defaultOrder = ["scrapingBee", "fire-engine", "playwright", "scrapingBeeLoad", "fetch"];
const filteredDefaultOrder = defaultOrder.filter((scraper: typeof baseScrapers[number]) => availableScrapers.includes(scraper));
const uniqueScrapers = new Set(defaultScraper ? [defaultScraper, ...filteredDefaultOrder, ...availableScrapers] : [...filteredDefaultOrder, ...availableScrapers]);
const scrapersInOrder = Array.from(uniqueScrapers);
return scrapersInOrder as typeof baseScrapers[number][];
}
export async function scrapSingleUrl( export async function scrapSingleUrl(
urlToScrap: string, urlToScrap: string,
pageOptions: PageOptions = { onlyMainContent: true, includeHtml: false }, pageOptions: PageOptions = { onlyMainContent: true, includeHtml: false },
existingHtml: string = ""
): Promise<Document> { ): Promise<Document> {
urlToScrap = urlToScrap.trim(); urlToScrap = urlToScrap.trim();
@ -121,17 +221,14 @@ export async function scrapSingleUrl(
const attemptScraping = async ( const attemptScraping = async (
url: string, url: string,
method: method: typeof baseScrapers[number]
| "firecrawl-scraper"
| "scrapingBee"
| "playwright"
| "scrapingBeeLoad"
| "fetch"
) => { ) => {
let text = ""; let text = "";
switch (method) { switch (method) {
case "firecrawl-scraper": case "fire-engine":
text = await scrapWithCustomFirecrawl(url); if (process.env.FIRE_ENGINE_BETA_URL) {
text = await scrapWithFireEngine(url);
}
break; break;
case "scrapingBee": case "scrapingBee":
if (process.env.SCRAPING_BEE_API_KEY) { if (process.env.SCRAPING_BEE_API_KEY) {
@ -153,19 +250,7 @@ export async function scrapSingleUrl(
} }
break; break;
case "fetch": case "fetch":
try { text = await scrapWithFetch(url);
const response = await fetch(url);
if (!response.ok) {
console.error(
`Error fetching URL: ${url} with status: ${response.status}`
);
return "";
}
text = await response.text();
} catch (error) {
console.error(`Error scraping URL: ${error}`);
return "";
}
break; break;
} }
@ -174,51 +259,47 @@ export async function scrapSingleUrl(
return [await parseMarkdown(cleanedHtml), text]; return [await parseMarkdown(cleanedHtml), text];
}; };
try { try {
// TODO: comment this out once we're ready to merge firecrawl-scraper into the mono-repo let [text, html] = ["", ""];
// let [text, html] = await attemptScraping(urlToScrap, 'firecrawl-scraper'); let urlKey = urlToScrap;
// if (!text || text.length < 100) { try {
// console.log("Falling back to scraping bee load"); urlKey = new URL(urlToScrap).hostname.replace(/^www\./, "");
// [text, html] = await attemptScraping(urlToScrap, 'scrapingBeeLoad'); } catch (error) {
// } console.error(`Invalid URL key, trying: ${urlToScrap}`);
let [text, html] = await attemptScraping(urlToScrap, "scrapingBee");
// Basically means that it is using /search endpoint
if (pageOptions.fallback === false) {
const soup = cheerio.load(html);
const metadata = extractMetadata(soup, urlToScrap);
return {
url: urlToScrap,
content: text,
markdown: text,
html: pageOptions.includeHtml ? html : undefined,
metadata: { ...metadata, sourceURL: urlToScrap },
} as Document;
} }
if (!text || text.length < 100) { const defaultScraper = urlSpecificParams[urlKey]?.defaultScraper ?? "";
console.log("Falling back to playwright"); const scrapersInOrder = getScrapingFallbackOrder(defaultScraper)
[text, html] = await attemptScraping(urlToScrap, "playwright");
for (const scraper of scrapersInOrder) {
// If exists text coming from crawler, use it
if (existingHtml && existingHtml.trim().length >= 100) {
let cleanedHtml = removeUnwantedElements(existingHtml, pageOptions);
text = await parseMarkdown(cleanedHtml);
html = existingHtml;
break;
}
[text, html] = await attemptScraping(urlToScrap, scraper);
if (text && text.trim().length >= 100) break;
const nextScraperIndex = scrapersInOrder.indexOf(scraper) + 1;
if (nextScraperIndex < scrapersInOrder.length) {
console.info(`Falling back to ${scrapersInOrder[nextScraperIndex]}`);
}
} }
if (!text || text.length < 100) { if (!text) {
console.log("Falling back to scraping bee load"); throw new Error(`All scraping methods failed for URL: ${urlToScrap}`);
[text, html] = await attemptScraping(urlToScrap, "scrapingBeeLoad");
}
if (!text || text.length < 100) {
console.log("Falling back to fetch");
[text, html] = await attemptScraping(urlToScrap, "fetch");
} }
const soup = cheerio.load(html); const soup = cheerio.load(html);
const metadata = extractMetadata(soup, urlToScrap); const metadata = extractMetadata(soup, urlToScrap);
const document: Document = {
return {
content: text, content: text,
markdown: text, markdown: text,
html: pageOptions.includeHtml ? html : undefined, html: pageOptions.includeHtml ? html : undefined,
metadata: { ...metadata, sourceURL: urlToScrap }, metadata: { ...metadata, sourceURL: urlToScrap },
} as Document; };
return document;
} catch (error) { } catch (error) {
console.error(`Error: ${error} - Failed to fetch URL: ${urlToScrap}`); console.error(`Error: ${error} - Failed to fetch URL: ${urlToScrap}`);
return { return {

13
apps/api/src/scraper/WebScraper/utils/__tests__/docxProcessor.test.ts Normal file
View File

@ -0,0 +1,13 @@
import * as docxProcessor from "../docxProcessor";
describe("DOCX Processing Module - Integration Test", () => {
it("should correctly process a simple DOCX file without the LLAMAPARSE_API_KEY", async () => {
delete process.env.LLAMAPARSE_API_KEY;
const docxContent = await docxProcessor.fetchAndProcessDocx(
"https://nvca.org/wp-content/uploads/2019/06/NVCA-Model-Document-Stock-Purchase-Agreement.docx"
);
expect(docxContent.trim()).toContain(
"SERIES A PREFERRED STOCK PURCHASE AGREEMENT"
);
});
});

103
apps/api/src/scraper/WebScraper/utils/custom/website_params.ts
View File

@ -22,9 +22,112 @@ export const urlSpecificParams = {
}, },
}, },
"support.greenpay.me":{ "support.greenpay.me":{
defaultScraper: "playwright",
params: { params: {
wait_browser: "networkidle2", wait_browser: "networkidle2",
block_resources: false, block_resources: false,
wait: 2000,
},
headers: {
"User-Agent":
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
"sec-fetch-site": "same-origin",
"sec-fetch-mode": "cors",
"sec-fetch-dest": "empty",
referer: "https://www.google.com/",
"accept-language": "en-US,en;q=0.9",
"accept-encoding": "gzip, deflate, br",
accept:
"text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
},
},
"docs.pdw.co":{
defaultScraper: "playwright",
params: {
wait_browser: "networkidle2",
block_resources: false,
wait: 3000,
},
headers: {
"User-Agent":
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
"sec-fetch-site": "same-origin",
"sec-fetch-mode": "cors",
"sec-fetch-dest": "empty",
referer: "https://www.google.com/",
"accept-language": "en-US,en;q=0.9",
"accept-encoding": "gzip, deflate, br",
accept:
"text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
},
},
"ycombinator.com":{
defaultScraper: "fire-engine",
params: {
wait_browser: "networkidle2",
block_resources: false,
wait: 3000,
},
headers: {
"User-Agent":
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
"sec-fetch-site": "same-origin",
"sec-fetch-mode": "cors",
"sec-fetch-dest": "empty",
referer: "https://www.google.com/",
"accept-language": "en-US,en;q=0.9",
"accept-encoding": "gzip, deflate, br",
accept:
"text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
},
},
"developers.notion.com":{
defaultScraper: "playwright",
params: {
wait_browser: "networkidle2",
block_resources: false,
wait: 2000,
},
headers: {
"User-Agent":
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
"sec-fetch-site": "same-origin",
"sec-fetch-mode": "cors",
"sec-fetch-dest": "empty",
referer: "https://www.google.com/",
"accept-language": "en-US,en;q=0.9",
"accept-encoding": "gzip, deflate, br",
accept:
"text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
},
},
"docs2.hubitat.com":{
defaultScraper: "playwright",
params: {
wait_browser: "networkidle2",
block_resources: false,
wait: 2000,
},
headers: {
"User-Agent":
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
"sec-fetch-site": "same-origin",
"sec-fetch-mode": "cors",
"sec-fetch-dest": "empty",
referer: "https://www.google.com/",
"accept-language": "en-US,en;q=0.9",
"accept-encoding": "gzip, deflate, br",
accept:
"text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
},
},
"help.salesforce.com":{
defaultScraper: "playwright",
params: {
wait_browser: "networkidle2",
block_resources: false,
wait: 2000,
}, },
headers: { headers: {
"User-Agent": "User-Agent":

41
apps/api/src/scraper/WebScraper/utils/docxProcessor.ts Normal file
View File

@ -0,0 +1,41 @@
import axios from "axios";
import fs from "fs";
import { createWriteStream } from "node:fs";
import path from "path";
import os from "os";
import mammoth from "mammoth";
export async function fetchAndProcessDocx(url: string): Promise<string> {
const tempFilePath = await downloadDocx(url);
const content = await processDocxToText(tempFilePath);
fs.unlinkSync(tempFilePath); // Clean up the temporary file
return content;
}
async function downloadDocx(url: string): Promise<string> {
const response = await axios({
url,
method: "GET",
responseType: "stream",
});
const tempFilePath = path.join(os.tmpdir(), `tempDocx-${Date.now()}.docx`);
const writer = createWriteStream(tempFilePath);
response.data.pipe(writer);
return new Promise((resolve, reject) => {
writer.on("finish", () => resolve(tempFilePath));
writer.on("error", reject);
});
}
export async function processDocxToText(filePath: string): Promise<string> {
const content = await extractTextFromDocx(filePath);
return content;
}
async function extractTextFromDocx(filePath: string): Promise<string> {
const result = await mammoth.extractRawText({ path: filePath });
return result.value;
}

10
apps/api/src/scraper/WebScraper/utils/excludeTags.ts
View File

@ -34,8 +34,6 @@ export const excludeNonMainTags = [
"#nav", "#nav",
".breadcrumbs", ".breadcrumbs",
"#breadcrumbs", "#breadcrumbs",
".form",
"form",
"#search-form", "#search-form",
".search", ".search",
"#search", "#search",
@ -51,10 +49,6 @@ export const excludeNonMainTags = [
"#tag", "#tag",
".category", ".category",
"#category", "#category",
".comment", ".cookie",
"#comment", "#cookie"
".reply",
"#reply",
".author",
"#author",
]; ];

16
apps/api/src/scraper/WebScraper/utils/pdfProcessor.ts
View File

@ -19,8 +19,8 @@ export async function fetchAndProcessPdf(url: string): Promise<string> {
async function downloadPdf(url: string): Promise<string> { async function downloadPdf(url: string): Promise<string> {
const response = await axios({ const response = await axios({
url, url,
method: 'GET', method: "GET",
responseType: 'stream', responseType: "stream",
}); });
const tempFilePath = path.join(os.tmpdir(), `tempPdf-${Date.now()}.pdf`); const tempFilePath = path.join(os.tmpdir(), `tempPdf-${Date.now()}.pdf`);
@ -29,8 +29,8 @@ async function downloadPdf(url: string): Promise<string> {
response.data.pipe(writer); response.data.pipe(writer);
return new Promise((resolve, reject) => { return new Promise((resolve, reject) => {
writer.on('finish', () => resolve(tempFilePath)); writer.on("finish", () => resolve(tempFilePath));
writer.on('error', reject); writer.on("error", reject);
}); });
} }
@ -77,12 +77,12 @@ export async function processPdfToText(filePath: string): Promise<string> {
} else { } else {
// If the status code is not 200, increment the attempt counter and wait // If the status code is not 200, increment the attempt counter and wait
attempt++; attempt++;
await new Promise((resolve) => setTimeout(resolve, 250)); // Wait for 2 seconds await new Promise((resolve) => setTimeout(resolve, 500)); // Wait for 0.5 seconds
} }
} catch (error) { } catch (error) {
console.error("Error fetching result:", error); console.error("Error fetching result:", error || '');
attempt++; attempt++;
await new Promise((resolve) => setTimeout(resolve, 250)); // Wait for 2 seconds before retrying await new Promise((resolve) => setTimeout(resolve, 500)); // Wait for 0.5 seconds before retrying
// You may want to handle specific errors differently // You may want to handle specific errors differently
} }
} }
@ -101,7 +101,7 @@ export async function processPdfToText(filePath: string): Promise<string> {
return content; return content;
} }
async function processPdf(file: string){ async function processPdf(file: string) {
const fileContent = fs.readFileSync(file); const fileContent = fs.readFileSync(file);
const data = await pdf(fileContent); const data = await pdf(fileContent);
return data.text; return data.text;

31
apps/api/src/services/billing/credit_billing.ts
View File

@ -212,20 +212,27 @@ export async function supaCheckTeamCredits(team_id: string, credits: number) {
return { success: true, message: "Sufficient credits available" }; return { success: true, message: "Sufficient credits available" };
} }
// Calculate the total credits used by the team within the current billing period let totalCreditsUsed = 0;
const { data: creditUsages, error: creditUsageError } = await supabase_service try {
.from("credit_usage") const { data: creditUsages, error: creditUsageError } = await supabase_service
.select("credits_used") .rpc("get_credit_usage_2", {
.eq("subscription_id", subscription.id) sub_id: subscription.id,
.gte("created_at", subscription.current_period_start) start_time: subscription.current_period_start,
.lte("created_at", subscription.current_period_end); end_time: subscription.current_period_end
});
if (creditUsageError) {
console.error("Error calculating credit usage:", creditUsageError);
}
if (creditUsages && creditUsages.length > 0) {
totalCreditsUsed = creditUsages[0].total_credits_used;
// console.log("Total Credits Used:", totalCreditsUsed);
}
} catch (error) {
console.error("Error calculating credit usage:", error);
if (creditUsageError) {
throw new Error(`Failed to retrieve credit usage for subscription_id: ${subscription.id}`);
} }
const totalCreditsUsed = creditUsages.reduce((acc, usage) => acc + usage.credits_used, 0);
// Adjust total credits used by subtracting coupon value // Adjust total credits used by subtracting coupon value
const adjustedCreditsUsed = Math.max(0, totalCreditsUsed - couponCredits); const adjustedCreditsUsed = Math.max(0, totalCreditsUsed - couponCredits);

7
apps/api/src/services/queue-worker.ts
View File

@ -5,6 +5,11 @@ import { logtail } from "./logtail";
import { startWebScraperPipeline } from "../main/runWebScraper"; import { startWebScraperPipeline } from "../main/runWebScraper";
import { callWebhook } from "./webhook"; import { callWebhook } from "./webhook";
import { logJob } from "./logging/log_job"; import { logJob } from "./logging/log_job";
import { initSDK } from '@hyperdx/node-opentelemetry';
if(process.env.ENV === 'production') {
initSDK({ consoleCapture: true, additionalInstrumentations: []});
}
getWebScraperQueue().process( getWebScraperQueue().process(
Math.floor(Number(process.env.NUM_WORKERS_PER_QUEUE ?? 8)), Math.floor(Number(process.env.NUM_WORKERS_PER_QUEUE ?? 8)),
@ -26,7 +31,7 @@ getWebScraperQueue().process(
success: success, success: success,
result: { result: {
links: docs.map((doc) => { links: docs.map((doc) => {
return { content: doc, source: doc.metadata.sourceURL }; return { content: doc, source: doc?.metadata?.sourceURL ?? doc?.url ?? "" };
}), }),
}, },
project_id: job.data.project_id, project_id: job.data.project_id,

133
apps/api/src/services/rate-limiter.ts
View File

@ -2,17 +2,21 @@ import { RateLimiterRedis } from "rate-limiter-flexible";
import * as redis from "redis"; import * as redis from "redis";
import { RateLimiterMode } from "../../src/types"; import { RateLimiterMode } from "../../src/types";
const MAX_REQUESTS_PER_MINUTE_PREVIEW = 5; const MAX_CRAWLS_PER_MINUTE_STARTER = 3;
const MAX_CRAWLS_PER_MINUTE_STARTER = 2; const MAX_CRAWLS_PER_MINUTE_STANDARD = 5;
const MAX_CRAWLS_PER_MINUTE_STANDARD = 4;
const MAX_CRAWLS_PER_MINUTE_SCALE = 20; const MAX_CRAWLS_PER_MINUTE_SCALE = 20;
const MAX_SCRAPES_PER_MINUTE_STARTER = 20;
const MAX_SCRAPES_PER_MINUTE_STANDARD = 40;
const MAX_SCRAPES_PER_MINUTE_SCALE = 50;
const MAX_SEARCHES_PER_MINUTE_STARTER = 20;
const MAX_SEARCHES_PER_MINUTE_STANDARD = 40;
const MAX_SEARCHES_PER_MINUTE_SCALE = 50;
const MAX_REQUESTS_PER_MINUTE_PREVIEW = 5;
const MAX_REQUESTS_PER_MINUTE_ACCOUNT = 20; const MAX_REQUESTS_PER_MINUTE_ACCOUNT = 20;
const MAX_REQUESTS_PER_MINUTE_CRAWL_STATUS = 150;
const MAX_REQUESTS_PER_MINUTE_CRAWL_STATUS = 120;
export const redisClient = redis.createClient({ export const redisClient = redis.createClient({
url: process.env.REDIS_URL, url: process.env.REDIS_URL,
@ -21,60 +25,109 @@ export const redisClient = redis.createClient({
export const previewRateLimiter = new RateLimiterRedis({ export const previewRateLimiter = new RateLimiterRedis({
storeClient: redisClient, storeClient: redisClient,
keyPrefix: "middleware", keyPrefix: "preview",
points: MAX_REQUESTS_PER_MINUTE_PREVIEW, points: MAX_REQUESTS_PER_MINUTE_PREVIEW,
duration: 60, // Duration in seconds duration: 60, // Duration in seconds
}); });
export const serverRateLimiter = new RateLimiterRedis({ export const serverRateLimiter = new RateLimiterRedis({
storeClient: redisClient, storeClient: redisClient,
keyPrefix: "middleware", keyPrefix: "server",
points: MAX_REQUESTS_PER_MINUTE_ACCOUNT, points: MAX_REQUESTS_PER_MINUTE_ACCOUNT,
duration: 60, // Duration in seconds duration: 60, // Duration in seconds
}); });
export const crawlStatusRateLimiter = new RateLimiterRedis({ export const crawlStatusRateLimiter = new RateLimiterRedis({
storeClient: redisClient, storeClient: redisClient,
keyPrefix: "middleware", keyPrefix: "crawl-status",
points: MAX_REQUESTS_PER_MINUTE_CRAWL_STATUS, points: MAX_REQUESTS_PER_MINUTE_CRAWL_STATUS,
duration: 60, // Duration in seconds duration: 60, // Duration in seconds
}); });
export const testSuiteRateLimiter = new RateLimiterRedis({
storeClient: redisClient,
keyPrefix: "test-suite",
points: 10000,
duration: 60, // Duration in seconds
});
export function crawlRateLimit(plan: string){
if(plan === "standard"){ export function getRateLimiter(mode: RateLimiterMode, token: string, plan?: string){
return new RateLimiterRedis({ // Special test suite case. TODO: Change this later.
storeClient: redisClient, if (token.includes("5089cefa58") || token.includes("6254cf9")){
keyPrefix: "middleware", return testSuiteRateLimiter;
points: MAX_CRAWLS_PER_MINUTE_STANDARD,
duration: 60, // Duration in seconds
});
}else if(plan === "scale"){
return new RateLimiterRedis({
storeClient: redisClient,
keyPrefix: "middleware",
points: MAX_CRAWLS_PER_MINUTE_SCALE,
duration: 60, // Duration in seconds
});
} }
return new RateLimiterRedis({ switch (mode) {
storeClient: redisClient,
keyPrefix: "middleware",
points: MAX_CRAWLS_PER_MINUTE_STARTER,
duration: 60, // Duration in seconds
});
}
export function getRateLimiter(mode: RateLimiterMode){
switch(mode) {
case RateLimiterMode.Preview: case RateLimiterMode.Preview:
return previewRateLimiter; return previewRateLimiter;
case RateLimiterMode.CrawlStatus: case RateLimiterMode.CrawlStatus:
return crawlStatusRateLimiter; return crawlStatusRateLimiter;
case RateLimiterMode.Crawl:
if (plan === "standard"){
return new RateLimiterRedis({
storeClient: redisClient,
keyPrefix: "crawl-standard",
points: MAX_CRAWLS_PER_MINUTE_STANDARD,
duration: 60, // Duration in seconds
});
} else if (plan === "scale"){
return new RateLimiterRedis({
storeClient: redisClient,
keyPrefix: "crawl-scale",
points: MAX_CRAWLS_PER_MINUTE_SCALE,
duration: 60, // Duration in seconds
});
}
return new RateLimiterRedis({
storeClient: redisClient,
keyPrefix: "crawl-starter",
points: MAX_CRAWLS_PER_MINUTE_STARTER,
duration: 60, // Duration in seconds
});
case RateLimiterMode.Scrape:
if (plan === "standard"){
return new RateLimiterRedis({
storeClient: redisClient,
keyPrefix: "scrape-standard",
points: MAX_SCRAPES_PER_MINUTE_STANDARD,
duration: 60, // Duration in seconds
});
} else if (plan === "scale"){
return new RateLimiterRedis({
storeClient: redisClient,
keyPrefix: "scrape-scale",
points: MAX_SCRAPES_PER_MINUTE_SCALE,
duration: 60, // Duration in seconds
});
}
return new RateLimiterRedis({
storeClient: redisClient,
keyPrefix: "scrape-starter",
points: MAX_SCRAPES_PER_MINUTE_STARTER,
duration: 60, // Duration in seconds
});
case RateLimiterMode.Search:
if (plan === "standard"){
return new RateLimiterRedis({
storeClient: redisClient,
keyPrefix: "search-standard",
points: MAX_SEARCHES_PER_MINUTE_STANDARD,
duration: 60, // Duration in seconds
});
} else if (plan === "scale"){
return new RateLimiterRedis({
storeClient: redisClient,
keyPrefix: "search-scale",
points: MAX_SEARCHES_PER_MINUTE_SCALE,
duration: 60, // Duration in seconds
});
}
return new RateLimiterRedis({
storeClient: redisClient,
keyPrefix: "search-starter",
points: MAX_SEARCHES_PER_MINUTE_STARTER,
duration: 60, // Duration in seconds
});
default: default:
return serverRateLimiter; return serverRateLimiter;
} }

65
apps/js-sdk/example.js
View File

@ -1,8 +1,14 @@
import { v4 as uuidv4 } from 'uuid'; import { v4 as uuidv4 } from 'uuid';
import FirecrawlApp from '@mendable/firecrawl-js'; import FirecrawlApp from '@mendable/firecrawl-js';
import { z } from "zod";
const app = new FirecrawlApp({apiKey: "YOUR_API_KEY"}); const app = new FirecrawlApp({apiKey: "fc-YOUR_API_KEY"});
// Scrape a website:
const scrapeResult = await app.scrapeUrl('firecrawl.dev');
console.log(scrapeResult.data.content)
// Crawl a website:
const idempotencyKey = uuidv4(); // optional const idempotencyKey = uuidv4(); // optional
const crawlResult = await app.crawlUrl('mendable.ai', {crawlerOptions: {excludes: ['blog/*'], limit: 5}}, false, 2, idempotencyKey); const crawlResult = await app.crawlUrl('mendable.ai', {crawlerOptions: {excludes: ['blog/*'], limit: 5}}, false, 2, idempotencyKey);
console.log(crawlResult) console.log(crawlResult)
@ -20,3 +26,60 @@ while (true) {
} }
console.log(job.data[0].content); console.log(job.data[0].content);
// Search for a query:
const query = 'what is mendable?'
const searchResult = await app.search(query)
console.log(searchResult)
// LLM Extraction:
// Define schema to extract contents into using zod schema
const zodSchema = z.object({
top: z
.array(
z.object({
title: z.string(),
points: z.number(),
by: z.string(),
commentsURL: z.string(),
})
)
.length(5)
.describe("Top 5 stories on Hacker News"),
});
let llmExtractionResult = await app.scrapeUrl("https://news.ycombinator.com", {
extractorOptions: { extractionSchema: zodSchema },
});
console.log(llmExtractionResult.data.llm_extraction);
// Define schema to extract contents into using json schema
const jsonSchema = {
"type": "object",
"properties": {
"top": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": {"type": "string"},
"points": {"type": "number"},
"by": {"type": "string"},
"commentsURL": {"type": "string"}
},
"required": ["title", "points", "by", "commentsURL"]
},
"minItems": 5,
"maxItems": 5,
"description": "Top 5 stories on Hacker News"
}
},
"required": ["top"]
}
llmExtractionResult = await app.scrapeUrl("https://news.ycombinator.com", {
extractorOptions: { extractionSchema: jsonSchema },
});
console.log(llmExtractionResult.data.llm_extraction);

83
apps/js-sdk/example.ts Normal file
View File

@ -0,0 +1,83 @@
import FirecrawlApp, { JobStatusResponse } from '@mendable/firecrawl-js';
import { z } from "zod";
const app = new FirecrawlApp({apiKey: "fc-YOUR_API_KEY"});
// Scrape a website:
const scrapeResult = await app.scrapeUrl('firecrawl.dev');
console.log(scrapeResult.data.content)
// Crawl a website:
const crawlResult = await app.crawlUrl('mendable.ai', {crawlerOptions: {excludes: ['blog/*'], limit: 5}}, false);
console.log(crawlResult)
const jobId: string = await crawlResult['jobId'];
console.log(jobId);
let job: JobStatusResponse;
while (true) {
job = await app.checkCrawlStatus(jobId);
if (job.status === 'completed') {
break;
}
await new Promise(resolve => setTimeout(resolve, 1000)); // wait 1 second
}
console.log(job.data[0].content);
// Search for a query:
const query = 'what is mendable?'
const searchResult = await app.search(query)
console.log(searchResult)
// LLM Extraction:
// Define schema to extract contents into using zod schema
const zodSchema = z.object({
top: z
.array(
z.object({
title: z.string(),
points: z.number(),
by: z.string(),
commentsURL: z.string(),
})
)
.length(5)
.describe("Top 5 stories on Hacker News"),
});
let llmExtractionResult = await app.scrapeUrl("https://news.ycombinator.com", {
extractorOptions: { extractionSchema: zodSchema },
});
console.log(llmExtractionResult.data.llm_extraction);
// Define schema to extract contents into using json schema
const jsonSchema = {
"type": "object",
"properties": {
"top": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": {"type": "string"},
"points": {"type": "number"},
"by": {"type": "string"},
"commentsURL": {"type": "string"}
},
"required": ["title", "points", "by", "commentsURL"]
},
"minItems": 5,
"maxItems": 5,
"description": "Top 5 stories on Hacker News"
}
},
"required": ["top"]
}
llmExtractionResult = await app.scrapeUrl("https://news.ycombinator.com", {
extractorOptions: { extractionSchema: jsonSchema },
});
console.log(llmExtractionResult.data.llm_extraction);

36
apps/js-sdk/firecrawl/README.md
View File

@ -77,6 +77,42 @@ To scrape a single URL with error handling, use the `scrapeUrl` method. It takes
scrapeExample(); scrapeExample();
``` ```
### Extracting structured data from a URL
With LLM extraction, you can easily extract structured data from any URL. We support zod schemas to make it easier for you too. Here is how you to use it:
```js
import { z } from "zod";
const zodSchema = z.object({
top: z
.array(
z.object({
title: z.string(),
points: z.number(),
by: z.string(),
commentsURL: z.string(),
})
)
.length(5)
.describe("Top 5 stories on Hacker News"),
});
let llmExtractionResult = await app.scrapeUrl("https://news.ycombinator.com", {
extractorOptions: { extractionSchema: zodSchema },
});
console.log(llmExtractionResult.data.llm_extraction);
```
### Search for a query
Used to search the web, get the most relevant results, scrap each page and return the markdown.
```js
query = 'what is mendable?'
searchResult = app.search(query)
```
### Crawling a Website ### Crawling a Website

68
apps/js-sdk/firecrawl/build/index.js
View File

@ -7,7 +7,9 @@ var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, ge
step((generator = generator.apply(thisArg, _arguments || [])).next()); step((generator = generator.apply(thisArg, _arguments || [])).next());
}); });
}; };
import axios from 'axios'; import axios from "axios";
import { z } from "zod";
import { zodToJsonSchema } from "zod-to-json-schema";
/** /**
* Main class for interacting with the Firecrawl API. * Main class for interacting with the Firecrawl API.
*/ */
@ -19,7 +21,7 @@ export default class FirecrawlApp {
constructor({ apiKey = null }) { constructor({ apiKey = null }) {
this.apiKey = apiKey || ''; this.apiKey = apiKey || '';
if (!this.apiKey) { if (!this.apiKey) {
throw new Error('No API key provided'); throw new Error("No API key provided");
} }
} }
/** /**
@ -30,16 +32,22 @@ export default class FirecrawlApp {
*/ */
scrapeUrl(url_1) { scrapeUrl(url_1) {
return __awaiter(this, arguments, void 0, function* (url, params = null) { return __awaiter(this, arguments, void 0, function* (url, params = null) {
var _a;
const headers = { const headers = {
'Content-Type': 'application/json', "Content-Type": "application/json",
'Authorization': `Bearer ${this.apiKey}`, Authorization: `Bearer ${this.apiKey}`,
}; };
let jsonData = { url }; let jsonData = Object.assign({ url }, params);
if (params) { if ((_a = params === null || params === void 0 ? void 0 : params.extractorOptions) === null || _a === void 0 ? void 0 : _a.extractionSchema) {
jsonData = Object.assign(Object.assign({}, jsonData), params); let schema = params.extractorOptions.extractionSchema;
// Check if schema is an instance of ZodSchema to correctly identify Zod schemas
if (schema instanceof z.ZodSchema) {
schema = zodToJsonSchema(schema);
}
jsonData = Object.assign(Object.assign({}, jsonData), { extractorOptions: Object.assign(Object.assign({}, params.extractorOptions), { extractionSchema: schema, mode: params.extractorOptions.mode || "llm-extraction" }) });
} }
try { try {
const response = yield axios.post('https://api.firecrawl.dev/v0/scrape', jsonData, { headers }); const response = yield axios.post("https://api.firecrawl.dev/v0/scrape", jsonData, { headers });
if (response.status === 200) { if (response.status === 200) {
const responseData = response.data; const responseData = response.data;
if (responseData.success) { if (responseData.success) {
@ -50,13 +58,13 @@ export default class FirecrawlApp {
} }
} }
else { else {
this.handleError(response, 'scrape URL'); this.handleError(response, "scrape URL");
} }
} }
catch (error) { catch (error) {
throw new Error(error.message); throw new Error(error.message);
} }
return { success: false, error: 'Internal server error.' }; return { success: false, error: "Internal server error." };
}); });
} }
/** /**
@ -68,15 +76,15 @@ export default class FirecrawlApp {
search(query_1) { search(query_1) {
return __awaiter(this, arguments, void 0, function* (query, params = null) { return __awaiter(this, arguments, void 0, function* (query, params = null) {
const headers = { const headers = {
'Content-Type': 'application/json', "Content-Type": "application/json",
'Authorization': `Bearer ${this.apiKey}`, Authorization: `Bearer ${this.apiKey}`,
}; };
let jsonData = { query }; let jsonData = { query };
if (params) { if (params) {
jsonData = Object.assign(Object.assign({}, jsonData), params); jsonData = Object.assign(Object.assign({}, jsonData), params);
} }
try { try {
const response = yield axios.post('https://api.firecrawl.dev/v0/search', jsonData, { headers }); const response = yield axios.post("https://api.firecrawl.dev/v0/search", jsonData, { headers });
if (response.status === 200) { if (response.status === 200) {
const responseData = response.data; const responseData = response.data;
if (responseData.success) { if (responseData.success) {
@ -87,13 +95,13 @@ export default class FirecrawlApp {
} }
} }
else { else {
this.handleError(response, 'search'); this.handleError(response, "search");
} }
} }
catch (error) { catch (error) {
throw new Error(error.message); throw new Error(error.message);
} }
return { success: false, error: 'Internal server error.' }; return { success: false, error: "Internal server error." };
}); });
} }
/** /**
@ -113,7 +121,7 @@ export default class FirecrawlApp {
jsonData = Object.assign(Object.assign({}, jsonData), params); jsonData = Object.assign(Object.assign({}, jsonData), params);
} }
try { try {
const response = yield this.postRequest('https://api.firecrawl.dev/v0/crawl', jsonData, headers); const response = yield this.postRequest("https://api.firecrawl.dev/v0/crawl", jsonData, headers);
if (response.status === 200) { if (response.status === 200) {
const jobId = response.data.jobId; const jobId = response.data.jobId;
if (waitUntilDone) { if (waitUntilDone) {
@ -124,14 +132,14 @@ export default class FirecrawlApp {
} }
} }
else { else {
this.handleError(response, 'start crawl job'); this.handleError(response, "start crawl job");
} }
} }
catch (error) { catch (error) {
console.log(error); console.log(error);
throw new Error(error.message); throw new Error(error.message);
} }
return { success: false, error: 'Internal server error.' }; return { success: false, error: "Internal server error." };
}); });
} }
/** /**
@ -148,13 +156,17 @@ export default class FirecrawlApp {
return response.data; return response.data;
} }
else { else {
this.handleError(response, 'check crawl status'); this.handleError(response, "check crawl status");
} }
} }
catch (error) { catch (error) {
throw new Error(error.message); throw new Error(error.message);
} }
return { success: false, status: 'unknown', error: 'Internal server error.' }; return {
success: false,
status: "unknown",
error: "Internal server error.",
};
}); });
} }
/** /**
@ -196,26 +208,26 @@ export default class FirecrawlApp {
const statusResponse = yield this.getRequest(`https://api.firecrawl.dev/v0/crawl/status/${jobId}`, headers); const statusResponse = yield this.getRequest(`https://api.firecrawl.dev/v0/crawl/status/${jobId}`, headers);
if (statusResponse.status === 200) { if (statusResponse.status === 200) {
const statusData = statusResponse.data; const statusData = statusResponse.data;
if (statusData.status === 'completed') { if (statusData.status === "completed") {
if ('data' in statusData) { if ("data" in statusData) {
return statusData.data; return statusData.data;
} }
else { else {
throw new Error('Crawl job completed but no data was returned'); throw new Error("Crawl job completed but no data was returned");
} }
} }
else if (['active', 'paused', 'pending', 'queued'].includes(statusData.status)) { else if (["active", "paused", "pending", "queued"].includes(statusData.status)) {
if (timeout < 2) { if (timeout < 2) {
timeout = 2; timeout = 2;
} }
yield new Promise(resolve => setTimeout(resolve, timeout * 1000)); // Wait for the specified timeout before checking again yield new Promise((resolve) => setTimeout(resolve, timeout * 1000)); // Wait for the specified timeout before checking again
} }
else { else {
throw new Error(`Crawl job failed or was stopped. Status: ${statusData.status}`); throw new Error(`Crawl job failed or was stopped. Status: ${statusData.status}`);
} }
} }
else { else {
this.handleError(statusResponse, 'check crawl status'); this.handleError(statusResponse, "check crawl status");
} }
} }
}); });
@ -226,8 +238,8 @@ export default class FirecrawlApp {
* @param {string} action - The action being performed when the error occurred. * @param {string} action - The action being performed when the error occurred.
*/ */
handleError(response, action) { handleError(response, action) {
if ([402, 409, 500].includes(response.status)) { if ([402, 408, 409, 500].includes(response.status)) {
const errorMessage = response.data.error || 'Unknown error occurred'; const errorMessage = response.data.error || "Unknown error occurred";
throw new Error(`Failed to ${action}. Status code: ${response.status}. Error: ${errorMessage}`); throw new Error(`Failed to ${action}. Status code: ${response.status}. Error: ${errorMessage}`);
} }
else { else {

24
apps/js-sdk/firecrawl/package-lock.json generated
View File

@ -1,15 +1,17 @@
{ {
"name": "@mendable/firecrawl-js", "name": "@mendable/firecrawl-js",
"version": "0.0.13", "version": "0.0.17-beta.8",
"lockfileVersion": 3, "lockfileVersion": 3,
"requires": true, "requires": true,
"packages": { "packages": {
"": { "": {
"name": "@mendable/firecrawl-js", "name": "@mendable/firecrawl-js",
"version": "0.0.13", "version": "0.0.17-beta.8",
"license": "MIT", "license": "MIT",
"dependencies": { "dependencies": {
"axios": "^1.6.8" "axios": "^1.6.8",
"zod": "^3.23.8",
"zod-to-json-schema": "^3.23.0"
}, },
"devDependencies": { "devDependencies": {
"@jest/globals": "^29.7.0", "@jest/globals": "^29.7.0",
@ -3766,6 +3768,22 @@
"funding": { "funding": {
"url": "https://github.com/sponsors/sindresorhus" "url": "https://github.com/sponsors/sindresorhus"
} }
},
"node_modules/zod": {
"version": "3.23.8",
"resolved": "https://registry.npmjs.org/zod/-/zod-3.23.8.tgz",
"integrity": "sha512-XBx9AXhXktjUqnepgTiE5flcKIYWi/rme0Eaj+5Y0lftuGBq+jyRu/md4WnuxqgP1ubdpNCsYEYPxrzVHD8d6g==",
"funding": {
"url": "https://github.com/sponsors/colinhacks"
}
},
"node_modules/zod-to-json-schema": {
"version": "3.23.0",
"resolved": "https://registry.npmjs.org/zod-to-json-schema/-/zod-to-json-schema-3.23.0.tgz",
"integrity": "sha512-az0uJ243PxsRIa2x1WmNE/pnuA05gUq/JB8Lwe1EDCCL/Fz9MgjYQ0fPlyc2Tcv6aF2ZA7WM5TWaRZVEFaAIag==",
"peerDependencies": {
"zod": "^3.23.3"
}
} }
} }
} }

7
apps/js-sdk/firecrawl/package.json
View File

@ -1,6 +1,6 @@
{ {
"name": "@mendable/firecrawl-js", "name": "@mendable/firecrawl-js",
"version": "0.0.16", "version": "0.0.21",
"description": "JavaScript SDK for Firecrawl API", "description": "JavaScript SDK for Firecrawl API",
"main": "build/index.js", "main": "build/index.js",
"types": "types/index.d.ts", "types": "types/index.d.ts",
@ -8,6 +8,7 @@
"scripts": { "scripts": {
"build": "tsc", "build": "tsc",
"publish": "npm run build && npm publish --access public", "publish": "npm run build && npm publish --access public",
"publish-beta": "npm run build && npm publish --access public --tag beta",
"test": "jest src/**/*.test.ts" "test": "jest src/**/*.test.ts"
}, },
"repository": { "repository": {
@ -17,7 +18,9 @@
"author": "Mendable.ai", "author": "Mendable.ai",
"license": "MIT", "license": "MIT",
"dependencies": { "dependencies": {
"axios": "^1.6.8" "axios": "^1.6.8",
"zod": "^3.23.8",
"zod-to-json-schema": "^3.23.0"
}, },
"bugs": { "bugs": {
"url": "https://github.com/mendableai/firecrawl/issues" "url": "https://github.com/mendableai/firecrawl/issues"

156
apps/js-sdk/firecrawl/src/index.ts
View File

@ -1,5 +1,6 @@
import axios, { AxiosResponse, AxiosRequestHeaders } from 'axios'; import axios, { AxiosResponse, AxiosRequestHeaders } from "axios";
import { z } from "zod";
import { zodToJsonSchema } from "zod-to-json-schema";
/** /**
* Configuration interface for FirecrawlApp. * Configuration interface for FirecrawlApp.
*/ */
@ -12,6 +13,11 @@ export interface FirecrawlAppConfig {
*/ */
export interface Params { export interface Params {
[key: string]: any; [key: string]: any;
extractorOptions?: {
extractionSchema: z.ZodSchema | any;
mode?: "llm-extraction";
extractionPrompt?: string;
};
} }
/** /**
@ -63,9 +69,9 @@ export default class FirecrawlApp {
* @param {FirecrawlAppConfig} config - Configuration options for the FirecrawlApp instance. * @param {FirecrawlAppConfig} config - Configuration options for the FirecrawlApp instance.
*/ */
constructor({ apiKey = null }: FirecrawlAppConfig) { constructor({ apiKey = null }: FirecrawlAppConfig) {
this.apiKey = apiKey || ''; this.apiKey = apiKey || "";
if (!this.apiKey) { if (!this.apiKey) {
throw new Error('No API key provided'); throw new Error("No API key provided");
} }
} }
@ -75,17 +81,36 @@ export default class FirecrawlApp {
* @param {Params | null} params - Additional parameters for the scrape request. * @param {Params | null} params - Additional parameters for the scrape request.
* @returns {Promise<ScrapeResponse>} The response from the scrape operation. * @returns {Promise<ScrapeResponse>} The response from the scrape operation.
*/ */
async scrapeUrl(url: string, params: Params | null = null): Promise<ScrapeResponse> { async scrapeUrl(
url: string,
params: Params | null = null
): Promise<ScrapeResponse> {
const headers: AxiosRequestHeaders = { const headers: AxiosRequestHeaders = {
'Content-Type': 'application/json', "Content-Type": "application/json",
'Authorization': `Bearer ${this.apiKey}`, Authorization: `Bearer ${this.apiKey}`,
} as AxiosRequestHeaders; } as AxiosRequestHeaders;
let jsonData: Params = { url }; let jsonData: Params = { url, ...params };
if (params) { if (params?.extractorOptions?.extractionSchema) {
jsonData = { ...jsonData, ...params }; let schema = params.extractorOptions.extractionSchema;
// Check if schema is an instance of ZodSchema to correctly identify Zod schemas
if (schema instanceof z.ZodSchema) {
schema = zodToJsonSchema(schema);
}
jsonData = {
...jsonData,
extractorOptions: {
...params.extractorOptions,
extractionSchema: schema,
mode: params.extractorOptions.mode || "llm-extraction",
},
};
} }
try { try {
const response: AxiosResponse = await axios.post('https://api.firecrawl.dev/v0/scrape', jsonData, { headers }); const response: AxiosResponse = await axios.post(
"https://api.firecrawl.dev/v0/scrape",
jsonData,
{ headers },
);
if (response.status === 200) { if (response.status === 200) {
const responseData = response.data; const responseData = response.data;
if (responseData.success) { if (responseData.success) {
@ -94,12 +119,12 @@ export default class FirecrawlApp {
throw new Error(`Failed to scrape URL. Error: ${responseData.error}`); throw new Error(`Failed to scrape URL. Error: ${responseData.error}`);
} }
} else { } else {
this.handleError(response, 'scrape URL'); this.handleError(response, "scrape URL");
} }
} catch (error: any) { } catch (error: any) {
throw new Error(error.message); throw new Error(error.message);
} }
return { success: false, error: 'Internal server error.' }; return { success: false, error: "Internal server error." };
} }
/** /**
@ -108,17 +133,24 @@ export default class FirecrawlApp {
* @param {Params | null} params - Additional parameters for the search request. * @param {Params | null} params - Additional parameters for the search request.
* @returns {Promise<SearchResponse>} The response from the search operation. * @returns {Promise<SearchResponse>} The response from the search operation.
*/ */
async search(query: string, params: Params | null = null): Promise<SearchResponse> { async search(
query: string,
params: Params | null = null
): Promise<SearchResponse> {
const headers: AxiosRequestHeaders = { const headers: AxiosRequestHeaders = {
'Content-Type': 'application/json', "Content-Type": "application/json",
'Authorization': `Bearer ${this.apiKey}`, Authorization: `Bearer ${this.apiKey}`,
} as AxiosRequestHeaders; } as AxiosRequestHeaders;
let jsonData: Params = { query }; let jsonData: Params = { query };
if (params) { if (params) {
jsonData = { ...jsonData, ...params }; jsonData = { ...jsonData, ...params };
} }
try { try {
const response: AxiosResponse = await axios.post('https://api.firecrawl.dev/v0/search', jsonData, { headers }); const response: AxiosResponse = await axios.post(
"https://api.firecrawl.dev/v0/search",
jsonData,
{ headers }
);
if (response.status === 200) { if (response.status === 200) {
const responseData = response.data; const responseData = response.data;
if (responseData.success) { if (responseData.success) {
@ -127,12 +159,12 @@ export default class FirecrawlApp {
throw new Error(`Failed to search. Error: ${responseData.error}`); throw new Error(`Failed to search. Error: ${responseData.error}`);
} }
} else { } else {
this.handleError(response, 'search'); this.handleError(response, "search");
} }
} catch (error: any) { } catch (error: any) {
throw new Error(error.message); throw new Error(error.message);
} }
return { success: false, error: 'Internal server error.' }; return { success: false, error: "Internal server error." };
} }
/** /**
@ -144,14 +176,24 @@ export default class FirecrawlApp {
* @param {string} idempotencyKey - Optional idempotency key for the request. * @param {string} idempotencyKey - Optional idempotency key for the request.
* @returns {Promise<CrawlResponse | any>} The response from the crawl operation. * @returns {Promise<CrawlResponse | any>} The response from the crawl operation.
*/ */
async crawlUrl(url: string, params: Params | null = null, waitUntilDone: boolean = true, timeout: number = 2, idempotencyKey?: string): Promise<CrawlResponse | any> { async crawlUrl(
url: string,
params: Params | null = null,
waitUntilDone: boolean = true,
timeout: number = 2,
idempotencyKey?: string
): Promise<CrawlResponse | any> {
const headers = this.prepareHeaders(idempotencyKey); const headers = this.prepareHeaders(idempotencyKey);
let jsonData: Params = { url }; let jsonData: Params = { url };
if (params) { if (params) {
jsonData = { ...jsonData, ...params }; jsonData = { ...jsonData, ...params };
} }
try { try {
const response: AxiosResponse = await this.postRequest('https://api.firecrawl.dev/v0/crawl', jsonData, headers); const response: AxiosResponse = await this.postRequest(
"https://api.firecrawl.dev/v0/crawl",
jsonData,
headers
);
if (response.status === 200) { if (response.status === 200) {
const jobId: string = response.data.jobId; const jobId: string = response.data.jobId;
if (waitUntilDone) { if (waitUntilDone) {
@ -160,13 +202,13 @@ export default class FirecrawlApp {
return { success: true, jobId }; return { success: true, jobId };
} }
} else { } else {
this.handleError(response, 'start crawl job'); this.handleError(response, "start crawl job");
} }
} catch (error: any) { } catch (error: any) {
console.log(error) console.log(error);
throw new Error(error.message); throw new Error(error.message);
} }
return { success: false, error: 'Internal server error.' }; return { success: false, error: "Internal server error." };
} }
/** /**
@ -177,16 +219,23 @@ export default class FirecrawlApp {
async checkCrawlStatus(jobId: string): Promise<JobStatusResponse> { async checkCrawlStatus(jobId: string): Promise<JobStatusResponse> {
const headers: AxiosRequestHeaders = this.prepareHeaders(); const headers: AxiosRequestHeaders = this.prepareHeaders();
try { try {
const response: AxiosResponse = await this.getRequest(`https://api.firecrawl.dev/v0/crawl/status/${jobId}`, headers); const response: AxiosResponse = await this.getRequest(
`https://api.firecrawl.dev/v0/crawl/status/${jobId}`,
headers
);
if (response.status === 200) { if (response.status === 200) {
return response.data; return response.data;
} else { } else {
this.handleError(response, 'check crawl status'); this.handleError(response, "check crawl status");
} }
} catch (error: any) { } catch (error: any) {
throw new Error(error.message); throw new Error(error.message);
} }
return { success: false, status: 'unknown', error: 'Internal server error.' }; return {
success: false,
status: "unknown",
error: "Internal server error.",
};
} }
/** /**
@ -208,7 +257,11 @@ export default class FirecrawlApp {
* @param {AxiosRequestHeaders} headers - The headers for the request. * @param {AxiosRequestHeaders} headers - The headers for the request.
* @returns {Promise<AxiosResponse>} The response from the POST request. * @returns {Promise<AxiosResponse>} The response from the POST request.
*/ */
postRequest(url: string, data: Params, headers: AxiosRequestHeaders): Promise<AxiosResponse> { postRequest(
url: string,
data: Params,
headers: AxiosRequestHeaders
): Promise<AxiosResponse> {
return axios.post(url, data, { headers }); return axios.post(url, data, { headers });
} }
@ -218,7 +271,10 @@ export default class FirecrawlApp {
* @param {AxiosRequestHeaders} headers - The headers for the request. * @param {AxiosRequestHeaders} headers - The headers for the request.
* @returns {Promise<AxiosResponse>} The response from the GET request. * @returns {Promise<AxiosResponse>} The response from the GET request.
*/ */
getRequest(url: string, headers: AxiosRequestHeaders): Promise<AxiosResponse> { getRequest(
url: string,
headers: AxiosRequestHeaders
): Promise<AxiosResponse> {
return axios.get(url, { headers }); return axios.get(url, { headers });
} }
@ -229,27 +285,38 @@ export default class FirecrawlApp {
* @param {number} timeout - Timeout in seconds for job status checks. * @param {number} timeout - Timeout in seconds for job status checks.
* @returns {Promise<any>} The final job status or data. * @returns {Promise<any>} The final job status or data.
*/ */
async monitorJobStatus(jobId: string, headers: AxiosRequestHeaders, timeout: number): Promise<any> { async monitorJobStatus(
jobId: string,
headers: AxiosRequestHeaders,
timeout: number
): Promise<any> {
while (true) { while (true) {
const statusResponse: AxiosResponse = await this.getRequest(`https://api.firecrawl.dev/v0/crawl/status/${jobId}`, headers); const statusResponse: AxiosResponse = await this.getRequest(
`https://api.firecrawl.dev/v0/crawl/status/${jobId}`,
headers
);
if (statusResponse.status === 200) { if (statusResponse.status === 200) {
const statusData = statusResponse.data; const statusData = statusResponse.data;
if (statusData.status === 'completed') { if (statusData.status === "completed") {
if ('data' in statusData) { if ("data" in statusData) {
return statusData.data; return statusData.data;
} else { } else {
throw new Error('Crawl job completed but no data was returned'); throw new Error("Crawl job completed but no data was returned");
} }
} else if (['active', 'paused', 'pending', 'queued'].includes(statusData.status)) { } else if (
["active", "paused", "pending", "queued"].includes(statusData.status)
) {
if (timeout < 2) { if (timeout < 2) {
timeout = 2; timeout = 2;
} }
await new Promise(resolve => setTimeout(resolve, timeout * 1000)); // Wait for the specified timeout before checking again await new Promise((resolve) => setTimeout(resolve, timeout * 1000)); // Wait for the specified timeout before checking again
} else { } else {
throw new Error(`Crawl job failed or was stopped. Status: ${statusData.status}`); throw new Error(
`Crawl job failed or was stopped. Status: ${statusData.status}`
);
} }
} else { } else {
this.handleError(statusResponse, 'check crawl status'); this.handleError(statusResponse, "check crawl status");
} }
} }
} }
@ -260,11 +327,16 @@ export default class FirecrawlApp {
* @param {string} action - The action being performed when the error occurred. * @param {string} action - The action being performed when the error occurred.
*/ */
handleError(response: AxiosResponse, action: string): void { handleError(response: AxiosResponse, action: string): void {
if ([402, 409, 500].includes(response.status)) { if ([402, 408, 409, 500].includes(response.status)) {
const errorMessage: string = response.data.error || 'Unknown error occurred'; const errorMessage: string =
throw new Error(`Failed to ${action}. Status code: ${response.status}. Error: ${errorMessage}`); response.data.error || "Unknown error occurred";
throw new Error(
`Failed to ${action}. Status code: ${response.status}. Error: ${errorMessage}`
);
} else { } else {
throw new Error(`Unexpected error occurred while trying to ${action}. Status code: ${response.status}`); throw new Error(
`Unexpected error occurred while trying to ${action}. Status code: ${response.status}`
);
} }
} }
} }

8
apps/js-sdk/firecrawl/types/index.d.ts vendored
View File

@ -1,4 +1,5 @@
import { AxiosResponse, AxiosRequestHeaders } from 'axios'; import { AxiosResponse, AxiosRequestHeaders } from "axios";
import { z } from "zod";
/** /**
* Configuration interface for FirecrawlApp. * Configuration interface for FirecrawlApp.
*/ */
@ -10,6 +11,11 @@ export interface FirecrawlAppConfig {
*/ */
export interface Params { export interface Params {
[key: string]: any; [key: string]: any;
extractorOptions?: {
extractionSchema: z.ZodSchema | any;
mode?: "llm-extraction";
extractionPrompt?: string;
};
} }
/** /**
* Response interface for scraping operations. * Response interface for scraping operations.

673
apps/js-sdk/package-lock.json generated
View File

@ -9,20 +9,481 @@
"version": "1.0.0", "version": "1.0.0",
"license": "ISC", "license": "ISC",
"dependencies": { "dependencies": {
"@mendable/firecrawl-js": "^0.0.15", "@mendable/firecrawl-js": "^0.0.19",
"axios": "^1.6.8", "axios": "^1.6.8",
"uuid": "^9.0.1" "uuid": "^9.0.1",
"ts-node": "^10.9.2",
"typescript": "^5.4.5",
"zod": "^3.23.8"
},
"devDependencies": {
"tsx": "^4.9.3"
}
},
"node_modules/@cspotcode/source-map-support": {
"version": "0.8.1",
"resolved": "https://registry.npmjs.org/@cspotcode/source-map-support/-/source-map-support-0.8.1.tgz",
"integrity": "sha512-IchNf6dN4tHoMFIn/7OE8LWZ19Y6q/67Bmf6vnGREv8RSbBVb9LPJxEcnwrcwX6ixSvaiGoomAUvu4YSxXrVgw==",
"dependencies": {
"@jridgewell/trace-mapping": "0.3.9"
},
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/aix-ppc64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.20.2.tgz",
"integrity": "sha512-D+EBOJHXdNZcLJRBkhENNG8Wji2kgc9AZ9KiPr1JuZjsNtyHzrsfLRrY0tk2H2aoFu6RANO1y1iPPUCDYWkb5g==",
"cpu": [
"ppc64"
],
"dev": true,
"optional": true,
"os": [
"aix"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/android-arm": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.20.2.tgz",
"integrity": "sha512-t98Ra6pw2VaDhqNWO2Oph2LXbz/EJcnLmKLGBJwEwXX/JAN83Fym1rU8l0JUWK6HkIbWONCSSatf4sf2NBRx/w==",
"cpu": [
"arm"
],
"dev": true,
"optional": true,
"os": [
"android"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/android-arm64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.20.2.tgz",
"integrity": "sha512-mRzjLacRtl/tWU0SvD8lUEwb61yP9cqQo6noDZP/O8VkwafSYwZ4yWy24kan8jE/IMERpYncRt2dw438LP3Xmg==",
"cpu": [
"arm64"
],
"dev": true,
"optional": true,
"os": [
"android"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/android-x64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.20.2.tgz",
"integrity": "sha512-btzExgV+/lMGDDa194CcUQm53ncxzeBrWJcncOBxuC6ndBkKxnHdFJn86mCIgTELsooUmwUm9FkhSp5HYu00Rg==",
"cpu": [
"x64"
],
"dev": true,
"optional": true,
"os": [
"android"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/darwin-arm64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.20.2.tgz",
"integrity": "sha512-4J6IRT+10J3aJH3l1yzEg9y3wkTDgDk7TSDFX+wKFiWjqWp/iCfLIYzGyasx9l0SAFPT1HwSCR+0w/h1ES/MjA==",
"cpu": [
"arm64"
],
"dev": true,
"optional": true,
"os": [
"darwin"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/darwin-x64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.20.2.tgz",
"integrity": "sha512-tBcXp9KNphnNH0dfhv8KYkZhjc+H3XBkF5DKtswJblV7KlT9EI2+jeA8DgBjp908WEuYll6pF+UStUCfEpdysA==",
"cpu": [
"x64"
],
"dev": true,
"optional": true,
"os": [
"darwin"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/freebsd-arm64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.20.2.tgz",
"integrity": "sha512-d3qI41G4SuLiCGCFGUrKsSeTXyWG6yem1KcGZVS+3FYlYhtNoNgYrWcvkOoaqMhwXSMrZRl69ArHsGJ9mYdbbw==",
"cpu": [
"arm64"
],
"dev": true,
"optional": true,
"os": [
"freebsd"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/freebsd-x64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.20.2.tgz",
"integrity": "sha512-d+DipyvHRuqEeM5zDivKV1KuXn9WeRX6vqSqIDgwIfPQtwMP4jaDsQsDncjTDDsExT4lR/91OLjRo8bmC1e+Cw==",
"cpu": [
"x64"
],
"dev": true,
"optional": true,
"os": [
"freebsd"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-arm": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.20.2.tgz",
"integrity": "sha512-VhLPeR8HTMPccbuWWcEUD1Az68TqaTYyj6nfE4QByZIQEQVWBB8vup8PpR7y1QHL3CpcF6xd5WVBU/+SBEvGTg==",
"cpu": [
"arm"
],
"dev": true,
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-arm64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.20.2.tgz",
"integrity": "sha512-9pb6rBjGvTFNira2FLIWqDk/uaf42sSyLE8j1rnUpuzsODBq7FvpwHYZxQ/It/8b+QOS1RYfqgGFNLRI+qlq2A==",
"cpu": [
"arm64"
],
"dev": true,
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-ia32": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.20.2.tgz",
"integrity": "sha512-o10utieEkNPFDZFQm9CoP7Tvb33UutoJqg3qKf1PWVeeJhJw0Q347PxMvBgVVFgouYLGIhFYG0UGdBumROyiig==",
"cpu": [
"ia32"
],
"dev": true,
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-loong64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.20.2.tgz",
"integrity": "sha512-PR7sp6R/UC4CFVomVINKJ80pMFlfDfMQMYynX7t1tNTeivQ6XdX5r2XovMmha/VjR1YN/HgHWsVcTRIMkymrgQ==",
"cpu": [
"loong64"
],
"dev": true,
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-mips64el": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.20.2.tgz",
"integrity": "sha512-4BlTqeutE/KnOiTG5Y6Sb/Hw6hsBOZapOVF6njAESHInhlQAghVVZL1ZpIctBOoTFbQyGW+LsVYZ8lSSB3wkjA==",
"cpu": [
"mips64el"
],
"dev": true,
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-ppc64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.20.2.tgz",
"integrity": "sha512-rD3KsaDprDcfajSKdn25ooz5J5/fWBylaaXkuotBDGnMnDP1Uv5DLAN/45qfnf3JDYyJv/ytGHQaziHUdyzaAg==",
"cpu": [
"ppc64"
],
"dev": true,
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-riscv64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.20.2.tgz",
"integrity": "sha512-snwmBKacKmwTMmhLlz/3aH1Q9T8v45bKYGE3j26TsaOVtjIag4wLfWSiZykXzXuE1kbCE+zJRmwp+ZbIHinnVg==",
"cpu": [
"riscv64"
],
"dev": true,
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-s390x": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.20.2.tgz",
"integrity": "sha512-wcWISOobRWNm3cezm5HOZcYz1sKoHLd8VL1dl309DiixxVFoFe/o8HnwuIwn6sXre88Nwj+VwZUvJf4AFxkyrQ==",
"cpu": [
"s390x"
],
"dev": true,
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/linux-x64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.20.2.tgz",
"integrity": "sha512-1MdwI6OOTsfQfek8sLwgyjOXAu+wKhLEoaOLTjbijk6E2WONYpH9ZU2mNtR+lZ2B4uwr+usqGuVfFT9tMtGvGw==",
"cpu": [
"x64"
],
"dev": true,
"optional": true,
"os": [
"linux"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/netbsd-x64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.20.2.tgz",
"integrity": "sha512-K8/DhBxcVQkzYc43yJXDSyjlFeHQJBiowJ0uVL6Tor3jGQfSGHNNJcWxNbOI8v5k82prYqzPuwkzHt3J1T1iZQ==",
"cpu": [
"x64"
],
"dev": true,
"optional": true,
"os": [
"netbsd"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/openbsd-x64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.20.2.tgz",
"integrity": "sha512-eMpKlV0SThJmmJgiVyN9jTPJ2VBPquf6Kt/nAoo6DgHAoN57K15ZghiHaMvqjCye/uU4X5u3YSMgVBI1h3vKrQ==",
"cpu": [
"x64"
],
"dev": true,
"optional": true,
"os": [
"openbsd"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/sunos-x64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.20.2.tgz",
"integrity": "sha512-2UyFtRC6cXLyejf/YEld4Hajo7UHILetzE1vsRcGL3earZEW77JxrFjH4Ez2qaTiEfMgAXxfAZCm1fvM/G/o8w==",
"cpu": [
"x64"
],
"dev": true,
"optional": true,
"os": [
"sunos"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/win32-arm64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.20.2.tgz",
"integrity": "sha512-GRibxoawM9ZCnDxnP3usoUDO9vUkpAxIIZ6GQI+IlVmr5kP3zUq+l17xELTHMWTWzjxa2guPNyrpq1GWmPvcGQ==",
"cpu": [
"arm64"
],
"dev": true,
"optional": true,
"os": [
"win32"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/win32-ia32": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.20.2.tgz",
"integrity": "sha512-HfLOfn9YWmkSKRQqovpnITazdtquEW8/SoHW7pWpuEeguaZI4QnCRW6b+oZTztdBnZOS2hqJ6im/D5cPzBTTlQ==",
"cpu": [
"ia32"
],
"dev": true,
"optional": true,
"os": [
"win32"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@esbuild/win32-x64": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.20.2.tgz",
"integrity": "sha512-N49X4lJX27+l9jbLKSqZ6bKNjzQvHaT8IIFUy+YIqmXQdjYCToGWwOItDrfby14c78aDd5NHQl29xingXfCdLQ==",
"cpu": [
"x64"
],
"dev": true,
"optional": true,
"os": [
"win32"
],
"engines": {
"node": ">=12"
}
},
"node_modules/@jridgewell/resolve-uri": {
"version": "3.1.2",
"resolved": "https://registry.npmjs.org/@jridgewell/resolve-uri/-/resolve-uri-3.1.2.tgz",
"integrity": "sha512-bRISgCIjP20/tbWSPWMEi54QVPRZExkuD9lJL+UIxUKtwVJA8wW1Trb1jMs1RFXo1CBTNZ/5hpC9QvmKWdopKw==",
"engines": {
"node": ">=6.0.0"
}
},
"node_modules/@jridgewell/sourcemap-codec": {
"version": "1.4.15",
"resolved": "https://registry.npmjs.org/@jridgewell/sourcemap-codec/-/sourcemap-codec-1.4.15.tgz",
"integrity": "sha512-eF2rxCRulEKXHTRiDrDy6erMYWqNw4LPdQ8UQA4huuxaQsVeRPFl2oM8oDGxMFhJUWZf9McpLtJasDDZb/Bpeg=="
},
"node_modules/@jridgewell/trace-mapping": {
"version": "0.3.9",
"resolved": "https://registry.npmjs.org/@jridgewell/trace-mapping/-/trace-mapping-0.3.9.tgz",
"integrity": "sha512-3Belt6tdc8bPgAtbcmdtNJlirVoTmEb5e2gC94PnkwEW9jI6CAHUeoG85tjWP5WquqfavoMtMwiG4P926ZKKuQ==",
"dependencies": {
"@jridgewell/resolve-uri": "^3.0.3",
"@jridgewell/sourcemap-codec": "^1.4.10"
} }
}, },
"node_modules/@mendable/firecrawl-js": { "node_modules/@mendable/firecrawl-js": {
"version": "0.0.15", "version": "0.0.19",
"resolved": "https://registry.npmjs.org/@mendable/firecrawl-js/-/firecrawl-js-0.0.15.tgz", "resolved": "https://registry.npmjs.org/@mendable/firecrawl-js/-/firecrawl-js-0.0.19.tgz",
"integrity": "sha512-e3iCCrLIiEh+jEDerGV9Uhdkn8ymo+sG+k3osCwPg51xW1xUdAnmlcHrcJoR43RvKXdvD/lqoxg8odUEsqyH+w==", "integrity": "sha512-u9BDVIN/bftDztxLlE2cf02Nz0si3+Vmy9cANDFHj/iriT3guzI8ITBk4uC81CyRmPzNyXrW6hSAG90g9ol4cA==",
"dependencies": { "dependencies": {
"axios": "^1.6.8", "axios": "^1.6.8",
"dotenv": "^16.4.5" "zod": "^3.23.8",
"zod-to-json-schema": "^3.23.0"
} }
}, },
"node_modules/@tsconfig/node10": {
"version": "1.0.11",
"resolved": "https://registry.npmjs.org/@tsconfig/node10/-/node10-1.0.11.tgz",
"integrity": "sha512-DcRjDCujK/kCk/cUe8Xz8ZSpm8mS3mNNpta+jGCA6USEDfktlNvm1+IuZ9eTcDbNk41BHwpHHeW+N1lKCz4zOw=="
},
"node_modules/@tsconfig/node12": {
"version": "1.0.11",
"resolved": "https://registry.npmjs.org/@tsconfig/node12/-/node12-1.0.11.tgz",
"integrity": "sha512-cqefuRsh12pWyGsIoBKJA9luFu3mRxCA+ORZvA4ktLSzIuCUtWVxGIuXigEwO5/ywWFMZ2QEGKWvkZG1zDMTag=="
},
"node_modules/@tsconfig/node14": {
"version": "1.0.3",
"resolved": "https://registry.npmjs.org/@tsconfig/node14/-/node14-1.0.3.tgz",
"integrity": "sha512-ysT8mhdixWK6Hw3i1V2AeRqZ5WfXg1G43mqoYlM2nc6388Fq5jcXyr5mRsqViLx/GJYdoL0bfXD8nmF+Zn/Iow=="
},
"node_modules/@tsconfig/node16": {
"version": "1.0.4",
"resolved": "https://registry.npmjs.org/@tsconfig/node16/-/node16-1.0.4.tgz",
"integrity": "sha512-vxhUy4J8lyeyinH7Azl1pdd43GJhZH/tP2weN8TntQblOY+A0XbT8DJk1/oCPuOOyg/Ja757rG0CgHcWC8OfMA=="
},
"node_modules/@types/node": {
"version": "20.12.11",
"resolved": "https://registry.npmjs.org/@types/node/-/node-20.12.11.tgz",
"integrity": "sha512-vDg9PZ/zi+Nqp6boSOT7plNuthRugEKixDv5sFTIpkE89MmNtEArAShI4mxuX2+UrLEe9pxC1vm2cjm9YlWbJw==",
"peer": true,
"dependencies": {
"undici-types": "~5.26.4"
}
},
"node_modules/acorn": {
"version": "8.11.3",
"resolved": "https://registry.npmjs.org/acorn/-/acorn-8.11.3.tgz",
"integrity": "sha512-Y9rRfJG5jcKOE0CLisYbojUjIrIEE7AGMzA/Sm4BslANhbS+cDMpgBdcPT91oJ7OuJ9hYJBx59RjbhxVnrF8Xg==",
"bin": {
"acorn": "bin/acorn"
},
"engines": {
"node": ">=0.4.0"
}
},
"node_modules/acorn-walk": {
"version": "8.3.2",
"resolved": "https://registry.npmjs.org/acorn-walk/-/acorn-walk-8.3.2.tgz",
"integrity": "sha512-cjkyv4OtNCIeqhHrfS81QWXoCBPExR/J62oyEqepVw8WaQeSqpW2uhuLPh1m9eWhDuOo/jUXVTlifvesOWp/4A==",
"engines": {
"node": ">=0.4.0"
}
},
"node_modules/arg": {
"version": "4.1.3",
"resolved": "https://registry.npmjs.org/arg/-/arg-4.1.3.tgz",
"integrity": "sha512-58S9QDqG0Xx27YwPSt9fJxivjYl432YCwfDMfZ+71RAqUrZef7LrKQZ3LHLOwCS4FLNBplP533Zx895SeOCHvA=="
},
"node_modules/asynckit": { "node_modules/asynckit": {
"version": "0.4.0", "version": "0.4.0",
"resolved": "https://registry.npmjs.org/asynckit/-/asynckit-0.4.0.tgz", "resolved": "https://registry.npmjs.org/asynckit/-/asynckit-0.4.0.tgz",
@ -49,6 +510,11 @@
"node": ">= 0.8" "node": ">= 0.8"
} }
}, },
"node_modules/create-require": {
"version": "1.1.1",
"resolved": "https://registry.npmjs.org/create-require/-/create-require-1.1.1.tgz",
"integrity": "sha512-dcKFX3jn0MpIaXjisoRvexIJVEKzaq7z2rZKxf+MSr9TkdmHmsU4m2lcLojrj/FHl8mk5VxMmYA+ftRkP/3oKQ=="
},
"node_modules/delayed-stream": { "node_modules/delayed-stream": {
"version": "1.0.0", "version": "1.0.0",
"resolved": "https://registry.npmjs.org/delayed-stream/-/delayed-stream-1.0.0.tgz", "resolved": "https://registry.npmjs.org/delayed-stream/-/delayed-stream-1.0.0.tgz",
@ -57,15 +523,50 @@
"node": ">=0.4.0" "node": ">=0.4.0"
} }
}, },
"node_modules/dotenv": { "node_modules/diff": {
"version": "16.4.5", "version": "4.0.2",
"resolved": "https://registry.npmjs.org/dotenv/-/dotenv-16.4.5.tgz", "resolved": "https://registry.npmjs.org/diff/-/diff-4.0.2.tgz",
"integrity": "sha512-ZmdL2rui+eB2YwhsWzjInR8LldtZHGDoQ1ugH85ppHKwpUHL7j7rN0Ti9NCnGiQbhaZ11FpR+7ao1dNsmduNUg==", "integrity": "sha512-58lmxKSA4BNyLz+HHMUzlOEpg09FV+ev6ZMe3vJihgdxzgcwZ8VoEEPmALCZG9LmqfVoNMMKpttIYTVG6uDY7A==",
"engines": {
"node": ">=0.3.1"
}
},
"node_modules/esbuild": {
"version": "0.20.2",
"resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.20.2.tgz",
"integrity": "sha512-WdOOppmUNU+IbZ0PaDiTst80zjnrOkyJNHoKupIcVyU8Lvla3Ugx94VzkQ32Ijqd7UhHJy75gNWDMUekcrSJ6g==",
"dev": true,
"hasInstallScript": true,
"bin": {
"esbuild": "bin/esbuild"
},
"engines": { "engines": {
"node": ">=12" "node": ">=12"
}, },
"funding": { "optionalDependencies": {
"url": "https://dotenvx.com" "@esbuild/aix-ppc64": "0.20.2",
"@esbuild/android-arm": "0.20.2",
"@esbuild/android-arm64": "0.20.2",
"@esbuild/android-x64": "0.20.2",
"@esbuild/darwin-arm64": "0.20.2",
"@esbuild/darwin-x64": "0.20.2",
"@esbuild/freebsd-arm64": "0.20.2",
"@esbuild/freebsd-x64": "0.20.2",
"@esbuild/linux-arm": "0.20.2",
"@esbuild/linux-arm64": "0.20.2",
"@esbuild/linux-ia32": "0.20.2",
"@esbuild/linux-loong64": "0.20.2",
"@esbuild/linux-mips64el": "0.20.2",
"@esbuild/linux-ppc64": "0.20.2",
"@esbuild/linux-riscv64": "0.20.2",
"@esbuild/linux-s390x": "0.20.2",
"@esbuild/linux-x64": "0.20.2",
"@esbuild/netbsd-x64": "0.20.2",
"@esbuild/openbsd-x64": "0.20.2",
"@esbuild/sunos-x64": "0.20.2",
"@esbuild/win32-arm64": "0.20.2",
"@esbuild/win32-ia32": "0.20.2",
"@esbuild/win32-x64": "0.20.2"
} }
}, },
"node_modules/follow-redirects": { "node_modules/follow-redirects": {
@ -100,6 +601,37 @@
"node": ">= 6" "node": ">= 6"
} }
}, },
"node_modules/fsevents": {
"version": "2.3.3",
"resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.3.tgz",
"integrity": "sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==",
"dev": true,
"hasInstallScript": true,
"optional": true,
"os": [
"darwin"
],
"engines": {
"node": "^8.16.0 || ^10.6.0 || >=11.0.0"
}
},
"node_modules/get-tsconfig": {
"version": "4.7.4",
"resolved": "https://registry.npmjs.org/get-tsconfig/-/get-tsconfig-4.7.4.tgz",
"integrity": "sha512-ofbkKj+0pjXjhejr007J/fLf+sW+8H7K5GCm+msC8q3IpvgjobpyPqSRFemNyIMxklC0zeJpi7VDFna19FacvQ==",
"dev": true,
"dependencies": {
"resolve-pkg-maps": "^1.0.0"
},
"funding": {
"url": "https://github.com/privatenumber/get-tsconfig?sponsor=1"
}
},
"node_modules/make-error": {
"version": "1.3.6",
"resolved": "https://registry.npmjs.org/make-error/-/make-error-1.3.6.tgz",
"integrity": "sha512-s8UhlNe7vPKomQhC1qFelMokr/Sc3AgNbso3n74mVPA5LTZwkB9NlXf4XPamLxJE8h0gh73rM94xvwRT2CVInw=="
},
"node_modules/mime-db": { "node_modules/mime-db": {
"version": "1.52.0", "version": "1.52.0",
"resolved": "https://registry.npmjs.org/mime-db/-/mime-db-1.52.0.tgz", "resolved": "https://registry.npmjs.org/mime-db/-/mime-db-1.52.0.tgz",
@ -124,6 +656,123 @@
"resolved": "https://registry.npmjs.org/proxy-from-env/-/proxy-from-env-1.1.0.tgz", "resolved": "https://registry.npmjs.org/proxy-from-env/-/proxy-from-env-1.1.0.tgz",
"integrity": "sha512-D+zkORCbA9f1tdWRK0RaCR3GPv50cMxcrz4X8k5LTSUD1Dkw47mKJEZQNunItRTkWwgtaUSo1RVFRIG9ZXiFYg==" "integrity": "sha512-D+zkORCbA9f1tdWRK0RaCR3GPv50cMxcrz4X8k5LTSUD1Dkw47mKJEZQNunItRTkWwgtaUSo1RVFRIG9ZXiFYg=="
}, },
"node_modules/resolve-pkg-maps": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/resolve-pkg-maps/-/resolve-pkg-maps-1.0.0.tgz",
"integrity": "sha512-seS2Tj26TBVOC2NIc2rOe2y2ZO7efxITtLZcGSOnHHNOQ7CkiUBfw0Iw2ck6xkIhPwLhKNLS8BO+hEpngQlqzw==",
"dev": true,
"funding": {
"url": "https://github.com/privatenumber/resolve-pkg-maps?sponsor=1"
}
},
"node_modules/ts-node": {
"version": "10.9.2",
"resolved": "https://registry.npmjs.org/ts-node/-/ts-node-10.9.2.tgz",
"integrity": "sha512-f0FFpIdcHgn8zcPSbf1dRevwt047YMnaiJM3u2w2RewrB+fob/zePZcrOyQoLMMO7aBIddLcQIEK5dYjkLnGrQ==",
"dependencies": {
"@cspotcode/source-map-support": "^0.8.0",
"@tsconfig/node10": "^1.0.7",
"@tsconfig/node12": "^1.0.7",
"@tsconfig/node14": "^1.0.0",
"@tsconfig/node16": "^1.0.2",
"acorn": "^8.4.1",
"acorn-walk": "^8.1.1",
"arg": "^4.1.0",
"create-require": "^1.1.0",
"diff": "^4.0.1",
"make-error": "^1.1.1",
"v8-compile-cache-lib": "^3.0.1",
"yn": "3.1.1"
},
"bin": {
"ts-node": "dist/bin.js",
"ts-node-cwd": "dist/bin-cwd.js",
"ts-node-esm": "dist/bin-esm.js",
"ts-node-script": "dist/bin-script.js",
"ts-node-transpile-only": "dist/bin-transpile.js",
"ts-script": "dist/bin-script-deprecated.js"
},
"peerDependencies": {
"@swc/core": ">=1.2.50",
"@swc/wasm": ">=1.2.50",
"@types/node": "*",
"typescript": ">=2.7"
},
"peerDependenciesMeta": {
"@swc/core": {
"optional": true
},
"@swc/wasm": {
"optional": true
}
}
},
"node_modules/tsx": {
"version": "4.9.3",
"resolved": "https://registry.npmjs.org/tsx/-/tsx-4.9.3.tgz",
"integrity": "sha512-czVbetlILiyJZI5zGlj2kw9vFiSeyra9liPD4nG+Thh4pKTi0AmMEQ8zdV/L2xbIVKrIqif4sUNrsMAOksx9Zg==",
"dev": true,
"dependencies": {
"esbuild": "~0.20.2",
"get-tsconfig": "^4.7.3"
},
"bin": {
"tsx": "dist/cli.mjs"
},
"engines": {
"node": ">=18.0.0"
},
"optionalDependencies": {
"fsevents": "~2.3.3"
}
},
"node_modules/typescript": {
"version": "5.4.5",
"resolved": "https://registry.npmjs.org/typescript/-/typescript-5.4.5.tgz",
"integrity": "sha512-vcI4UpRgg81oIRUFwR0WSIHKt11nJ7SAVlYNIu+QpqeyXP+gpQJy/Z4+F0aGxSE4MqwjyXvW/TzgkLAx2AGHwQ==",
"bin": {
"tsc": "bin/tsc",
"tsserver": "bin/tsserver"
},
"engines": {
"node": ">=14.17"
}
},
"node_modules/undici-types": {
"version": "5.26.5",
"resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz",
"integrity": "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA==",
"peer": true
},
"node_modules/v8-compile-cache-lib": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/v8-compile-cache-lib/-/v8-compile-cache-lib-3.0.1.tgz",
"integrity": "sha512-wa7YjyUGfNZngI/vtK0UHAN+lgDCxBPCylVXGp0zu59Fz5aiGtNXaq3DhIov063MorB+VfufLh3JlF2KdTK3xg=="
},
"node_modules/yn": {
"version": "3.1.1",
"resolved": "https://registry.npmjs.org/yn/-/yn-3.1.1.tgz",
"integrity": "sha512-Ux4ygGWsu2c7isFWe8Yu1YluJmqVhxqK2cLXNQA5AcC3QfbGNpM7fu0Y8b/z16pXLnFxZYvWhd3fhBY9DLmC6Q==",
"engines": {
"node": ">=6"
}
},
"node_modules/zod": {
"version": "3.23.8",
"resolved": "https://registry.npmjs.org/zod/-/zod-3.23.8.tgz",
"integrity": "sha512-XBx9AXhXktjUqnepgTiE5flcKIYWi/rme0Eaj+5Y0lftuGBq+jyRu/md4WnuxqgP1ubdpNCsYEYPxrzVHD8d6g==",
"funding": {
"url": "https://github.com/sponsors/colinhacks"
}
},
"node_modules/zod-to-json-schema": {
"version": "3.23.0",
"resolved": "https://registry.npmjs.org/zod-to-json-schema/-/zod-to-json-schema-3.23.0.tgz",
"integrity": "sha512-az0uJ243PxsRIa2x1WmNE/pnuA05gUq/JB8Lwe1EDCCL/Fz9MgjYQ0fPlyc2Tcv6aF2ZA7WM5TWaRZVEFaAIag==",
"peerDependencies": {
"zod": "^3.23.3"
}
},
"node_modules/uuid": { "node_modules/uuid": {
"version": "9.0.1", "version": "9.0.1",
"resolved": "https://registry.npmjs.org/uuid/-/uuid-9.0.1.tgz", "resolved": "https://registry.npmjs.org/uuid/-/uuid-9.0.1.tgz",

10
apps/js-sdk/package.json
View File

@ -11,8 +11,14 @@
"author": "", "author": "",
"license": "ISC", "license": "ISC",
"dependencies": { "dependencies": {
"@mendable/firecrawl-js": "^0.0.15",
"axios": "^1.6.8", "axios": "^1.6.8",
"uuid": "^9.0.1" "uuid": "^9.0.1",
"@mendable/firecrawl-js": "^0.0.19",
"ts-node": "^10.9.2",
"typescript": "^5.4.5",
"zod": "^3.23.8"
},
"devDependencies": {
"tsx": "^4.9.3"
} }
} }

28
apps/js-sdk/test.ts Normal file
View File

@ -0,0 +1,28 @@
import FirecrawlApp from "@mendable/firecrawl-js";
import { z } from "zod";
async function a() {
const app = new FirecrawlApp({
apiKey: "fc-YOUR_API_KEY",
});
// Define schema to extract contents into
const schema = z.object({
top: z
.array(
z.object({
title: z.string(),
points: z.number(),
by: z.string(),
commentsURL: z.string(),
})
)
.length(5)
.describe("Top 5 stories on Hacker News"),
});
const scrapeResult = await app.scrapeUrl("https://firecrawl.dev", {
extractorOptions: { extractionSchema: schema },
});
console.log(scrapeResult.data["llm_extraction"]);
}
a();

72
apps/js-sdk/tsconfig.json Normal file
View File

@ -0,0 +1,72 @@
{
"compilerOptions": {
/* Visit https://aka.ms/tsconfig.json to read more about this file */
/* Basic Options */
// "incremental": true, /* Enable incremental compilation */
"target": "es6" /* Specify ECMAScript target version: 'ES3' (default), 'ES5', 'ES2015', 'ES2016', 'ES2017', 'ES2018', 'ES2019', 'ES2020', or 'ESNEXT'. */,
"module": "commonjs" /* Specify module code generation: 'none', 'commonjs', 'amd', 'system', 'umd', 'es2015', 'es2020', or 'ESNext'. */,
// "lib": [], /* Specify library files to be included in the compilation. */
// "allowJs": true, /* Allow javascript files to be compiled. */
// "checkJs": true, /* Report errors in .js files. */
// "jsx": "preserve", /* Specify JSX code generation: 'preserve', 'react-native', or 'react'. */
"declaration": true /* Generates corresponding '.d.ts' file. */,
// "declarationMap": true, /* Generates a sourcemap for each corresponding '.d.ts' file. */
// "sourceMap": true, /* Generates corresponding '.map' file. */
// "outFile": "./", /* Concatenate and emit output to single file. */
"outDir": "./build" /* Redirect output structure to the directory. */,
// "rootDir": "./", /* Specify the root directory of input files. Use to control the output directory structure with --outDir. */
// "composite": true, /* Enable project compilation */
// "tsBuildInfoFile": "./", /* Specify file to store incremental compilation information */
// "removeComments": true, /* Do not emit comments to output. */
// "noEmit": true, /* Do not emit outputs. */
// "importHelpers": true, /* Import emit helpers from 'tslib'. */
// "downlevelIteration": true, /* Provide full support for iterables in 'for-of', spread, and destructuring when targeting 'ES5' or 'ES3'. */
// "isolatedModules": true, /* Transpile each file as a separate module (similar to 'ts.transpileModule'). */
/* Strict Type-Checking Options */
"strict": false /* Enable all strict type-checking options. */,
// "noImplicitAny": true, /* Raise error on expressions and declarations with an implied 'any' type. */
// "strictNullChecks": true, /* Enable strict null checks. */
// "strictFunctionTypes": true, /* Enable strict checking of function types. */
// "strictBindCallApply": true, /* Enable strict 'bind', 'call', and 'apply' methods on functions. */
// "strictPropertyInitialization": true, /* Enable strict checking of property initialization in classes. */
// "noImplicitThis": true, /* Raise error on 'this' expressions with an implied 'any' type. */
// "alwaysStrict": true, /* Parse in strict mode and emit "use strict" for each source file. */
/* Additional Checks */
// "noUnusedLocals": true, /* Report errors on unused locals. */
// "noUnusedParameters": true, /* Report errors on unused parameters. */
// "noImplicitReturns": true, /* Report error when not all code paths in function return a value. */
// "noFallthroughCasesInSwitch": true, /* Report errors for fallthrough cases in switch statement. */
/* Module Resolution Options */
// "moduleResolution": "node", /* Specify module resolution strategy: 'node' (Node.js) or 'classic' (TypeScript pre-1.6). */
// "baseUrl": "./", /* Base directory to resolve non-absolute module names. */
// "paths": {}, /* A series of entries which re-map imports to lookup locations relative to the 'baseUrl'. */
// "rootDirs": [], /* List of root folders whose combined content represents the structure of the project at runtime. */
// "typeRoots": [], /* List of folders to include type definitions from. */
// "types": [], /* Type declaration files to be included in compilation. */
// "allowSyntheticDefaultImports": true, /* Allow default imports from modules with no default export. This does not affect code emit, just typechecking. */
"resolveJsonModule": true,
"esModuleInterop": true /* Enables emit interoperability between CommonJS and ES Modules via creation of namespace objects for all imports. Implies 'allowSyntheticDefaultImports'. */,
// "preserveSymlinks": true, /* Do not resolve the real path of symlinks. */
// "allowUmdGlobalAccess": true, /* Allow accessing UMD globals from modules. */
/* Source Map Options */
// "sourceRoot": "", /* Specify the location where debugger should locate TypeScript files instead of source locations. */
// "mapRoot": "", /* Specify the location where debugger should locate map files instead of generated locations. */
// "inlineSourceMap": true, /* Emit a single file with source maps instead of having a separate file. */
// "inlineSources": true, /* Emit the source alongside the sourcemaps within a single file; requires '--inlineSourceMap' or '--sourceMap' to be set. */
/* Experimental Options */
// "experimentalDecorators": true, /* Enables experimental support for ES7 decorators. */
// "emitDecoratorMetadata": true, /* Enables experimental support for emitting type metadata for decorators. */
/* Advanced Options */
"skipLibCheck": true /* Skip type checking of declaration files. */,
"forceConsistentCasingInFileNames": true /* Disallow inconsistently-cased references to the same file. */
},
"include": ["src", "test.ts"],
"exclude": ["node_modules", "**/__tests__/*"]
}

6
apps/playwright-service/main.py
View File

@ -5,9 +5,9 @@ from pydantic import BaseModel
app = FastAPI() app = FastAPI()
class UrlModel(BaseModel): class UrlModel(BaseModel):
url: str url: str
wait: int = None
browser: Browser = None browser: Browser = None
@ -29,7 +29,9 @@ async def shutdown_event():
async def root(body: UrlModel): async def root(body: UrlModel):
context = await browser.new_context() context = await browser.new_context()
page = await context.new_page() page = await context.new_page()
await page.goto(body.url) await page.goto(body.url, timeout=15000) # Set max timeout to 15s
if body.wait: # Check if wait parameter is provided in the request body
await page.wait_for_timeout(body.wait) # Convert seconds to milliseconds for playwright
page_content = await page.content() page_content = await page.content()
await context.close() await context.close()
json_compatible_item_data = {"content": page_content} json_compatible_item_data = {"content": page_content}

25
apps/python-sdk/README.md
View File

@ -46,6 +46,31 @@ To scrape a single URL, use the `scrape_url` method. It takes the URL as a param
url = 'https://example.com' url = 'https://example.com'
scraped_data = app.scrape_url(url) scraped_data = app.scrape_url(url)
``` ```
### Extracting structured data from a URL
With LLM extraction, you can easily extract structured data from any URL. We support pydantic schemas to make it easier for you too. Here is how you to use it:
```python
class ArticleSchema(BaseModel):
title: str
points: int
by: str
commentsURL: str
class TopArticlesSchema(BaseModel):
top: List[ArticleSchema] = Field(..., max_items=5, description="Top 5 stories")
data = app.scrape_url('https://news.ycombinator.com', {
'extractorOptions': {
'extractionSchema': TopArticlesSchema.model_json_schema(),
'mode': 'llm-extraction'
},
'pageOptions':{
'onlyMainContent': True
}
})
print(data["llm_extraction"])
```
### Search for a query ### Search for a query

70
apps/python-sdk/build/lib/firecrawl/firecrawl.py
View File

@ -1,33 +1,55 @@
import os import os
from typing import Any, Dict, Optional
import requests import requests
import time
class FirecrawlApp: class FirecrawlApp:
def __init__(self, api_key=None): def __init__(self, api_key=None, api_url='https://api.firecrawl.dev'):
self.api_key = api_key or os.getenv('FIRECRAWL_API_KEY') self.api_key = api_key or os.getenv('FIRECRAWL_API_KEY')
if self.api_key is None: if self.api_key is None:
raise ValueError('No API key provided') raise ValueError('No API key provided')
self.api_url = api_url or os.getenv('FIRECRAWL_API_URL')
def scrape_url(self, url, params=None):
def scrape_url(self, url: str, params: Optional[Dict[str, Any]] = None) -> Any:
headers = { headers = {
'Content-Type': 'application/json', 'Content-Type': 'application/json',
'Authorization': f'Bearer {self.api_key}' 'Authorization': f'Bearer {self.api_key}'
} }
json_data = {'url': url} # Prepare the base scrape parameters with the URL
scrape_params = {'url': url}
# If there are additional params, process them
if params: if params:
json_data.update(params) # Initialize extractorOptions if present
extractor_options = params.get('extractorOptions', {})
# Check and convert the extractionSchema if it's a Pydantic model
if 'extractionSchema' in extractor_options:
if hasattr(extractor_options['extractionSchema'], 'schema'):
extractor_options['extractionSchema'] = extractor_options['extractionSchema'].schema()
# Ensure 'mode' is set, defaulting to 'llm-extraction' if not explicitly provided
extractor_options['mode'] = extractor_options.get('mode', 'llm-extraction')
# Update the scrape_params with the processed extractorOptions
scrape_params['extractorOptions'] = extractor_options
# Include any other params directly at the top level of scrape_params
for key, value in params.items():
if key != 'extractorOptions':
scrape_params[key] = value
# Make the POST request with the prepared headers and JSON data
response = requests.post( response = requests.post(
'https://api.firecrawl.dev/v0/scrape', f'{self.api_url}/v0/scrape',
headers=headers, headers=headers,
json=json_data json=scrape_params
) )
if response.status_code == 200: if response.status_code == 200:
response = response.json() response = response.json()
if response['success'] == True: if response['success']:
return response['data'] return response['data']
else: else:
raise Exception(f'Failed to scrape URL. Error: {response["error"]}') raise Exception(f'Failed to scrape URL. Error: {response["error"]}')
elif response.status_code in [402, 408, 409, 500]:
elif response.status_code in [402, 409, 500]:
error_message = response.json().get('error', 'Unknown error occurred') error_message = response.json().get('error', 'Unknown error occurred')
raise Exception(f'Failed to scrape URL. Status code: {response.status_code}. Error: {error_message}') raise Exception(f'Failed to scrape URL. Status code: {response.status_code}. Error: {error_message}')
else: else:
@ -42,7 +64,7 @@ class FirecrawlApp:
if params: if params:
json_data.update(params) json_data.update(params)
response = requests.post( response = requests.post(
'https://api.firecrawl.dev/v0/search', f'{self.api_url}/v0/search',
headers=headers, headers=headers,
json=json_data json=json_data
) )
@ -64,7 +86,7 @@ class FirecrawlApp:
json_data = {'url': url} json_data = {'url': url}
if params: if params:
json_data.update(params) json_data.update(params)
response = self._post_request('https://api.firecrawl.dev/v0/crawl', json_data, headers) response = self._post_request(f'{self.api_url}/v0/crawl', json_data, headers)
if response.status_code == 200: if response.status_code == 200:
job_id = response.json().get('jobId') job_id = response.json().get('jobId')
if wait_until_done: if wait_until_done:
@ -76,7 +98,7 @@ class FirecrawlApp:
def check_crawl_status(self, job_id): def check_crawl_status(self, job_id):
headers = self._prepare_headers() headers = self._prepare_headers()
response = self._get_request(f'https://api.firecrawl.dev/v0/crawl/status/{job_id}', headers) response = self._get_request(f'{self.api_url}/v0/crawl/status/{job_id}', headers)
if response.status_code == 200: if response.status_code == 200:
return response.json() return response.json()
else: else:
@ -88,16 +110,28 @@ class FirecrawlApp:
'Authorization': f'Bearer {self.api_key}' 'Authorization': f'Bearer {self.api_key}'
} }
def _post_request(self, url, data, headers): def _post_request(self, url, data, headers, retries=3, backoff_factor=0.5):
return requests.post(url, headers=headers, json=data) for attempt in range(retries):
response = requests.post(url, headers=headers, json=data)
if response.status_code == 502:
time.sleep(backoff_factor * (2 ** attempt))
else:
return response
return response
def _get_request(self, url, headers): def _get_request(self, url, headers, retries=3, backoff_factor=0.5):
return requests.get(url, headers=headers) for attempt in range(retries):
response = requests.get(url, headers=headers)
if response.status_code == 502:
time.sleep(backoff_factor * (2 ** attempt))
else:
return response
return response
def _monitor_job_status(self, job_id, headers, timeout): def _monitor_job_status(self, job_id, headers, timeout):
import time import time
while True: while True:
status_response = self._get_request(f'https://api.firecrawl.dev/v0/crawl/status/{job_id}', headers) status_response = self._get_request(f'{self.api_url}/v0/crawl/status/{job_id}', headers)
if status_response.status_code == 200: if status_response.status_code == 200:
status_data = status_response.json() status_data = status_response.json()
if status_data['status'] == 'completed': if status_data['status'] == 'completed':
@ -115,7 +149,7 @@ class FirecrawlApp:
self._handle_error(status_response, 'check crawl status') self._handle_error(status_response, 'check crawl status')
def _handle_error(self, response, action): def _handle_error(self, response, action):
if response.status_code in [402, 409, 500]: if response.status_code in [402, 408, 409, 500]:
error_message = response.json().get('error', 'Unknown error occurred') error_message = response.json().get('error', 'Unknown error occurred')
raise Exception(f'Failed to {action}. Status code: {response.status_code}. Error: {error_message}') raise Exception(f'Failed to {action}. Status code: {response.status_code}. Error: {error_message}')
else: else:

BIN
apps/python-sdk/dist/firecrawl-py-0.0.6.tar.gz vendored
View File

Binary file not shown.

BIN
apps/python-sdk/dist/firecrawl-py-0.0.9.tar.gz vendored Normal file
View File

Binary file not shown.

BIN
apps/python-sdk/dist/firecrawl_py-0.0.6-py3-none-any.whl vendored
View File

Binary file not shown.

BIN
apps/python-sdk/dist/firecrawl_py-0.0.9-py3-none-any.whl vendored Normal file
View File

Binary file not shown.

72
apps/python-sdk/example.py
View File

@ -1,13 +1,73 @@
from firecrawl import FirecrawlApp from firecrawl import FirecrawlApp
app = FirecrawlApp(api_key="fc-YOUR_API_KEY")
app = FirecrawlApp(api_key="YOUR_API_KEY") # Scrape a website:
scrape_result = app.scrape_url('firecrawl.dev')
print(scrape_result['markdown'])
# Crawl a website:
crawl_result = app.crawl_url('mendable.ai', {'crawlerOptions': {'excludes': ['blog/*']}}) crawl_result = app.crawl_url('mendable.ai', {'crawlerOptions': {'excludes': ['blog/*']}})
print(crawl_result[0]['markdown']) print(crawl_result)
job_id = crawl_result['jobId'] # LLM Extraction:
print(job_id) # Define schema to extract contents into using pydantic
from pydantic import BaseModel, Field
from typing import List
status = app.check_crawl_status(job_id) class ArticleSchema(BaseModel):
print(status) title: str
points: int
by: str
commentsURL: str
class TopArticlesSchema(BaseModel):
top: List[ArticleSchema] = Field(..., max_items=5, description="Top 5 stories")
llm_extraction_result = app.scrape_url('https://news.ycombinator.com', {
'extractorOptions': {
'extractionSchema': TopArticlesSchema.model_json_schema(),
'mode': 'llm-extraction'
},
'pageOptions':{
'onlyMainContent': True
}
})
print(llm_extraction_result['llm_extraction'])
# Define schema to extract contents into using json schema
json_schema = {
"type": "object",
"properties": {
"top": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": {"type": "string"},
"points": {"type": "number"},
"by": {"type": "string"},
"commentsURL": {"type": "string"}
},
"required": ["title", "points", "by", "commentsURL"]
},
"minItems": 5,
"maxItems": 5,
"description": "Top 5 stories on Hacker News"
}
},
"required": ["top"]
}
llm_extraction_result = app.scrape_url('https://news.ycombinator.com', {
'extractorOptions': {
'extractionSchema': json_schema,
'mode': 'llm-extraction'
},
'pageOptions':{
'onlyMainContent': True
}
})
print(llm_extraction_result['llm_extraction'])

49
apps/python-sdk/firecrawl/firecrawl.py
View File

@ -1,34 +1,55 @@
import os import os
from typing import Any, Dict, Optional
import requests import requests
import time import time
class FirecrawlApp: class FirecrawlApp:
def __init__(self, api_key=None): def __init__(self, api_key=None, api_url='https://api.firecrawl.dev'):
self.api_key = api_key or os.getenv('FIRECRAWL_API_KEY') self.api_key = api_key or os.getenv('FIRECRAWL_API_KEY')
if self.api_key is None: if self.api_key is None:
raise ValueError('No API key provided') raise ValueError('No API key provided')
self.api_url = api_url or os.getenv('FIRECRAWL_API_URL')
def scrape_url(self, url, params=None):
def scrape_url(self, url: str, params: Optional[Dict[str, Any]] = None) -> Any:
headers = { headers = {
'Content-Type': 'application/json', 'Content-Type': 'application/json',
'Authorization': f'Bearer {self.api_key}' 'Authorization': f'Bearer {self.api_key}'
} }
json_data = {'url': url} # Prepare the base scrape parameters with the URL
scrape_params = {'url': url}
# If there are additional params, process them
if params: if params:
json_data.update(params) # Initialize extractorOptions if present
extractor_options = params.get('extractorOptions', {})
# Check and convert the extractionSchema if it's a Pydantic model
if 'extractionSchema' in extractor_options:
if hasattr(extractor_options['extractionSchema'], 'schema'):
extractor_options['extractionSchema'] = extractor_options['extractionSchema'].schema()
# Ensure 'mode' is set, defaulting to 'llm-extraction' if not explicitly provided
extractor_options['mode'] = extractor_options.get('mode', 'llm-extraction')
# Update the scrape_params with the processed extractorOptions
scrape_params['extractorOptions'] = extractor_options
# Include any other params directly at the top level of scrape_params
for key, value in params.items():
if key != 'extractorOptions':
scrape_params[key] = value
# Make the POST request with the prepared headers and JSON data
response = requests.post( response = requests.post(
'https://api.firecrawl.dev/v0/scrape', f'{self.api_url}/v0/scrape',
headers=headers, headers=headers,
json=json_data json=scrape_params
) )
if response.status_code == 200: if response.status_code == 200:
response = response.json() response = response.json()
if response['success'] == True: if response['success']:
return response['data'] return response['data']
else: else:
raise Exception(f'Failed to scrape URL. Error: {response["error"]}') raise Exception(f'Failed to scrape URL. Error: {response["error"]}')
elif response.status_code in [402, 408, 409, 500]:
elif response.status_code in [402, 409, 500]:
error_message = response.json().get('error', 'Unknown error occurred') error_message = response.json().get('error', 'Unknown error occurred')
raise Exception(f'Failed to scrape URL. Status code: {response.status_code}. Error: {error_message}') raise Exception(f'Failed to scrape URL. Status code: {response.status_code}. Error: {error_message}')
else: else:
@ -43,7 +64,7 @@ class FirecrawlApp:
if params: if params:
json_data.update(params) json_data.update(params)
response = requests.post( response = requests.post(
'https://api.firecrawl.dev/v0/search', f'{self.api_url}/v0/search',
headers=headers, headers=headers,
json=json_data json=json_data
) )
@ -65,7 +86,7 @@ class FirecrawlApp:
json_data = {'url': url} json_data = {'url': url}
if params: if params:
json_data.update(params) json_data.update(params)
response = self._post_request('https://api.firecrawl.dev/v0/crawl', json_data, headers) response = self._post_request(f'{self.api_url}/v0/crawl', json_data, headers)
if response.status_code == 200: if response.status_code == 200:
job_id = response.json().get('jobId') job_id = response.json().get('jobId')
if wait_until_done: if wait_until_done:
@ -77,7 +98,7 @@ class FirecrawlApp:
def check_crawl_status(self, job_id): def check_crawl_status(self, job_id):
headers = self._prepare_headers() headers = self._prepare_headers()
response = self._get_request(f'https://api.firecrawl.dev/v0/crawl/status/{job_id}', headers) response = self._get_request(f'{self.api_url}/v0/crawl/status/{job_id}', headers)
if response.status_code == 200: if response.status_code == 200:
return response.json() return response.json()
else: else:
@ -110,7 +131,7 @@ class FirecrawlApp:
def _monitor_job_status(self, job_id, headers, timeout): def _monitor_job_status(self, job_id, headers, timeout):
import time import time
while True: while True:
status_response = self._get_request(f'https://api.firecrawl.dev/v0/crawl/status/{job_id}', headers) status_response = self._get_request(f'{self.api_url}/v0/crawl/status/{job_id}', headers)
if status_response.status_code == 200: if status_response.status_code == 200:
status_data = status_response.json() status_data = status_response.json()
if status_data['status'] == 'completed': if status_data['status'] == 'completed':
@ -128,7 +149,7 @@ class FirecrawlApp:
self._handle_error(status_response, 'check crawl status') self._handle_error(status_response, 'check crawl status')
def _handle_error(self, response, action): def _handle_error(self, response, action):
if response.status_code in [402, 409, 500]: if response.status_code in [402, 408, 409, 500]:
error_message = response.json().get('error', 'Unknown error occurred') error_message = response.json().get('error', 'Unknown error occurred')
raise Exception(f'Failed to {action}. Status code: {response.status_code}. Error: {error_message}') raise Exception(f'Failed to {action}. Status code: {response.status_code}. Error: {error_message}')
else: else:

2
apps/python-sdk/firecrawl_py.egg-info/PKG-INFO
View File

@ -1,6 +1,6 @@
Metadata-Version: 2.1 Metadata-Version: 2.1
Name: firecrawl-py Name: firecrawl-py
Version: 0.0.6 Version: 0.0.9
Summary: Python SDK for Firecrawl API Summary: Python SDK for Firecrawl API
Home-page: https://github.com/mendableai/firecrawl Home-page: https://github.com/mendableai/firecrawl
Author: Mendable.ai Author: Mendable.ai

2
apps/python-sdk/setup.py
View File

@ -2,7 +2,7 @@ from setuptools import setup, find_packages
setup( setup(
name='firecrawl-py', name='firecrawl-py',
version='0.0.6', version='0.0.9',
url='https://github.com/mendableai/firecrawl', url='https://github.com/mendableai/firecrawl',
author='Mendable.ai', author='Mendable.ai',
author_email='nick@mendable.ai', author_email='nick@mendable.ai',

5
apps/test-suite/.env.example Normal file
View File

@ -0,0 +1,5 @@
OPENAI_API_KEY=
TEST_API_KEY=
TEST_URL=http://localhost:3002
ANTHROPIC_API_KEY=
ENV=

43
apps/test-suite/README.md Normal file
View File

@ -0,0 +1,43 @@
# Test Suite for Firecrawl
This document provides an overview of the test suite for the Firecrawl project. It includes instructions on how to run the tests and interpret the results.
## Overview
The test suite is designed to ensure the reliability and performance of the Firecrawl system. It includes a series of automated tests that check various functionalities and performance metrics.
## Running the Tests
To run the tests, navigate to the `test-suite` directory and execute the following command:
```bash
npm install
npx playwright install
npm run test
```
## Test Results
The tests are designed to cover various aspects of the system, including:
- Crawling accuracy
- Response time
- Error handling
### Example Test Case
- **Test Name**: Accuracy Test
- **Description**: This test checks the accuracy of the scraping mechanism with 100 pages and a fuzzy threshold of 0.8.
- **Expected Result**: Accuracy >= 0.9
- **Received Result**: Accuracy between 0.2 and 0.3
## Troubleshooting
If you encounter any failures or unexpected results, please check the following:
- Ensure your network connection is stable.
- Verify that all dependencies are correctly installed.
- Review the error logs for any specific error messages.
## Contributing
Contributions to the test suite are welcome. Please refer to the project's main [CONTRIBUTING.md](../CONTRIBUTING.md) file for guidelines on how to contribute.

178
apps/test-suite/data/crawl.json Normal file
View File

@ -0,0 +1,178 @@
[
{
"website": "https://www.vellum.ai/llm-leaderboard",
"expected_min_num_of_pages": 1,
"expected_crawled_pages": ["https://www.vellum.ai/llm-leaderboard"]
},
{
"website": "https://openai.com/news",
"expected_min_num_of_pages": 4,
"expected_crawled_pages": [
"https://openai.com/news/company/",
"https://openai.com/news/research/",
"https://openai.com/news/safety-and-alignment/",
"https://openai.com/news/stories/"
]
},
{
"website": "https://www.framer.com/pricing",
"expected_min_num_of_pages": 1,
"expected_not_crawled_pages": [
"https://www.framer.com/features/navigation/",
"https://www.framer.com/contact/",
"https://www.framer.com/add-ons/",
"https://www.framer.com/free-saas-ui-kit/",
"https://www.framer.com/help/",
"https://www.framer.com/features/effects/",
"https://www.framer.com/enterprise/",
"https://www.framer.com/templates/"
]
},
{
"website": "https://mendable.ai/pricing",
"expected_min_num_of_pages": 1,
"expected_not_crawled_pages": [
"https://mendable.ai/",
"https://mendable.ai/blog",
"https://mendable.ai/signin",
"https://mendable.ai/signup",
"https://mendable.ai",
"https://mendable.ai/usecases/sales-enablement",
"https://mendable.ai/usecases/documentation",
"https://mendable.ai/usecases/cs-enablement",
"https://mendable.ai/usecases/productcopilot",
"https://mendable.ai/security"
],
"notes": "This one should not go backwards, but it does!"
},
{
"website": "https://agentops.ai/blog",
"expected_min_num_of_pages": 6,
"expected_crawled_pages": [
"https://www.agentops.ai/blog/effortless-hr-management-with-saas",
"https://www.agentops.ai/blog/streamlining-hr-with-saas",
"https://www.agentops.ai/blog/simplify-hr-with-modern-saas-solutions",
"https://www.agentops.ai/blog/efficient-hr-operations-with-saas",
"https://www.agentops.ai/blog/hr-made-simple-with-saas",
"https://agentops.ai/blog"
],
"expected_not_crawled_pages": [
"https://agentops.ai/about-us",
"https://agentops.ai/contact-us"
]
},
{
"website": "https://en.wikipedia.org/wiki/T._N._Seshan",
"expected_min_num_of_pages": 1,
"expected_not_crawled_pages": [
"https://en.wikipedia.org/wiki/Wikipedia:Contents",
"https://en.wikipedia.org/wiki/Wikipedia:Contact_us",
"https://en.wikipedia.org/wiki/V._S._Ramadevi",
"https://en.wikipedia.org/wiki/Wikipedia:About",
"https://en.wikipedia.org/wiki/Help:Introduction",
"https://en.wikipedia.org/wiki/H._D._Deve_Gowda",
"https://en.wikipedia.org/wiki/File:T.N._Seshan_in_1994.jpg"
]
},
{
"website": "https://ycombinator.com/companies",
"expected_min_num_of_pages": 20,
"expected_crawled_pages": [
"https://www.ycombinator.com/companies/industry/elearning",
"https://www.ycombinator.com/companies/industry/computer-vision",
"https://www.ycombinator.com/companies/industry/health-tech",
"https://www.ycombinator.com/companies/industry/education",
"https://www.ycombinator.com/companies/industry/robotics",
"https://www.ycombinator.com/companies/industry/hardware",
"https://www.ycombinator.com/companies/industry/saas",
"https://www.ycombinator.com/companies/industry/hard-tech",
"https://www.ycombinator.com/companies/industry/developer-tools",
"https://www.ycombinator.com/companies/industry/entertainment",
"https://www.ycombinator.com/companies/industry/finance",
"https://www.ycombinator.com/companies/industry/generative-ai",
"https://www.ycombinator.com/companies/industry/machine-learning"
]
},
{
"website": "https://firecrawl.dev",
"expected_min_num_of_pages": 2,
"expected_crawled_pages": [
"https://firecrawl.dev/",
"https://firecrawl.dev/pricing"
]
},
{
"website": "https://fly.io/docs/gpus/gpu-quickstart",
"expected_min_num_of_pages": 1,
"expected_not_crawled_pages": [
"https://fly.io/docs/getting-started/",
"https://fly.io/docs/hands-on/",
"https://fly.io/docs/about/support/",
"https://fly.io/docs/blueprints/going-to-production-with-healthcare-apps/",
"https://fly.io/docs/machines/flyctl/fly-machine-update/",
"https://fly.io/docs/blueprints/review-apps-guide/",
"https://fly.io/docs/blueprints/supercronic/"
],
"notes": "This one should not go backwards, but it does!"
},
{
"website": "https://www.instructables.com/circuits",
"expected_min_num_of_pages": 12,
"expected_crawled_pages": [
"https://www.instructables.com/circuits/",
"https://www.instructables.com/circuits/apple/projects/",
"https://www.instructables.com/circuits/art/projects/",
"https://www.instructables.com/circuits/electronics/projects/",
"https://www.instructables.com/circuits/microsoft/projects/",
"https://www.instructables.com/circuits/microcontrollers/projects/",
"https://www.instructables.com/circuits/community/",
"https://www.instructables.com/circuits/leds/projects/",
"https://www.instructables.com/circuits/gadgets/projects/",
"https://www.instructables.com/circuits/arduino/projects/",
"https://www.instructables.com/circuits/lasers/projects/",
"https://www.instructables.com/circuits/clocks/projects/"
]
},
{
"website": "https://richmondconfidential.org",
"expected_min_num_of_pages": 20,
"expected_crawled_pages": [
"https://richmondconfidential.org/2009/10/13/salesians-star-guard-has-a-big-impact/",
"https://richmondconfidential.org/2009/10/13/on-team-of-beginners-oilers-old-hand-stands-out/",
"https://richmondconfidential.org/2009/10/19/point-richmond-clockmaker-turns-clutter-into-crafts/",
"https://richmondconfidential.org/2009/10/13/profile-maurice-cathy/",
"https://richmondconfidential.org/2009/10/13/soul-food-rescue-mission-rebuilds-diets-and-lives/",
"https://richmondconfidential.org/2009/10/21/in-tough-economy-pain-trickles-to-the-bottom/",
"https://richmondconfidential.org/2009/10/19/richmond-homicide-map/",
"https://richmondconfidential.org/2009/10/13/rough-roads-for-richmonds-cab-drivers/",
"https://richmondconfidential.org/2009/10/13/before-napa-there-was-winehaven/",
"https://richmondconfidential.org/2009/10/13/family-calls-for-end-to-violence-at-memorial-for-slain-woman-friend/"
]
},
{
"website": "https://www.boardgamegeek.com",
"expected_min_num_of_pages": 15,
"expected_crawled_pages": [
"https://www.boardgamegeek.com/browse/boardgameartist",
"https://www.boardgamegeek.com/browse/boardgamehonor",
"https://www.boardgamegeek.com/browse/boardgamepublisher",
"https://www.boardgamegeek.com/browse/boardgamepodcast",
"https://www.boardgamegeek.com/wiki/page/Index",
"https://www.boardgamegeek.com/browse/boardgamecategory",
"https://www.boardgamegeek.com/boardgame/random",
"https://www.boardgamegeek.com/browse/boardgamemechanic",
"https://www.boardgamegeek.com/forums",
"https://www.boardgamegeek.com/gonecardboard",
"https://www.boardgamegeek.com/browse/boardgameaccessory",
"https://www.boardgamegeek.com/browse/boardgamedesigner",
"https://www.boardgamegeek.com/",
"https://www.boardgamegeek.com/previews",
"https://www.boardgamegeek.com/browse/boardgame"
]
}
]

118
apps/test-suite/data/scrape.json Normal file
View File

@ -0,0 +1,118 @@
[
{
"website": "https://www.anthropic.com/claude",
"prompt": "Does this website contain pricing information?",
"expected_output": "yes"
},
{
"website": "https://mendable.ai/pricing",
"prompt": "Does this website contain pricing information?",
"expected_output": "yes"
},
{
"website": "https://openai.com/news",
"prompt": "Does this website contain a list of research news?",
"expected_output": "yes"
},
{
"website": "https://agentops.ai",
"prompt": "Does this website contain a code snippets?",
"expected_output": "yes"
},
{
"website": "https://ycombinator.com/companies",
"prompt": "Does this website contain a list bigger than 5 of ycombinator companies?",
"expected_output": "yes"
},
{
"website": "https://firecrawl.dev",
"prompt": "Does this website contain a list bigger than 5 of ycombinator companies?",
"expected_output": "no"
},
{
"website": "https://en.wikipedia.org/wiki/T._N._Seshan",
"prompt": "Does this website talk about Seshan's career?",
"expected_output": "yes"
},
{
"website": "https://mendable.ai/blog",
"prompt": "Does this website contain multiple blog articles?",
"expected_output": "yes"
},
{
"website": "https://www.framer.com/pricing",
"prompt": "Is there an enterprise pricing option?",
"expected_output": "yes"
},
{
"website": "https://fly.io/docs/gpus/gpu-quickstart",
"prompt": "Is there a fly deploy command on this page?",
"expected_output": "yes"
},
{
"website": "https://news.ycombinator.com/",
"prompt": "Does this website contain a list of articles in a table markdown format?",
"expected_output": "yes"
},
{
"website": "https://www.vellum.ai/llm-leaderboard",
"prompt": "Does this website contain a model comparison table?",
"expected_output": "yes"
},
{
"website": "https://www.bigbadtoystore.com",
"prompt": "are there more than 3 toys in the new arrivals section?",
"expected_output": "yes"
},
{
"website": "https://www.instructables.com",
"prompt": "Does the site offer more than 5 links about circuits?",
"expected_output": "yes"
},
{
"website": "https://www.powells.com",
"prompt": "is there at least 10 books webpage links?",
"expected_output": "yes"
},
{
"website": "https://www.royalacademy.org.uk",
"prompt": "is there information on upcoming art exhibitions?",
"expected_output": "yes"
},
{
"website": "https://www.eastbaytimes.com",
"prompt": "Is there a Trending Nationally section that lists articles?",
"expected_output": "yes"
},
{
"website": "https://www.manchestereveningnews.co.uk",
"prompt": "is the content focused on Manchester sports news?",
"expected_output": "no"
},
{
"website": "https://physicsworld.com",
"prompt": "does the site provide at least 15 updates on the latest physics research?",
"expected_output": "yes"
},
{
"website": "https://richmondconfidential.org",
"prompt": "does the page contains more than 4 articles?",
"expected_output": "yes"
},
{
"website": "https://www.techinasia.com",
"prompt": "is there at least 10 articles of the startup scene in Asia?",
"expected_output": "yes",
"notes": "The website has a paywall and bot detectors."
},
{
"website": "https://www.boardgamegeek.com",
"prompt": "are there more than 5 board game news?",
"expected_output": "yes"
},
{
"website": "https://www.mountainproject.com",
"prompt": "Are there more than 3 climbing guides for Arizona?",
"expected_output": "yes"
}
]

5
apps/test-suite/jest.config.js Normal file
View File

@ -0,0 +1,5 @@
module.exports = {
preset: "ts-jest",
testEnvironment: "node",
setupFiles: ["./jest.setup.js"],
};

0
apps/test-suite/jest.setup.js Normal file
View File

28
apps/test-suite/package.json Normal file
View File

@ -0,0 +1,28 @@
{
"name": "test-suite",
"version": "1.0.0",
"description": "",
"scripts": {
"test": "npx jest --detectOpenHandles --forceExit --openHandlesTimeout=120000 --watchAll=false",
"test:scrape": "npx jest --detectOpenHandles --forceExit --openHandlesTimeout=120000 --watchAll=false --testPathPattern=tests/scrape.test.ts",
"test:crawl": "npx jest --detectOpenHandles --forceExit --openHandlesTimeout=120000 --watchAll=false --testPathPattern=tests/crawl.test.ts"
},
"author": "",
"license": "ISC",
"dependencies": {
"@anthropic-ai/sdk": "^0.20.8",
"@dqbd/tiktoken": "^1.0.14",
"@supabase/supabase-js": "^2.43.1",
"dotenv": "^16.4.5",
"jest": "^29.7.0",
"openai": "^4.40.2",
"playwright": "^1.43.1",
"supertest": "^7.0.0",
"ts-jest": "^29.1.2"
},
"devDependencies": {
"@types/jest": "^29.5.12",
"@types/supertest": "^6.0.2",
"typescript": "^5.4.5"
}
}

2746
apps/test-suite/pnpm-lock.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

150
apps/test-suite/tests/crawl.test.ts Normal file
View File

@ -0,0 +1,150 @@
import request from "supertest";
import dotenv from "dotenv";
import { WebsiteScrapeError } from "../utils/types";
import { logErrors } from "../utils/log";
import websitesData from "../data/crawl.json";
import "dotenv/config";
import fs from 'fs';
dotenv.config();
interface WebsiteData {
website: string;
expected_min_num_of_pages: number;
expected_crawled_pages: string[];
}
const TEST_URL = "http://127.0.0.1:3002";
describe("Crawling Checkup (E2E)", () => {
beforeAll(() => {
if (!process.env.TEST_API_KEY) {
throw new Error("TEST_API_KEY is not set");
}
});
describe("Crawling website tests with a dataset", () => {
it("Should crawl the website and verify the response", async () => {
let passedTests = 0;
const startTime = new Date().getTime();
const date = new Date();
const logsDir = `logs/${date.getMonth() + 1}-${date.getDate()}-${date.getFullYear()}`;
let errorLogFileName = `${logsDir}/run.log_${new Date().toTimeString().split(' ')[0]}`;
const errorLog: WebsiteScrapeError[] = [];
for (const websiteData of websitesData) {
try {
const crawlResponse = await request(TEST_URL || "")
.post("/v0/crawl")
.set("Content-Type", "application/json")
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
.send({ url: websiteData.website, pageOptions: { onlyMainContent: true }, crawlerOptions: { limit: 100, returnOnlyUrls: true }});
const jobId = crawlResponse.body.jobId;
let completedResponse: any;
let isFinished = false;
while (!isFinished) {
completedResponse = await request(TEST_URL)
.get(`/v0/crawl/status/${jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
isFinished = completedResponse.body.status === "completed";
if (!isFinished) {
await new Promise(resolve => setTimeout(resolve, 1000)); // Wait for 1 second before checking again
}
}
if(!completedResponse) {
// fail the test
console.log('No response');
continue;
// continue;
}
if (!completedResponse.body || completedResponse.body.status !== "completed") {
errorLog.push({
website: websiteData.website,
prompt: 'CRAWL',
expected_output: 'SUCCESS',
actual_output: 'FAILURE',
error: `Crawl job did not complete successfully.`
});
continue;
}
// check how many webpages were crawled successfully
// compares with expected_num_of_pages
if (completedResponse.body.data.length < websiteData.expected_min_num_of_pages) {
errorLog.push({
website: websiteData.website,
prompt: 'CRAWL',
expected_output: `SUCCESS: ${websiteData.expected_min_num_of_pages}`,
actual_output: `FAILURE: ${completedResponse.body.data.length}`,
error: `Expected at least ${websiteData.expected_min_num_of_pages} webpages, but got ${completedResponse.body.data.length}`
});
console.log('Error: ', errorLog);
continue;
}
// checks if crawled pages contain expected_crawled_pages
if (websiteData.expected_crawled_pages && websiteData.expected_crawled_pages.length > 0 && websiteData.expected_crawled_pages.some(page => !completedResponse.body.data?.some((d: { url: string }) => d.url === page))) {
errorLog.push({
website: websiteData.website,
prompt: 'CRAWL',
expected_output: `SUCCESS: ${websiteData.expected_crawled_pages}`,
actual_output: `FAILURE: ${completedResponse.body.data}`,
error: `Expected crawled pages to contain ${websiteData.expected_crawled_pages}, but got ${completedResponse.body.data}`
});
console.log('Error: ', errorLog);
continue;
}
// checks if crawled pages not contain expected_not_crawled_pages
if (websiteData.expected_not_crawled_pages && websiteData.expected_not_crawled_pages.length > 0 && completedResponse.body.data && websiteData.expected_not_crawled_pages.filter(page => completedResponse.body.data.some((d: { url: string }) => d.url === page)).length > 0) {
errorLog.push({
website: websiteData.website,
prompt: 'CRAWL',
expected_output: `SUCCESS: ${websiteData.expected_not_crawled_pages}`,
actual_output: `FAILURE: ${completedResponse.body.data}`,
error: `Expected crawled pages to not contain ${websiteData.expected_not_crawled_pages}, but got ${completedResponse.body.data}`
});
console.log('Error: ', errorLog);
continue;
}
passedTests++;
} catch (error) {
console.error(`Error processing ${websiteData.website}: ${error}`);
errorLog.push({
website: websiteData.website,
prompt: 'CRAWL',
expected_output: 'SUCCESS',
actual_output: 'FAILURE',
error: `Error processing ${websiteData.website}: ${error}`
});
continue;
}
}
const score = (passedTests / websitesData.length) * 100;
const endTime = new Date().getTime();
const timeTaken = (endTime - startTime) / 1000;
console.log(`Score: ${score}%`);
await logErrors(errorLog, timeTaken, 0, score, websitesData.length);
if (process.env.ENV === "local" && errorLog.length > 0) {
if (!fs.existsSync(logsDir)){
fs.mkdirSync(logsDir, { recursive: true });
}
fs.writeFileSync(errorLogFileName, JSON.stringify(errorLog, null, 2));
}
expect(score).toBeGreaterThanOrEqual(90);
}, 350000); // 150 seconds timeout
});
});

182
apps/test-suite/tests/scrape.test.ts Normal file
View File

@ -0,0 +1,182 @@
import request from "supertest";
import dotenv from "dotenv";
import { numTokensFromString } from "../utils/tokens";
import OpenAI from "openai";
import { WebsiteScrapeError } from "../utils/types";
import { logErrors } from "../utils/log";
import websitesData from "../data/scrape.json";
import "dotenv/config";
import fs from 'fs';
dotenv.config();
interface WebsiteData {
website: string;
prompt: string;
expected_output: string;
}
const TEST_URL = "http://127.0.0.1:3002";
describe("Scraping Checkup (E2E)", () => {
beforeAll(() => {
if (!process.env.TEST_API_KEY) {
throw new Error("TEST_API_KEY is not set");
}
if (!process.env.OPENAI_API_KEY) {
throw new Error("OPENAI_API_KEY is not set");
}
});
describe("Scraping website tests with a dataset", () => {
it("Should scrape the website and prompt it against OpenAI", async () => {
let passedTests = 0;
const batchSize = 15; // Adjusted to comply with the rate limit of 15 per minute
const batchPromises = [];
let totalTokens = 0;
const startTime = new Date().getTime();
const date = new Date();
const logsDir = `logs/${date.getMonth() + 1}-${date.getDate()}-${date.getFullYear()}`;
let errorLogFileName = `${logsDir}/run.log_${new Date().toTimeString().split(' ')[0]}`;
const errorLog: WebsiteScrapeError[] = [];
for (let i = 0; i < websitesData.length; i += batchSize) {
// Introducing delay to respect the rate limit of 15 requests per minute
await new Promise(resolve => setTimeout(resolve, 10000));
const batch = websitesData.slice(i, i + batchSize);
const batchPromise = Promise.all(
batch.map(async (websiteData: WebsiteData) => {
try {
const scrapedContent = await request(TEST_URL || "")
.post("/v0/scrape")
.set("Content-Type", "application/json")
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
.send({ url: websiteData.website, pageOptions: { onlyMainContent: true } });
if (scrapedContent.statusCode !== 200) {
console.error(`Failed to scrape ${websiteData.website} ${scrapedContent.statusCode}`);
errorLog.push({
website: websiteData.website,
prompt: websiteData.prompt,
expected_output: websiteData.expected_output,
actual_output: "",
error: `Failed to scrape website. ${scrapedContent.statusCode} ${scrapedContent.body.error}`
});
return null;
}
const openai = new OpenAI({
apiKey: process.env.OPENAI_API_KEY,
});
const prompt = `Based on this markdown extracted from a website html page, ${websiteData.prompt} Just say 'yes' or 'no' to the question.\nWebsite markdown: ${scrapedContent.body.data.markdown}\n`;
let msg = null;
const maxRetries = 3;
let attempts = 0;
while (!msg && attempts < maxRetries) {
try {
msg = await openai.chat.completions.create({
model: "gpt-4-turbo",
max_tokens: 100,
temperature: 0,
messages: [
{
role: "user",
content: prompt
},
],
});
} catch (error) {
console.error(`Attempt ${attempts + 1}: Failed to prompt for ${websiteData.website}, error: ${error}`);
attempts++;
if (attempts < maxRetries) {
console.log(`Retrying... Attempt ${attempts + 1}`);
await new Promise(resolve => setTimeout(resolve, 2000)); // Wait for 2 seconds before retrying
}
}
}
if (!msg) {
console.error(`Failed to prompt for ${websiteData.website} after ${maxRetries} attempts`);
errorLog.push({
website: websiteData.website,
prompt: websiteData.prompt,
expected_output: websiteData.expected_output,
actual_output: "",
error: "Failed to prompt... model error."
});
return null;
}
const actualOutput = (msg.choices[0].message.content ?? "").toLowerCase()
const expectedOutput = websiteData.expected_output.toLowerCase();
const numTokens = numTokensFromString(prompt,"gpt-4") + numTokensFromString(actualOutput,"gpt-4");
totalTokens += numTokens;
if (actualOutput.includes(expectedOutput)) {
passedTests++;
} else {
console.error(
`This website failed the test: ${websiteData.website}`
);
console.error(`Actual output: ${actualOutput}`);
errorLog.push({
website: websiteData.website,
prompt: websiteData.prompt,
expected_output: websiteData.expected_output,
actual_output: actualOutput,
error: "Output mismatch"
});
}
return {
website: websiteData.website,
prompt: websiteData.prompt,
expectedOutput,
actualOutput,
};
} catch (error) {
console.error(
`Error processing ${websiteData.website}: ${error}`
);
errorLog.push({
website: websiteData.website,
prompt: websiteData.prompt,
expected_output: websiteData.expected_output,
actual_output: "",
error: `Error processing ${websiteData.website}: ${error}`
});
return null;
}
})
);
batchPromises.push(batchPromise);
}
(await Promise.all(batchPromises)).flat();
const score = (passedTests / websitesData.length) * 100;
const endTime = new Date().getTime();
const timeTaken = (endTime - startTime) / 1000;
console.log(`Score: ${score}%`);
console.log(`Total tokens: ${totalTokens}`);
await logErrors(errorLog, timeTaken, totalTokens, score, websitesData.length);
if (process.env.ENV === "local" && errorLog.length > 0) {
if (!fs.existsSync(logsDir)){
fs.mkdirSync(logsDir, { recursive: true });
}
fs.writeFileSync(errorLogFileName, JSON.stringify(errorLog, null, 2));
}
expect(score).toBeGreaterThanOrEqual(70);
}, 350000); // 150 seconds timeout
});
});

109
apps/test-suite/tsconfig.json Normal file
View File

@ -0,0 +1,109 @@
{
"compilerOptions": {
/* Visit https://aka.ms/tsconfig to read more about this file */
/* Projects */
// "incremental": true, /* Save .tsbuildinfo files to allow for incremental compilation of projects. */
// "composite": true, /* Enable constraints that allow a TypeScript project to be used with project references. */
// "tsBuildInfoFile": "./.tsbuildinfo", /* Specify the path to .tsbuildinfo incremental compilation file. */
// "disableSourceOfProjectReferenceRedirect": true, /* Disable preferring source files instead of declaration files when referencing composite projects. */
// "disableSolutionSearching": true, /* Opt a project out of multi-project reference checking when editing. */
// "disableReferencedProjectLoad": true, /* Reduce the number of projects loaded automatically by TypeScript. */
/* Language and Environment */
"target": "es2016", /* Set the JavaScript language version for emitted JavaScript and include compatible library declarations. */
// "lib": [], /* Specify a set of bundled library declaration files that describe the target runtime environment. */
// "jsx": "preserve", /* Specify what JSX code is generated. */
// "experimentalDecorators": true, /* Enable experimental support for legacy experimental decorators. */
// "emitDecoratorMetadata": true, /* Emit design-type metadata for decorated declarations in source files. */
// "jsxFactory": "", /* Specify the JSX factory function used when targeting React JSX emit, e.g. 'React.createElement' or 'h'. */
// "jsxFragmentFactory": "", /* Specify the JSX Fragment reference used for fragments when targeting React JSX emit e.g. 'React.Fragment' or 'Fragment'. */
// "jsxImportSource": "", /* Specify module specifier used to import the JSX factory functions when using 'jsx: react-jsx*'. */
// "reactNamespace": "", /* Specify the object invoked for 'createElement'. This only applies when targeting 'react' JSX emit. */
// "noLib": true, /* Disable including any library files, including the default lib.d.ts. */
// "useDefineForClassFields": true, /* Emit ECMAScript-standard-compliant class fields. */
// "moduleDetection": "auto", /* Control what method is used to detect module-format JS files. */
/* Modules */
"module": "commonjs", /* Specify what module code is generated. */
// "rootDir": "./", /* Specify the root folder within your source files. */
// "moduleResolution": "node10", /* Specify how TypeScript looks up a file from a given module specifier. */
// "baseUrl": "./", /* Specify the base directory to resolve non-relative module names. */
// "paths": {}, /* Specify a set of entries that re-map imports to additional lookup locations. */
// "rootDirs": [], /* Allow multiple folders to be treated as one when resolving modules. */
// "typeRoots": [], /* Specify multiple folders that act like './node_modules/@types'. */
// "types": [], /* Specify type package names to be included without being referenced in a source file. */
// "allowUmdGlobalAccess": true, /* Allow accessing UMD globals from modules. */
// "moduleSuffixes": [], /* List of file name suffixes to search when resolving a module. */
// "allowImportingTsExtensions": true, /* Allow imports to include TypeScript file extensions. Requires '--moduleResolution bundler' and either '--noEmit' or '--emitDeclarationOnly' to be set. */
// "resolvePackageJsonExports": true, /* Use the package.json 'exports' field when resolving package imports. */
// "resolvePackageJsonImports": true, /* Use the package.json 'imports' field when resolving imports. */
// "customConditions": [], /* Conditions to set in addition to the resolver-specific defaults when resolving imports. */
"resolveJsonModule": true, /* Enable importing .json files. */
// "allowArbitraryExtensions": true, /* Enable importing files with any extension, provided a declaration file is present. */
// "noResolve": true, /* Disallow 'import's, 'require's or '<reference>'s from expanding the number of files TypeScript should add to a project. */
/* JavaScript Support */
// "allowJs": true, /* Allow JavaScript files to be a part of your program. Use the 'checkJS' option to get errors from these files. */
// "checkJs": true, /* Enable error reporting in type-checked JavaScript files. */
// "maxNodeModuleJsDepth": 1, /* Specify the maximum folder depth used for checking JavaScript files from 'node_modules'. Only applicable with 'allowJs'. */
/* Emit */
// "declaration": true, /* Generate .d.ts files from TypeScript and JavaScript files in your project. */
// "declarationMap": true, /* Create sourcemaps for d.ts files. */
// "emitDeclarationOnly": true, /* Only output d.ts files and not JavaScript files. */
// "sourceMap": true, /* Create source map files for emitted JavaScript files. */
// "inlineSourceMap": true, /* Include sourcemap files inside the emitted JavaScript. */
// "outFile": "./", /* Specify a file that bundles all outputs into one JavaScript file. If 'declaration' is true, also designates a file that bundles all .d.ts output. */
// "outDir": "./", /* Specify an output folder for all emitted files. */
// "removeComments": true, /* Disable emitting comments. */
// "noEmit": true, /* Disable emitting files from a compilation. */
// "importHelpers": true, /* Allow importing helper functions from tslib once per project, instead of including them per-file. */
// "importsNotUsedAsValues": "remove", /* Specify emit/checking behavior for imports that are only used for types. */
// "downlevelIteration": true, /* Emit more compliant, but verbose and less performant JavaScript for iteration. */
// "sourceRoot": "", /* Specify the root path for debuggers to find the reference source code. */
// "mapRoot": "", /* Specify the location where debugger should locate map files instead of generated locations. */
// "inlineSources": true, /* Include source code in the sourcemaps inside the emitted JavaScript. */
// "emitBOM": true, /* Emit a UTF-8 Byte Order Mark (BOM) in the beginning of output files. */
// "newLine": "crlf", /* Set the newline character for emitting files. */
// "stripInternal": true, /* Disable emitting declarations that have '@internal' in their JSDoc comments. */
// "noEmitHelpers": true, /* Disable generating custom helper functions like '__extends' in compiled output. */
// "noEmitOnError": true, /* Disable emitting files if any type checking errors are reported. */
// "preserveConstEnums": true, /* Disable erasing 'const enum' declarations in generated code. */
// "declarationDir": "./", /* Specify the output directory for generated declaration files. */
// "preserveValueImports": true, /* Preserve unused imported values in the JavaScript output that would otherwise be removed. */
/* Interop Constraints */
// "isolatedModules": true, /* Ensure that each file can be safely transpiled without relying on other imports. */
// "verbatimModuleSyntax": true, /* Do not transform or elide any imports or exports not marked as type-only, ensuring they are written in the output file's format based on the 'module' setting. */
// "allowSyntheticDefaultImports": true, /* Allow 'import x from y' when a module doesn't have a default export. */
"esModuleInterop": true, /* Emit additional JavaScript to ease support for importing CommonJS modules. This enables 'allowSyntheticDefaultImports' for type compatibility. */
// "preserveSymlinks": true, /* Disable resolving symlinks to their realpath. This correlates to the same flag in node. */
"forceConsistentCasingInFileNames": true, /* Ensure that casing is correct in imports. */
/* Type Checking */
"strict": true, /* Enable all strict type-checking options. */
// "noImplicitAny": true, /* Enable error reporting for expressions and declarations with an implied 'any' type. */
// "strictNullChecks": true, /* When type checking, take into account 'null' and 'undefined'. */
// "strictFunctionTypes": true, /* When assigning functions, check to ensure parameters and the return values are subtype-compatible. */
// "strictBindCallApply": true, /* Check that the arguments for 'bind', 'call', and 'apply' methods match the original function. */
// "strictPropertyInitialization": true, /* Check for class properties that are declared but not set in the constructor. */
// "noImplicitThis": true, /* Enable error reporting when 'this' is given the type 'any'. */
// "useUnknownInCatchVariables": true, /* Default catch clause variables as 'unknown' instead of 'any'. */
// "alwaysStrict": true, /* Ensure 'use strict' is always emitted. */
// "noUnusedLocals": true, /* Enable error reporting when local variables aren't read. */
// "noUnusedParameters": true, /* Raise an error when a function parameter isn't read. */
// "exactOptionalPropertyTypes": true, /* Interpret optional property types as written, rather than adding 'undefined'. */
// "noImplicitReturns": true, /* Enable error reporting for codepaths that do not explicitly return in a function. */
// "noFallthroughCasesInSwitch": true, /* Enable error reporting for fallthrough cases in switch statements. */
// "noUncheckedIndexedAccess": true, /* Add 'undefined' to a type when accessed using an index. */
// "noImplicitOverride": true, /* Ensure overriding members in derived classes are marked with an override modifier. */
// "noPropertyAccessFromIndexSignature": true, /* Enforces using indexed accessors for keys declared using an indexed type. */
// "allowUnusedLabels": true, /* Disable error reporting for unused labels. */
// "allowUnreachableCode": true, /* Disable error reporting for unreachable code. */
/* Completeness */
// "skipDefaultLibCheck": true, /* Skip type checking .d.ts files that are included with TypeScript. */
"skipLibCheck": true /* Skip type checking all .d.ts files. */
}
}

10
apps/test-suite/utils/log.ts Normal file
View File

@ -0,0 +1,10 @@
import { supabase_service } from "./supabase";
import { WebsiteScrapeError } from "./types";
export async function logErrors(dataError: WebsiteScrapeError[], time_taken: number, num_tokens:number, score: number, num_pages_tested: number,) {
try {
await supabase_service.from("test_suite_logs").insert([{log:dataError, time_taken, num_tokens, score, num_pages_tested, is_error: dataError.length > 0}]);
} catch (error) {
console.error(`Error logging to supabase: ${error}`);
}
}

47
apps/test-suite/utils/misc.ts Normal file
View File

@ -0,0 +1,47 @@
const getRandomLinksFromContent = async (options: {
content: string;
excludes: string[];
limit: number;
}): Promise<string[]> => {
const regex = /(?<=\()https:\/\/(.*?)(?=\))/g;
const links = options.content.match(regex);
const filteredLinks = links
? links.filter(
(link) => !options.excludes.some((exclude) => link.includes(exclude))
)
: [];
const uniqueLinks = [...new Set(filteredLinks)]; // Ensure all links are unique
const randomLinks = [];
while (randomLinks.length < options.limit && uniqueLinks.length > 0) {
const randomIndex = Math.floor(Math.random() * uniqueLinks.length);
randomLinks.push(uniqueLinks.splice(randomIndex, 1)[0]);
}
return randomLinks;
};
function fuzzyContains(options: {
largeText: string;
queryText: string;
threshold?: number;
}): boolean {
// Normalize texts: lowercasing and removing non-alphanumeric characters
const normalize = (text: string) =>
text.toLowerCase().replace(/[^a-z0-9]+/g, " ");
const normalizedLargeText = normalize(options.largeText);
const normalizedQueryText = normalize(options.queryText);
// Split the query into words
const queryWords = normalizedQueryText.split(/\s+/);
// Count how many query words are in the large text
const matchCount = queryWords.reduce((count, word) => {
return count + (normalizedLargeText.includes(word) ? 1 : 0);
}, 0);
// Calculate the percentage of words matched
const matchPercentage = matchCount / queryWords.length;
// Check if the match percentage meets or exceeds the threshold
return matchPercentage >= (options.threshold || 0.8);
}

56
apps/test-suite/utils/supabase.ts Normal file
View File

@ -0,0 +1,56 @@
import { createClient, SupabaseClient } from "@supabase/supabase-js";
import "dotenv/config";
// SupabaseService class initializes the Supabase client conditionally based on environment variables.
class SupabaseService {
private client: SupabaseClient | null = null;
constructor() {
const supabaseUrl = process.env.SUPABASE_URL;
const supabaseServiceToken = process.env.SUPABASE_SERVICE_TOKEN;
// Only initialize the Supabase client if both URL and Service Token are provided.
if (process.env.USE_DB_AUTHENTICATION === "false") {
// Warn the user that Authentication is disabled by setting the client to null
console.warn(
"\x1b[33mAuthentication is disabled. Supabase client will not be initialized.\x1b[0m"
);
this.client = null;
} else if (!supabaseUrl || !supabaseServiceToken) {
console.error(
"\x1b[31mSupabase environment variables aren't configured correctly. Supabase client will not be initialized. Fix ENV configuration or disable DB authentication with USE_DB_AUTHENTICATION env variable\x1b[0m"
);
} else {
this.client = createClient(supabaseUrl, supabaseServiceToken);
}
}
// Provides access to the initialized Supabase client, if available.
getClient(): SupabaseClient | null {
return this.client;
}
}
// Using a Proxy to handle dynamic access to the Supabase client or service methods.
// This approach ensures that if Supabase is not configured, any attempt to use it will result in a clear error.
export const supabase_service: SupabaseClient = new Proxy(
new SupabaseService(),
{
get: function (target, prop, receiver) {
const client = target.getClient();
// If the Supabase client is not initialized, intercept property access to provide meaningful error feedback.
if (client === null) {
console.error(
"Attempted to access Supabase client when it's not configured."
);
return () => {
throw new Error("Supabase client is not configured.");
};
}
// Direct access to SupabaseService properties takes precedence.
if (prop in target) {
return Reflect.get(target, prop, receiver);
}
// Otherwise, delegate access to the Supabase client.
return Reflect.get(client, prop, receiver);
},
}
) as unknown as SupabaseClient;

16
apps/test-suite/utils/tokens.ts Normal file
View File

@ -0,0 +1,16 @@
import { encoding_for_model } from "@dqbd/tiktoken";
import { TiktokenModel } from "@dqbd/tiktoken";
// This function calculates the number of tokens in a text string using GPT-3.5-turbo model
export function numTokensFromString(message: string, model: string): number {
const encoder = encoding_for_model(model as TiktokenModel);
// Encode the message into tokens
const tokens = encoder.encode(message);
// Free the encoder resources after use
encoder.free();
// Return the number of tokens
return tokens.length;
}

7
apps/test-suite/utils/types.ts Normal file
View File

@ -0,0 +1,7 @@
export interface WebsiteScrapeError {
website: string;
prompt: string;
expected_output: string;
actual_output: string;
error: string;
}

78
docker-compose.yaml Normal file
View File

@ -0,0 +1,78 @@
name: firecrawl
version: '3.9'
services:
playwright-service:
build: apps/playwright-service
environment:
- PORT=3000
networks:
- backend
api:
build: apps/api
environment:
- REDIS_URL=${REDIS_URL:-redis://redis:6379}
- PLAYWRIGHT_MICROSERVICE_URL=${PLAYWRIGHT_MICROSERVICE_URL:-http://playwright-service:3000}
- USE_DB_AUTHENTICATION=${USE_DB_AUTHENTICATION}
- PORT=${PORT:-3002}
- NUM_WORKERS_PER_QUEUE=${NUM_WORKERS_PER_QUEUE}
- OPENAI_API_KEY=${OPENAI_API_KEY}
- SLACK_WEBHOOK_URL=${SLACK_WEBHOOK_URL}
- SERPER_API_KEY=${SERPER_API_KEY}
- LLAMAPARSE_API_KEY=${LLAMAPARSE_API_KEY}
- LOGTAIL_KEY=${LOGTAIL_KEY}
- BULL_AUTH_KEY=${BULL_AUTH_KEY}
- TEST_API_KEY=${TEST_API_KEY}
- POSTHOG_API_KEY=${POSTHOG_API_KEY}
- POSTHOG_HOST=${POSTHOG_HOST}
- SUPABASE_ANON_TOKEN=${SUPABASE_ANON_TOKEN}
- SUPABASE_URL=${SUPABASE_URL}
- SUPABASE_SERVICE_TOKEN=${SUPABASE_SERVICE_TOKEN}
- SCRAPING_BEE_API_KEY=${SCRAPING_BEE_API_KEY}
- HOST=${HOST:-0.0.0.0}
depends_on:
- redis
- playwright-service
ports:
- "3002:3002"
command: [ "pnpm", "run", "start:production" ]
networks:
- backend
worker:
build: apps/api
environment:
- REDIS_URL=${REDIS_URL:-redis://redis:6379}
- PLAYWRIGHT_MICROSERVICE_URL=${PLAYWRIGHT_MICROSERVICE_URL:-http://playwright-service:3000}
- USE_DB_AUTHENTICATION=${USE_DB_AUTHENTICATION}
- PORT=${PORT:-3002}
- NUM_WORKERS_PER_QUEUE=${NUM_WORKERS_PER_QUEUE}
- OPENAI_API_KEY=${OPENAI_API_KEY}
- SLACK_WEBHOOK_URL=${SLACK_WEBHOOK_URL}
- SERPER_API_KEY=${SERPER_API_KEY}
- LLAMAPARSE_API_KEY=${LLAMAPARSE_API_KEY}
- LOGTAIL_KEY=${LOGTAIL_KEY}
- BULL_AUTH_KEY=${BULL_AUTH_KEY}
- TEST_API_KEY=${TEST_API_KEY}
- POSTHOG_API_KEY=${POSTHOG_API_KEY}
- POSTHOG_HOST=${POSTHOG_HOST}
- SUPABASE_ANON_TOKEN=${SUPABASE_ANON_TOKEN}
- SUPABASE_URL=${SUPABASE_URL}
- SUPABASE_SERVICE_TOKEN=${SUPABASE_SERVICE_TOKEN}
- SCRAPING_BEE_API_KEY=${SCRAPING_BEE_API_KEY}
- HOST=${HOST:-0.0.0.0}
depends_on:
- redis
- playwright-service
- api
networks:
- backend
redis:
image: redis:alpine
networks:
- backend
command: redis-server --bind 0.0.0.0
networks:
backend:
driver: bridge