From 00373228fa1147e96e718c312d39c825be98e13c Mon Sep 17 00:00:00 2001
From: Nicolas <nicolascamara29@gmail.com>
Date: Sat, 4 May 2024 11:53:16 -0700
Subject: [PATCH 01/17] Update index.ts

---
 apps/api/src/scraper/WebScraper/index.ts | 315 +++++++++--------------
 1 file changed, 121 insertions(+), 194 deletions(-)

diff --git a/apps/api/src/scraper/WebScraper/index.ts b/apps/api/src/scraper/WebScraper/index.ts
index fef5f69..ebd96d0 100644
--- a/apps/api/src/scraper/WebScraper/index.ts
+++ b/apps/api/src/scraper/WebScraper/index.ts
@@ -67,211 +67,138 @@ export class WebScraperDataProvider {
     useCaching: boolean = false,
     inProgress?: (progress: Progress) => void
   ): Promise<Document[]> {
-    
+    this.validateInitialUrl();
+
+    if (!useCaching) {
+      return this.processDocumentsWithoutCache(inProgress);
+    }
+
+    return this.processDocumentsWithCache(inProgress);
+  }
+
+  private validateInitialUrl(): void {
     if (this.urls[0].trim() === "") {
       throw new Error("Url is required");
     }
+  }
 
-    if (!useCaching) {
-      if (this.mode === "crawl") {
-        const crawler = new WebCrawler({
-          initialUrl: this.urls[0],
-          includes: this.includes,
-          excludes: this.excludes,
-          maxCrawledLinks: this.maxCrawledLinks,
-          limit: this.limit,
-          generateImgAltText: this.generateImgAltText,
-        });
-        let links = await crawler.start(inProgress, 5, this.limit);
-        if (this.returnOnlyUrls) {
-          inProgress({
-            current: links.length,
-            total: links.length,
-            status: "COMPLETED",
-            currentDocumentUrl: this.urls[0],
-          });
-          return links.map((url) => ({
-            content: "",
-            markdown: "",
-            metadata: { sourceURL: url },
-          }));
-        }
+  private async processDocumentsWithoutCache(inProgress?: (progress: Progress) => void): Promise<Document[]> {
+    switch (this.mode) {
+      case "crawl":
+        return this.handleCrawlMode(inProgress);
+      case "single_urls":
+        return this.handleSingleUrlsMode(inProgress);
+      case "sitemap":
+        return this.handleSitemapMode(inProgress);
+      default:
+        return [];
+    }
+  }
 
-        let pdfLinks = links.filter((link) => link.endsWith(".pdf"));
-        let pdfDocuments: Document[] = [];
-        for (let pdfLink of pdfLinks) {
-          const pdfContent = await fetchAndProcessPdf(pdfLink);
-          pdfDocuments.push({
-            content: pdfContent,
-            metadata: { sourceURL: pdfLink },
-            provider: "web-scraper"
-          });
-        }
-        links = links.filter((link) => !link.endsWith(".pdf"));
-
-        let documents = await this.convertUrlsToDocuments(links, inProgress);
-        documents = await this.getSitemapData(this.urls[0], documents);
-
-        if (this.replaceAllPathsWithAbsolutePaths) {
-          documents = replacePathsWithAbsolutePaths(documents);
-        } else {
-          documents = replaceImgPathsWithAbsolutePaths(documents);
-        }
-
-        if (this.generateImgAltText) {
-          documents = await this.generatesImgAltText(documents);
-        }
-        documents = documents.concat(pdfDocuments);
-
-        // CACHING DOCUMENTS
-        // - parent document
-        const cachedParentDocumentString = await getValue(
-          "web-scraper-cache:" + this.normalizeUrl(this.urls[0])
-        );
-        if (cachedParentDocumentString != null) {
-          let cachedParentDocument = JSON.parse(cachedParentDocumentString);
-          if (
-            !cachedParentDocument.childrenLinks ||
-            cachedParentDocument.childrenLinks.length < links.length - 1
-          ) {
-            cachedParentDocument.childrenLinks = links.filter(
-              (link) => link !== this.urls[0]
-            );
-            await setValue(
-              "web-scraper-cache:" + this.normalizeUrl(this.urls[0]),
-              JSON.stringify(cachedParentDocument),
-              60 * 60 * 24 * 10
-            ); // 10 days
-          }
-        } else {
-          let parentDocument = documents.filter(
-            (document) =>
-              this.normalizeUrl(document.metadata.sourceURL) ===
-              this.normalizeUrl(this.urls[0])
-          );
-          await this.setCachedDocuments(parentDocument, links);
-        }
-
-        await this.setCachedDocuments(
-          documents.filter(
-            (document) =>
-              this.normalizeUrl(document.metadata.sourceURL) !==
-              this.normalizeUrl(this.urls[0])
-          ),
-          []
-        );
-        documents = this.removeChildLinks(documents);
-        documents = documents.splice(0, this.limit);
-        return documents;
-      }
-
-      if (this.mode === "single_urls") {
-        let pdfLinks = this.urls.filter((link) => link.endsWith(".pdf"));
-        let pdfDocuments: Document[] = [];
-        for (let pdfLink of pdfLinks) {
-          const pdfContent = await fetchAndProcessPdf(pdfLink);
-          pdfDocuments.push({
-            content: pdfContent,
-            metadata: { sourceURL: pdfLink },
-            provider: "web-scraper"
-          });
-        }
-
-        let documents = await this.convertUrlsToDocuments(
-          this.urls.filter((link) => !link.endsWith(".pdf")),
-          inProgress
-        );
-
-        if (this.replaceAllPathsWithAbsolutePaths) {
-          documents = replacePathsWithAbsolutePaths(documents);
-        } else {
-          documents = replaceImgPathsWithAbsolutePaths(documents);
-        }
-
-        if (this.generateImgAltText) {
-          documents = await this.generatesImgAltText(documents);
-        }
-        const baseUrl = new URL(this.urls[0]).origin;
-        documents = await this.getSitemapData(baseUrl, documents);
-        documents = documents.concat(pdfDocuments);
-
-        if(this.extractorOptions.mode === "llm-extraction") {
-          documents = await generateCompletions(
-            documents,
-            this.extractorOptions
-          )
-        }
-
-        await this.setCachedDocuments(documents);
-        documents = this.removeChildLinks(documents);
-        documents = documents.splice(0, this.limit);
-        return documents;
-      }
-      if (this.mode === "sitemap") {
-        let links = await getLinksFromSitemap(this.urls[0]);
-        let pdfLinks = links.filter((link) => link.endsWith(".pdf"));
-        let pdfDocuments: Document[] = [];
-        for (let pdfLink of pdfLinks) {
-          const pdfContent = await fetchAndProcessPdf(pdfLink);
-          pdfDocuments.push({
-            content: pdfContent,
-            metadata: { sourceURL: pdfLink },
-            provider: "web-scraper"
-          });
-        }
-        links = links.filter((link) => !link.endsWith(".pdf"));
-
-        let documents = await this.convertUrlsToDocuments(
-          links.slice(0, this.limit),
-          inProgress
-        );
-
-        documents = await this.getSitemapData(this.urls[0], documents);
-
-        if (this.replaceAllPathsWithAbsolutePaths) {
-          documents = replacePathsWithAbsolutePaths(documents);
-        } else {
-          documents = replaceImgPathsWithAbsolutePaths(documents);
-        }
-
-        if (this.generateImgAltText) {
-          documents = await this.generatesImgAltText(documents);
-        }
-        documents = documents.concat(pdfDocuments);
-
-        await this.setCachedDocuments(documents);
-        documents = this.removeChildLinks(documents);
-        documents = documents.splice(0, this.limit);
-        return documents;
-      }
-
-      return [];
+  private async handleCrawlMode(inProgress?: (progress: Progress) => void): Promise<Document[]> {
+    const crawler = new WebCrawler({
+      initialUrl: this.urls[0],
+      includes: this.includes,
+      excludes: this.excludes,
+      maxCrawledLinks: this.maxCrawledLinks,
+      limit: this.limit,
+      generateImgAltText: this.generateImgAltText,
+    });
+    let links = await crawler.start(inProgress, 5, this.limit);
+    if (this.returnOnlyUrls) {
+      return this.returnOnlyUrlsResponse(links, inProgress);
     }
 
-    let documents = await this.getCachedDocuments(
-      this.urls.slice(0, this.limit)
-    );
+    let documents = await this.processLinks(links, inProgress);
+    return this.cacheAndFinalizeDocuments(documents, links);
+  }
+
+  private async handleSingleUrlsMode(inProgress?: (progress: Progress) => void): Promise<Document[]> {
+    let documents = await this.convertUrlsToDocuments(this.urls, inProgress);
+    documents = await this.applyPathReplacements(documents);
+    documents = await this.applyImgAltText(documents);
+    return documents;
+  }
+
+  private async handleSitemapMode(inProgress?: (progress: Progress) => void): Promise<Document[]> {
+    let links = await getLinksFromSitemap(this.urls[0]);
+    if (this.returnOnlyUrls) {
+      return this.returnOnlyUrlsResponse(links, inProgress);
+    }
+
+    let documents = await this.processLinks(links, inProgress);
+    return this.cacheAndFinalizeDocuments(documents, links);
+  }
+
+  private async returnOnlyUrlsResponse(links: string[], inProgress?: (progress: Progress) => void): Promise<Document[]> {
+    inProgress?.({
+      current: links.length,
+      total: links.length,
+      status: "COMPLETED",
+      currentDocumentUrl: this.urls[0],
+    });
+    return links.map(url => ({
+      content: "",
+      markdown: "",
+      metadata: { sourceURL: url },
+    }));
+  }
+
+  private async processLinks(links: string[], inProgress?: (progress: Progress) => void): Promise<Document[]> {
+    let pdfLinks = links.filter(link => link.endsWith(".pdf"));
+    let pdfDocuments = await this.fetchPdfDocuments(pdfLinks);
+    links = links.filter(link => !link.endsWith(".pdf"));
+
+    let documents = await this.convertUrlsToDocuments(links, inProgress);
+    documents = await this.getSitemapData(this.urls[0], documents);
+    documents = this.applyPathReplacements(documents);
+    documents = await this.applyImgAltText(documents);
+    return documents.concat(pdfDocuments);
+  }
+
+  private async fetchPdfDocuments(pdfLinks: string[]): Promise<Document[]> {
+    return Promise.all(pdfLinks.map(async pdfLink => {
+      const pdfContent = await fetchAndProcessPdf(pdfLink);
+      return {
+        content: pdfContent,
+        metadata: { sourceURL: pdfLink },
+        provider: "web-scraper"
+      };
+    }));
+  }
+
+  private applyPathReplacements(documents: Document[]): Document[] {
+    return this.replaceAllPathsWithAbsolutePaths ? replacePathsWithAbsolutePaths(documents) : replaceImgPathsWithAbsolutePaths(documents);
+  }
+
+  private async applyImgAltText(documents: Document[]): Promise<Document[]> {
+    return this.generateImgAltText ? this.generatesImgAltText(documents) : documents;
+  }
+
+  private async cacheAndFinalizeDocuments(documents: Document[], links: string[]): Promise<Document[]> {
+    await this.setCachedDocuments(documents, links);
+    documents = this.removeChildLinks(documents);
+    return documents.splice(0, this.limit);
+  }
+
+  private async processDocumentsWithCache(inProgress?: (progress: Progress) => void): Promise<Document[]> {
+    let documents = await this.getCachedDocuments(this.urls.slice(0, this.limit));
     if (documents.length < this.limit) {
-      const newDocuments: Document[] = await this.getDocuments(
-        false,
-        inProgress
-      );
-      newDocuments.forEach((doc) => {
-        if (
-          !documents.some(
-            (d) =>
-              this.normalizeUrl(d.metadata.sourceURL) ===
-              this.normalizeUrl(doc.metadata?.sourceURL)
-          )
-        ) {
-          documents.push(doc);
-        }
-      });
+      const newDocuments: Document[] = await this.getDocuments(false, inProgress);
+      documents = this.mergeNewDocuments(documents, newDocuments);
     }
     documents = this.filterDocsExcludeInclude(documents);
     documents = this.removeChildLinks(documents);
-    documents = documents.splice(0, this.limit);
-    return documents;
+    return documents.splice(0, this.limit);
+  }
+
+  private mergeNewDocuments(existingDocuments: Document[], newDocuments: Document[]): Document[] {
+    newDocuments.forEach(doc => {
+      if (!existingDocuments.some(d => this.normalizeUrl(d.metadata.sourceURL) === this.normalizeUrl(doc.metadata?.sourceURL))) {
+        existingDocuments.push(doc);
+      }
+    });
+    return existingDocuments;
   }
 
   private filterDocsExcludeInclude(documents: Document[]): Document[] {

From 2aa09a3000ea67ff1ecb906a9bd944d906ded4db Mon Sep 17 00:00:00 2001
From: Nicolas <nicolascamara29@gmail.com>
Date: Sat, 4 May 2024 12:30:12 -0700
Subject: [PATCH 02/17] Nick: partial docs working, cleaner

---
 apps/api/src/controllers/crawl-status.ts |  3 ++-
 apps/api/src/controllers/search.ts       |  2 +-
 apps/api/src/lib/entities.ts             |  1 +
 apps/api/src/main/runWebScraper.ts       |  5 ++++-
 apps/api/src/scraper/WebScraper/index.ts | 14 ++++++++++----
 5 files changed, 18 insertions(+), 7 deletions(-)

diff --git a/apps/api/src/controllers/crawl-status.ts b/apps/api/src/controllers/crawl-status.ts
index 3534cd1..05bdb75 100644
--- a/apps/api/src/controllers/crawl-status.ts
+++ b/apps/api/src/controllers/crawl-status.ts
@@ -19,7 +19,7 @@ export async function crawlStatusController(req: Request, res: Response) {
       return res.status(404).json({ error: "Job not found" });
     }
 
-    const { current, current_url, total, current_step } = await job.progress();
+    const { current, current_url, total, current_step, partialDocs } = await job.progress();
     res.json({
       status: await job.getState(),
       // progress: job.progress(),
@@ -28,6 +28,7 @@ export async function crawlStatusController(req: Request, res: Response) {
       current_step: current_step,
       total: total,
       data: job.returnvalue,
+      partial_docs: partialDocs ?? [],
     });
   } catch (error) {
     console.error(error);
diff --git a/apps/api/src/controllers/search.ts b/apps/api/src/controllers/search.ts
index 5c2cf80..41270cb 100644
--- a/apps/api/src/controllers/search.ts
+++ b/apps/api/src/controllers/search.ts
@@ -147,7 +147,7 @@ export async function searchController(req: Request, res: Response) {
     logJob({
       success: result.success,
       message: result.error,
-      num_docs: result.data.length,
+      num_docs: result.data ? result.data.length : 0,
       docs: result.data,
       time_taken: timeTakenInSeconds,
       team_id: team_id,
diff --git a/apps/api/src/lib/entities.ts b/apps/api/src/lib/entities.ts
index 4008785..5b663f2 100644
--- a/apps/api/src/lib/entities.ts
+++ b/apps/api/src/lib/entities.ts
@@ -7,6 +7,7 @@ export interface Progress {
     [key: string]: any;
   };
   currentDocumentUrl?: string;
+  currentDocument?: Document;
 }
 
 export type PageOptions = {
diff --git a/apps/api/src/main/runWebScraper.ts b/apps/api/src/main/runWebScraper.ts
index 892a2a3..827eec5 100644
--- a/apps/api/src/main/runWebScraper.ts
+++ b/apps/api/src/main/runWebScraper.ts
@@ -10,13 +10,15 @@ export async function startWebScraperPipeline({
 }: {
   job: Job<WebScraperOptions>;
 }) {
+  let partialDocs: Document[] = [];
   return (await runWebScraper({
     url: job.data.url,
     mode: job.data.mode,
     crawlerOptions: job.data.crawlerOptions,
     pageOptions: job.data.pageOptions,
     inProgress: (progress) => {
-      job.progress(progress);
+      partialDocs.push(progress.currentDocument);
+      job.progress({...progress, partialDocs: partialDocs});
     },
     onSuccess: (result) => {
       job.moveToCompleted(result);
@@ -69,6 +71,7 @@ export async function runWebScraper({
     }
     const docs = (await provider.getDocuments(false, (progress: Progress) => {
       inProgress(progress);
+      
     })) as Document[];
 
     if (docs.length === 0) {
diff --git a/apps/api/src/scraper/WebScraper/index.ts b/apps/api/src/scraper/WebScraper/index.ts
index ebd96d0..0cf001f 100644
--- a/apps/api/src/scraper/WebScraper/index.ts
+++ b/apps/api/src/scraper/WebScraper/index.ts
@@ -54,6 +54,7 @@ export class WebScraperDataProvider {
               total: totalUrls,
               status: "SCRAPING",
               currentDocumentUrl: url,
+              currentDocument: result
             });
           }
           results[i + index] = result;
@@ -114,9 +115,7 @@ export class WebScraperDataProvider {
   }
 
   private async handleSingleUrlsMode(inProgress?: (progress: Progress) => void): Promise<Document[]> {
-    let documents = await this.convertUrlsToDocuments(this.urls, inProgress);
-    documents = await this.applyPathReplacements(documents);
-    documents = await this.applyImgAltText(documents);
+    let documents = await this.processLinks(this.urls, inProgress);
     return documents;
   }
 
@@ -153,6 +152,13 @@ export class WebScraperDataProvider {
     documents = await this.getSitemapData(this.urls[0], documents);
     documents = this.applyPathReplacements(documents);
     documents = await this.applyImgAltText(documents);
+    
+    if(this.extractorOptions.mode === "llm-extraction" && this.mode === "single_urls") {
+      documents = await generateCompletions(
+        documents,
+        this.extractorOptions
+      )
+    }
     return documents.concat(pdfDocuments);
   }
 
@@ -275,7 +281,7 @@ export class WebScraperDataProvider {
         documents.push(cachedDocument);
 
         // get children documents
-        for (const childUrl of cachedDocument.childrenLinks) {
+        for (const childUrl of (cachedDocument.childrenLinks || [])) {
           const normalizedChildUrl = this.normalizeUrl(childUrl);
           const childCachedDocumentString = await getValue(
             "web-scraper-cache:" + normalizedChildUrl

From 67f135a5b67f2dcf6e5f5adbb4cd76ea60929b28 Mon Sep 17 00:00:00 2001
From: Nicolas <nicolascamara29@gmail.com>
Date: Sat, 4 May 2024 12:31:28 -0700
Subject: [PATCH 03/17] Update crawl-status.ts

---
 apps/api/src/controllers/crawl-status.ts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/apps/api/src/controllers/crawl-status.ts b/apps/api/src/controllers/crawl-status.ts
index 05bdb75..feda86c 100644
--- a/apps/api/src/controllers/crawl-status.ts
+++ b/apps/api/src/controllers/crawl-status.ts
@@ -28,7 +28,7 @@ export async function crawlStatusController(req: Request, res: Response) {
       current_step: current_step,
       total: total,
       data: job.returnvalue,
-      partial_docs: partialDocs ?? [],
+      partial_data: partialDocs ?? [],
     });
   } catch (error) {
     console.error(error);

From 15b774e9749f1dd644e88c7c735631876a0a12e3 Mon Sep 17 00:00:00 2001
From: Nicolas <nicolascamara29@gmail.com>
Date: Sat, 4 May 2024 12:44:30 -0700
Subject: [PATCH 04/17] Update index.ts

---
 apps/api/src/scraper/WebScraper/index.ts | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/apps/api/src/scraper/WebScraper/index.ts b/apps/api/src/scraper/WebScraper/index.ts
index 0cf001f..1e28552 100644
--- a/apps/api/src/scraper/WebScraper/index.ts
+++ b/apps/api/src/scraper/WebScraper/index.ts
@@ -7,7 +7,6 @@ import { getValue, setValue } from "../../services/redis";
 import { getImageDescription } from "./utils/imageDescription";
 import { fetchAndProcessPdf } from "./utils/pdfProcessor";
 import { replaceImgPathsWithAbsolutePaths, replacePathsWithAbsolutePaths } from "./utils/replacePaths";
-import OpenAI from 'openai'
 import { generateCompletions } from "../../lib/LLM-extraction";
 
 
@@ -83,6 +82,11 @@ export class WebScraperDataProvider {
     }
   }
 
+  /**
+   * Process documents without cache handling each mode
+   * @param inProgress inProgress
+   * @returns documents
+   */
   private async processDocumentsWithoutCache(inProgress?: (progress: Progress) => void): Promise<Document[]> {
     switch (this.mode) {
       case "crawl":

From ce7bab7b35691ce565210101d953f6bab9df7143 Mon Sep 17 00:00:00 2001
From: Nicolas <nicolascamara29@gmail.com>
Date: Sat, 4 May 2024 13:00:38 -0700
Subject: [PATCH 05/17] Update status.ts

---
 apps/api/src/controllers/status.ts | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/apps/api/src/controllers/status.ts b/apps/api/src/controllers/status.ts
index bd1d2ea..9079787 100644
--- a/apps/api/src/controllers/status.ts
+++ b/apps/api/src/controllers/status.ts
@@ -8,7 +8,7 @@ export async function crawlJobStatusPreviewController(req: Request, res: Respons
       return res.status(404).json({ error: "Job not found" });
     }
 
-    const { current, current_url, total, current_step } = await job.progress();
+    const { current, current_url, total, current_step, partialDocs } = await job.progress();
     res.json({
       status: await job.getState(),
       // progress: job.progress(),
@@ -17,6 +17,7 @@ export async function crawlJobStatusPreviewController(req: Request, res: Respons
       current_step: current_step,
       total: total,
       data: job.returnvalue,
+      partial_data: partialDocs ?? [],
     });
   } catch (error) {
     console.error(error);

From 5229a4902b48079a505fe8f318dff61a8acf2277 Mon Sep 17 00:00:00 2001
From: Nicolas <nicolascamara29@gmail.com>
Date: Sat, 4 May 2024 13:09:11 -0700
Subject: [PATCH 06/17] Update search.ts

---
 apps/api/src/controllers/search.ts | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/apps/api/src/controllers/search.ts b/apps/api/src/controllers/search.ts
index 41270cb..010af42 100644
--- a/apps/api/src/controllers/search.ts
+++ b/apps/api/src/controllers/search.ts
@@ -54,10 +54,12 @@ export async function searchHelper(
 
   // filter out social media links
 
+  console.log("Search results", searchOptions.limit);
+
   const a = new WebScraperDataProvider();
   await a.setOptions({
     mode: "single_urls",
-    urls: res.map((r) => r.url),
+    urls: res.map((r) => r.url).slice(0, searchOptions.limit ?? 7),
     crawlerOptions: {
       ...crawlerOptions,
     },
@@ -69,7 +71,7 @@ export async function searchHelper(
     },
   });
 
-  const docs = await a.getDocuments(true);
+  const docs = await a.getDocuments(false);
   if (docs.length === 0) {
     return { success: true, error: "No search results found", returnCode: 200 };
   }

From cd9a0840b5aa8eecc23d22332d6957efa8ae460b Mon Sep 17 00:00:00 2001
From: Nicolas <nicolascamara29@gmail.com>
Date: Sat, 4 May 2024 13:13:15 -0700
Subject: [PATCH 07/17] Update search.ts

---
 apps/api/src/controllers/search.ts | 1 -
 1 file changed, 1 deletion(-)

diff --git a/apps/api/src/controllers/search.ts b/apps/api/src/controllers/search.ts
index 010af42..1393922 100644
--- a/apps/api/src/controllers/search.ts
+++ b/apps/api/src/controllers/search.ts
@@ -54,7 +54,6 @@ export async function searchHelper(
 
   // filter out social media links
 
-  console.log("Search results", searchOptions.limit);
 
   const a = new WebScraperDataProvider();
   await a.setOptions({

From 797a7338eac922099e01b40db863e45579639e5e Mon Sep 17 00:00:00 2001
From: Nicolas <nicolascamara29@gmail.com>
Date: Sat, 4 May 2024 13:26:18 -0700
Subject: [PATCH 08/17] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index a66a050..786b05d 100644
--- a/README.md
+++ b/README.md
@@ -2,7 +2,7 @@
 
 Crawl and convert any website into LLM-ready markdown. Built by [Mendable.ai](https://mendable.ai?ref=gfirecrawl) and the firecrawl community.
 
-_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 completely ready for full self-host deployment yet, but you can already run it locally! - we're working on it_
+_This repository is in its early development stages. We are still merging custom modules in the mono repo. It's not completely yet ready for full self-host deployment, but you can already run it locally._
 
 ## What is Firecrawl?
 

From d1b6f6dcde63efa77793ea254bdc0c27e1d0b06c Mon Sep 17 00:00:00 2001
From: Nicolas <nicolascamara29@gmail.com>
Date: Sat, 4 May 2024 13:49:09 -0700
Subject: [PATCH 09/17] Update fly.toml

---
 apps/api/fly.toml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/apps/api/fly.toml b/apps/api/fly.toml
index 4d285eb..1272f4b 100644
--- a/apps/api/fly.toml
+++ b/apps/api/fly.toml
@@ -17,9 +17,9 @@ kill_timeout = '5s'
 [http_service]
   internal_port = 8080
   force_https = true
-  auto_stop_machines = true
+  auto_stop_machines = false
   auto_start_machines = true
-  min_machines_running = 0
+  min_machines_running = 2
   processes = ['app']
 
 [[services]]

From 6913fda710e34c1ea0b1b218e1bd56629ff15ef6 Mon Sep 17 00:00:00 2001
From: Nicolas <nicolascamara29@gmail.com>
Date: Sun, 5 May 2024 10:13:22 -0700
Subject: [PATCH 10/17] Update README.md

---
 README.md | 1 -
 1 file changed, 1 deletion(-)

diff --git a/README.md b/README.md
index 786b05d..9ac5636 100644
--- a/README.md
+++ b/README.md
@@ -261,5 +261,4 @@ search_result = app.search(query)
 
 We love contributions! Please read our [contributing guide](CONTRIBUTING.md) before submitting a pull request.
 
-
 *It is the sole responsibility of the end users to respect websites' policies when scraping, searching and crawling with Firecrawl. Users are advised to adhere to the applicable privacy policies and terms of use of the websites prior to initiating any scraping activities. By default, Firecrawl respects the directives specified in the websites' robots.txt files when crawling. By utilizing Firecrawl, you expressly agree to comply with these conditions.*

From 538355f1af759292364a07028e4749f311aaac36 Mon Sep 17 00:00:00 2001
From: rafaelsideguide <150964962+rafaelsideguide@users.noreply.github.com>
Date: Mon, 6 May 2024 11:36:44 -0300
Subject: [PATCH 11/17] Added toMarkdown option

---
 .../src/__tests__/e2e_withAuth/index.test.ts  | 51 +++++++++++++++++++
 apps/api/src/controllers/crawl.ts             |  2 +-
 apps/api/src/controllers/crawlPreview.ts      |  2 +-
 apps/api/src/controllers/scrape.ts            |  6 +--
 apps/api/src/controllers/search.ts            |  1 +
 apps/api/src/lib/entities.ts                  |  4 +-
 apps/api/src/scraper/WebScraper/index.ts      |  4 +-
 apps/api/src/scraper/WebScraper/single_url.ts | 10 ++--
 8 files changed, 67 insertions(+), 13 deletions(-)

diff --git a/apps/api/src/__tests__/e2e_withAuth/index.test.ts b/apps/api/src/__tests__/e2e_withAuth/index.test.ts
index c6c59bc..2e26230 100644
--- a/apps/api/src/__tests__/e2e_withAuth/index.test.ts
+++ b/apps/api/src/__tests__/e2e_withAuth/index.test.ts
@@ -81,6 +81,21 @@ describe("E2E Tests for API Routes", () => {
       expect(response.body.data).toHaveProperty("metadata");
       expect(response.body.data.content).toContain("🔥 FireCrawl");
     }, 30000); // 30 seconds timeout
+
+    it("should return a successful response with a valid API key and toMarkdown set to false", 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", pageOptions: { toMarkdown: false } });
+      expect(response.statusCode).toBe(200);
+      expect(response.body).toHaveProperty("data");
+      expect(response.body.data).toHaveProperty("content");
+      expect(response.body.data).not.toHaveProperty("markdown");
+      expect(response.body.data).toHaveProperty("metadata");
+      expect(response.body.data.content).toContain("FireCrawl");
+      expect(response.body.data.content).toContain("<h1");
+    }, 30000); // 30 seconds timeout
   });
 
   describe("POST /v0/crawl", () => {
@@ -250,6 +265,42 @@ describe("E2E Tests for API Routes", () => {
         "🔥 FireCrawl"
       );
     }, 60000); // 60 seconds
+
+    it("should return a successful response for a valid crawl job with toMarkdown set to false option", async () => {
+      const crawlResponse = await request(TEST_URL)
+        .post("/v0/crawl")
+        .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
+        .set("Content-Type", "application/json")
+        .send({ url: "https://firecrawl.dev", pageOptions: { toMarkdown: false } });
+      expect(crawlResponse.statusCode).toBe(200);
+
+      const response = await request(TEST_URL)
+        .get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
+        .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
+      expect(response.statusCode).toBe(200);
+      expect(response.body).toHaveProperty("status");
+      expect(response.body.status).toBe("active");
+
+      // wait for 30 seconds
+      await new Promise((r) => setTimeout(r, 30000));
+
+      const completedResponse = await request(TEST_URL)
+        .get(`/v0/crawl/status/${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]).not.toHaveProperty("markdown");
+      expect(completedResponse.body.data[0]).toHaveProperty("metadata");
+      expect(completedResponse.body.data[0].content).toContain(
+        "FireCrawl"
+      );
+      expect(completedResponse.body.data[0].content).toContain(
+        "<h1"
+      );
+    }, 60000); // 60 seconds
   });
 
   describe("POST /v0/scrape with LLM Extraction", () => {
diff --git a/apps/api/src/controllers/crawl.ts b/apps/api/src/controllers/crawl.ts
index 3d64f7f..d5877ab 100644
--- a/apps/api/src/controllers/crawl.ts
+++ b/apps/api/src/controllers/crawl.ts
@@ -35,7 +35,7 @@ export async function crawlController(req: Request, res: Response) {
     
     const mode = req.body.mode ?? "crawl";
     const crawlerOptions = req.body.crawlerOptions ?? {};
-    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false };
+    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, toMarkdown: true };
 
     if (mode === "single_urls" && !url.includes(",")) {
       try {
diff --git a/apps/api/src/controllers/crawlPreview.ts b/apps/api/src/controllers/crawlPreview.ts
index 569be33..0b4a08c 100644
--- a/apps/api/src/controllers/crawlPreview.ts
+++ b/apps/api/src/controllers/crawlPreview.ts
@@ -26,7 +26,7 @@ export async function crawlPreviewController(req: Request, res: Response) {
 
     const mode = req.body.mode ?? "crawl";
     const crawlerOptions = req.body.crawlerOptions ?? {};
-    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false };
+    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, toMarkdown: true};
 
     const job = await addWebScraperJob({
       url: url,
diff --git a/apps/api/src/controllers/scrape.ts b/apps/api/src/controllers/scrape.ts
index 849500a..e03c013 100644
--- a/apps/api/src/controllers/scrape.ts
+++ b/apps/api/src/controllers/scrape.ts
@@ -1,4 +1,4 @@
-import { ExtractorOptions } from './../lib/entities';
+import { ExtractorOptions, PageOptions } from './../lib/entities';
 import { Request, Response } from "express";
 import { WebScraperDataProvider } from "../scraper/WebScraper";
 import { billTeam, checkTeamCredits } from "../services/billing/credit_billing";
@@ -13,7 +13,7 @@ export async function scrapeHelper(
   req: Request,
   team_id: string,
   crawlerOptions: any,
-  pageOptions: any,
+  pageOptions: PageOptions,
   extractorOptions: ExtractorOptions
 ): Promise<{
   success: boolean;
@@ -91,7 +91,7 @@ export async function scrapeController(req: Request, res: Response) {
       return res.status(status).json({ error });
     }
     const crawlerOptions = req.body.crawlerOptions ?? {};
-    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false };
+    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, toMarkdown: true };
     const extractorOptions = req.body.extractorOptions ?? {
       mode: "markdown"
     }
diff --git a/apps/api/src/controllers/search.ts b/apps/api/src/controllers/search.ts
index 1393922..6529edc 100644
--- a/apps/api/src/controllers/search.ts
+++ b/apps/api/src/controllers/search.ts
@@ -66,6 +66,7 @@ export async function searchHelper(
       ...pageOptions,
       onlyMainContent: pageOptions?.onlyMainContent ?? true,
       fetchPageContent: pageOptions?.fetchPageContent ?? true,
+      toMarkdown: pageOptions?.toMarkdown ?? true,
       fallback: false,
     },
   });
diff --git a/apps/api/src/lib/entities.ts b/apps/api/src/lib/entities.ts
index 5b663f2..6150cdd 100644
--- a/apps/api/src/lib/entities.ts
+++ b/apps/api/src/lib/entities.ts
@@ -12,9 +12,9 @@ export interface Progress {
 
 export type PageOptions = {
   onlyMainContent?: boolean;
+  toMarkdown?: boolean;
   fallback?: boolean;
-  fetchPageContent?: boolean;
-  
+  fetchPageContent?: boolean;  
 };
 
 export type ExtractorOptions = {
diff --git a/apps/api/src/scraper/WebScraper/index.ts b/apps/api/src/scraper/WebScraper/index.ts
index 1e28552..2cfa84e 100644
--- a/apps/api/src/scraper/WebScraper/index.ts
+++ b/apps/api/src/scraper/WebScraper/index.ts
@@ -45,7 +45,7 @@ export class WebScraperDataProvider {
       const batchUrls = urls.slice(i, i + this.concurrentRequests);
       await Promise.all(
         batchUrls.map(async (url, index) => {
-          const result = await scrapSingleUrl(url, true, this.pageOptions);
+          const result = await scrapSingleUrl(url, this.pageOptions?.toMarkdown ?? true, this.pageOptions);
           processedUrls++;
           if (inProgress) {
             inProgress({
@@ -323,7 +323,7 @@ export class WebScraperDataProvider {
     this.limit = options.crawlerOptions?.limit ?? 10000;
     this.generateImgAltText =
       options.crawlerOptions?.generateImgAltText ?? false;
-    this.pageOptions = options.pageOptions ?? {onlyMainContent: false};
+    this.pageOptions = options.pageOptions ?? {onlyMainContent: false, toMarkdown: true};
     this.extractorOptions = options.extractorOptions ?? {mode: "markdown"}
     this.replaceAllPathsWithAbsolutePaths = options.crawlerOptions?.replaceAllPathsWithAbsolutePaths ?? false;
 
diff --git a/apps/api/src/scraper/WebScraper/single_url.ts b/apps/api/src/scraper/WebScraper/single_url.ts
index fab54bd..b7fa07a 100644
--- a/apps/api/src/scraper/WebScraper/single_url.ts
+++ b/apps/api/src/scraper/WebScraper/single_url.ts
@@ -172,7 +172,9 @@ export async function scrapSingleUrl(
 
     //* TODO: add an optional to return markdown or structured/extracted content 
     let cleanedHtml = removeUnwantedElements(text, pageOptions);
-
+    if (toMarkdown === false) {
+      return [cleanedHtml, text];
+    }
     return [await parseMarkdown(cleanedHtml), text];
   };
 
@@ -192,7 +194,7 @@ export async function scrapSingleUrl(
       return {
         url: urlToScrap,
         content: text,
-        markdown: text,
+        markdown: pageOptions.toMarkdown === false ? undefined : text,
         metadata: { ...metadata, sourceURL: urlToScrap },
       } as Document;
     }
@@ -215,14 +217,14 @@ export async function scrapSingleUrl(
 
     return {
       content: text,
-      markdown: text,
+      markdown: pageOptions.toMarkdown === false ? undefined : text,
       metadata: { ...metadata, sourceURL: urlToScrap },
     } as Document;
   } catch (error) {
     console.error(`Error: ${error} - Failed to fetch URL: ${urlToScrap}`);
     return {
       content: "",
-      markdown: "",
+      markdown: pageOptions.toMarkdown === false ? undefined : "",
       metadata: { sourceURL: urlToScrap },
     } as Document;
   }

From 509250c4ef6fe41d60f6d5ad8ed2a8a6495c6bf2 Mon Sep 17 00:00:00 2001
From: rafaelsideguide <150964962+rafaelsideguide@users.noreply.github.com>
Date: Mon, 6 May 2024 19:45:56 -0300
Subject: [PATCH 12/17] changed to `includeHtml`

---
 .../src/__tests__/e2e_withAuth/index.test.ts  | 44 +++++++++++--------
 apps/api/src/controllers/crawl.ts             |  5 ++-
 apps/api/src/controllers/crawlPreview.ts      |  4 +-
 apps/api/src/controllers/scrape.ts            | 15 ++++---
 apps/api/src/controllers/search.ts            | 10 +++--
 apps/api/src/lib/entities.ts                  |  2 +-
 apps/api/src/main/runWebScraper.ts            |  5 +++
 apps/api/src/scraper/WebScraper/crawler.ts    |  4 ++
 apps/api/src/scraper/WebScraper/index.ts      |  9 ++--
 apps/api/src/scraper/WebScraper/single_url.ts | 17 +++----
 apps/api/src/types.ts                         |  4 +-
 11 files changed, 78 insertions(+), 41 deletions(-)

diff --git a/apps/api/src/__tests__/e2e_withAuth/index.test.ts b/apps/api/src/__tests__/e2e_withAuth/index.test.ts
index 2e26230..e0f725e 100644
--- a/apps/api/src/__tests__/e2e_withAuth/index.test.ts
+++ b/apps/api/src/__tests__/e2e_withAuth/index.test.ts
@@ -79,22 +79,25 @@ describe("E2E Tests for API Routes", () => {
       expect(response.body.data).toHaveProperty("content");
       expect(response.body.data).toHaveProperty("markdown");
       expect(response.body.data).toHaveProperty("metadata");
+      expect(response.body.data).not.toHaveProperty("html");
       expect(response.body.data.content).toContain("🔥 FireCrawl");
     }, 30000); // 30 seconds timeout
 
-    it("should return a successful response with a valid API key and toMarkdown set to false", async () => {
+    it("should return a successful response with a valid API key and includeHtml set to true", 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", pageOptions: { toMarkdown: false } });
+        .send({ url: "https://firecrawl.dev", includeHtml: true });
       expect(response.statusCode).toBe(200);
       expect(response.body).toHaveProperty("data");
       expect(response.body.data).toHaveProperty("content");
-      expect(response.body.data).not.toHaveProperty("markdown");
+      expect(response.body.data).toHaveProperty("markdown");
+      expect(response.body.data).toHaveProperty("html");
       expect(response.body.data).toHaveProperty("metadata");
-      expect(response.body.data.content).toContain("FireCrawl");
-      expect(response.body.data.content).toContain("<h1");
+      expect(response.body.data.content).toContain("🔥 FireCrawl");
+      expect(response.body.data.markdown).toContain("🔥 FireCrawl");
+      expect(response.body.data.html).toContain("<h1");
     }, 30000); // 30 seconds timeout
   });
 
@@ -158,16 +161,17 @@ describe("E2E Tests for API Routes", () => {
       expect(response.statusCode).toBe(401);
     });
 
-    it("should return an error for a blocklisted URL", async () => {
-      const blocklistedUrl = "https://instagram.com/fake-test";
-      const response = await request(TEST_URL)
-        .post("/v0/crawlWebsitePreview")
-        .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
-        .set("Content-Type", "application/json")
-        .send({ url: blocklistedUrl });
-      expect(response.statusCode).toBe(403);
-      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 an error for a blocklisted URL", async () => {
+    //   const blocklistedUrl = "https://instagram.com/fake-test";
+    //   const response = await request(TEST_URL)
+    //     .post("/v0/crawlWebsitePreview")
+    //     .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
+    //     .set("Content-Type", "application/json")
+    //     .send({ url: blocklistedUrl });
+    // // is returning 429 instead of 403
+    //   expect(response.statusCode).toBe(403);
+    //   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 successful response with a valid API key", async () => {
       const response = await request(TEST_URL)
@@ -271,7 +275,7 @@ describe("E2E Tests for API Routes", () => {
         .post("/v0/crawl")
         .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
         .set("Content-Type", "application/json")
-        .send({ url: "https://firecrawl.dev", pageOptions: { toMarkdown: false } });
+        .send({ url: "https://firecrawl.dev", includeHtml: true });
       expect(crawlResponse.statusCode).toBe(200);
 
       const response = await request(TEST_URL)
@@ -292,12 +296,16 @@ describe("E2E Tests for API Routes", () => {
       expect(completedResponse.body.status).toBe("completed");
       expect(completedResponse.body).toHaveProperty("data");
       expect(completedResponse.body.data[0]).toHaveProperty("content");
-      expect(completedResponse.body.data[0]).not.toHaveProperty("markdown");
+      expect(completedResponse.body.data[0]).toHaveProperty("markdown");
+      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].content).toContain(
+      expect(completedResponse.body.data[0].html).toContain(
         "<h1"
       );
     }, 60000); // 60 seconds
diff --git a/apps/api/src/controllers/crawl.ts b/apps/api/src/controllers/crawl.ts
index d5877ab..d432092 100644
--- a/apps/api/src/controllers/crawl.ts
+++ b/apps/api/src/controllers/crawl.ts
@@ -35,7 +35,8 @@ export async function crawlController(req: Request, res: Response) {
     
     const mode = req.body.mode ?? "crawl";
     const crawlerOptions = req.body.crawlerOptions ?? {};
-    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, toMarkdown: true };
+    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false };
+    const includeHtml = req.body.includeHtml || false;
 
     if (mode === "single_urls" && !url.includes(",")) {
       try {
@@ -47,6 +48,7 @@ export async function crawlController(req: Request, res: Response) {
             returnOnlyUrls: true,
           },
           pageOptions: pageOptions,
+          includeHtml: includeHtml,
         });
 
         const docs = await a.getDocuments(false, (progress) => {
@@ -73,6 +75,7 @@ export async function crawlController(req: Request, res: Response) {
       team_id: team_id,
       pageOptions: pageOptions,
       origin: req.body.origin ?? "api",
+      includeHtml: includeHtml,
     });
 
     res.json({ jobId: job.id });
diff --git a/apps/api/src/controllers/crawlPreview.ts b/apps/api/src/controllers/crawlPreview.ts
index 0b4a08c..2b1b676 100644
--- a/apps/api/src/controllers/crawlPreview.ts
+++ b/apps/api/src/controllers/crawlPreview.ts
@@ -26,7 +26,8 @@ export async function crawlPreviewController(req: Request, res: Response) {
 
     const mode = req.body.mode ?? "crawl";
     const crawlerOptions = req.body.crawlerOptions ?? {};
-    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, toMarkdown: true};
+    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false };
+    const includeHtml = req.body.includeHtml ?? false;
 
     const job = await addWebScraperJob({
       url: url,
@@ -35,6 +36,7 @@ export async function crawlPreviewController(req: Request, res: Response) {
       team_id: "preview",
       pageOptions: pageOptions,
       origin: "website-preview",
+      includeHtml: includeHtml,
     });
 
     res.json({ jobId: job.id });
diff --git a/apps/api/src/controllers/scrape.ts b/apps/api/src/controllers/scrape.ts
index e03c013..5bd61a5 100644
--- a/apps/api/src/controllers/scrape.ts
+++ b/apps/api/src/controllers/scrape.ts
@@ -14,7 +14,8 @@ export async function scrapeHelper(
   team_id: string,
   crawlerOptions: any,
   pageOptions: PageOptions,
-  extractorOptions: ExtractorOptions
+  extractorOptions: ExtractorOptions,
+  includeHtml: boolean = false
 ): Promise<{
   success: boolean;
   error?: string;
@@ -39,7 +40,8 @@ export async function scrapeHelper(
       ...crawlerOptions,
     },
     pageOptions: pageOptions,
-    extractorOptions: extractorOptions
+    extractorOptions: extractorOptions,
+    includeHtml: includeHtml
   });
 
   const docs = await a.getDocuments(false);
@@ -91,11 +93,12 @@ export async function scrapeController(req: Request, res: Response) {
       return res.status(status).json({ error });
     }
     const crawlerOptions = req.body.crawlerOptions ?? {};
-    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, toMarkdown: true };
+    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false };
     const extractorOptions = req.body.extractorOptions ?? {
       mode: "markdown"
     }
     const origin = req.body.origin ?? "api";
+    const includeHtml = req.body.includeHtml ?? false;
 
     try {
       const { success: creditsCheckSuccess, message: creditsCheckMessage } =
@@ -113,7 +116,8 @@ export async function scrapeController(req: Request, res: Response) {
       team_id,
       crawlerOptions,
       pageOptions,
-      extractorOptions
+      extractorOptions,
+      includeHtml
     );
     const endTime = new Date().getTime();
     const timeTakenInSeconds = (endTime - startTime) / 1000;
@@ -132,7 +136,8 @@ export async function scrapeController(req: Request, res: Response) {
       pageOptions: pageOptions,
       origin: origin, 
       extractor_options: extractorOptions,
-      num_tokens: numTokens
+      num_tokens: numTokens,
+      includeHtml: includeHtml
     });
     return res.status(result.returnCode).json(result);
   } catch (error) {
diff --git a/apps/api/src/controllers/search.ts b/apps/api/src/controllers/search.ts
index 6529edc..314e475 100644
--- a/apps/api/src/controllers/search.ts
+++ b/apps/api/src/controllers/search.ts
@@ -13,7 +13,8 @@ export async function searchHelper(
   team_id: string,
   crawlerOptions: any,
   pageOptions: PageOptions,
-  searchOptions: SearchOptions
+  searchOptions: SearchOptions,
+  includeHtml: boolean = false
 ): Promise<{
   success: boolean;
   error?: string;
@@ -59,6 +60,7 @@ export async function searchHelper(
   await a.setOptions({
     mode: "single_urls",
     urls: res.map((r) => r.url).slice(0, searchOptions.limit ?? 7),
+    includeHtml,
     crawlerOptions: {
       ...crawlerOptions,
     },
@@ -66,7 +68,6 @@ export async function searchHelper(
       ...pageOptions,
       onlyMainContent: pageOptions?.onlyMainContent ?? true,
       fetchPageContent: pageOptions?.fetchPageContent ?? true,
-      toMarkdown: pageOptions?.toMarkdown ?? true,
       fallback: false,
     },
   });
@@ -125,6 +126,7 @@ export async function searchController(req: Request, res: Response) {
     const origin = req.body.origin ?? "api";
 
     const searchOptions = req.body.searchOptions ?? { limit: 7 };
+    const includeHtml = req.body.includeHtml ?? false;
 
     try {
       const { success: creditsCheckSuccess, message: creditsCheckMessage } =
@@ -142,7 +144,8 @@ export async function searchController(req: Request, res: Response) {
       team_id,
       crawlerOptions,
       pageOptions,
-      searchOptions
+      searchOptions,
+      includeHtml
     );
     const endTime = new Date().getTime();
     const timeTakenInSeconds = (endTime - startTime) / 1000;
@@ -158,6 +161,7 @@ export async function searchController(req: Request, res: Response) {
       crawlerOptions: crawlerOptions,
       pageOptions: pageOptions,
       origin: origin,
+      includeHtml,
     });
     return res.status(result.returnCode).json(result);
   } catch (error) {
diff --git a/apps/api/src/lib/entities.ts b/apps/api/src/lib/entities.ts
index 6150cdd..b6340d8 100644
--- a/apps/api/src/lib/entities.ts
+++ b/apps/api/src/lib/entities.ts
@@ -12,7 +12,6 @@ export interface Progress {
 
 export type PageOptions = {
   onlyMainContent?: boolean;
-  toMarkdown?: boolean;
   fallback?: boolean;
   fetchPageContent?: boolean;  
 };
@@ -47,6 +46,7 @@ export type WebScraperOptions = {
   pageOptions?: PageOptions;
   extractorOptions?: ExtractorOptions;
   concurrentRequests?: number;
+  includeHtml?: boolean;
 };
 
 export interface DocumentUrl {
diff --git a/apps/api/src/main/runWebScraper.ts b/apps/api/src/main/runWebScraper.ts
index 827eec5..798bb65 100644
--- a/apps/api/src/main/runWebScraper.ts
+++ b/apps/api/src/main/runWebScraper.ts
@@ -27,6 +27,7 @@ export async function startWebScraperPipeline({
       job.moveToFailed(error);
     },
     team_id: job.data.team_id,
+    includeHtml: job.data.includeHtml,
   })) as { success: boolean; message: string; docs: Document[] };
 }
 export async function runWebScraper({
@@ -38,6 +39,7 @@ export async function runWebScraper({
   onSuccess,
   onError,
   team_id,
+  includeHtml = false,
 }: {
   url: string;
   mode: "crawl" | "single_urls" | "sitemap";
@@ -47,6 +49,7 @@ export async function runWebScraper({
   onSuccess: (result: any) => void;
   onError: (error: any) => void;
   team_id: string;
+  includeHtml?: boolean;
 }): Promise<{
   success: boolean;
   message: string;
@@ -60,6 +63,7 @@ export async function runWebScraper({
         urls: [url],
         crawlerOptions: crawlerOptions,
         pageOptions: pageOptions,
+        includeHtml: includeHtml,
       });
     } else {
       await provider.setOptions({
@@ -67,6 +71,7 @@ export async function runWebScraper({
         urls: url.split(","),
         crawlerOptions: crawlerOptions,
         pageOptions: pageOptions,
+        includeHtml: includeHtml,
       });
     }
     const docs = (await provider.getDocuments(false, (progress: Progress) => {
diff --git a/apps/api/src/scraper/WebScraper/crawler.ts b/apps/api/src/scraper/WebScraper/crawler.ts
index 23cb629..d3877b3 100644
--- a/apps/api/src/scraper/WebScraper/crawler.ts
+++ b/apps/api/src/scraper/WebScraper/crawler.ts
@@ -19,6 +19,7 @@ export class WebCrawler {
   private robotsTxtUrl: string;
   private robots: any;
   private generateImgAltText: boolean;
+  private includeHtml: boolean;
 
   constructor({
     initialUrl,
@@ -27,6 +28,7 @@ export class WebCrawler {
     maxCrawledLinks,
     limit = 10000,
     generateImgAltText = false,
+    includeHtml = false,
   }: {
     initialUrl: string;
     includes?: string[];
@@ -34,6 +36,7 @@ export class WebCrawler {
     maxCrawledLinks?: number;
     limit?: number;
     generateImgAltText?: boolean;
+    includeHtml?: boolean;
   }) {
     this.initialUrl = initialUrl;
     this.baseUrl = new URL(initialUrl).origin;
@@ -45,6 +48,7 @@ export class WebCrawler {
     // Deprecated, use limit instead
     this.maxCrawledLinks = maxCrawledLinks ?? limit;
     this.generateImgAltText = generateImgAltText ?? false;
+    this.includeHtml = includeHtml ?? false;
   }
 
 
diff --git a/apps/api/src/scraper/WebScraper/index.ts b/apps/api/src/scraper/WebScraper/index.ts
index 2cfa84e..2a3916b 100644
--- a/apps/api/src/scraper/WebScraper/index.ts
+++ b/apps/api/src/scraper/WebScraper/index.ts
@@ -24,6 +24,7 @@ export class WebScraperDataProvider {
   private extractorOptions?: ExtractorOptions;
   private replaceAllPathsWithAbsolutePaths?: boolean = false;
   private generateImgAltTextModel: "gpt-4-turbo" | "claude-3-opus" = "gpt-4-turbo";
+  private includeHtml: boolean = false;
 
   authorize(): void {
     throw new Error("Method not implemented.");
@@ -45,7 +46,7 @@ export class WebScraperDataProvider {
       const batchUrls = urls.slice(i, i + this.concurrentRequests);
       await Promise.all(
         batchUrls.map(async (url, index) => {
-          const result = await scrapSingleUrl(url, this.pageOptions?.toMarkdown ?? true, this.pageOptions);
+          const result = await scrapSingleUrl(url, this.pageOptions, this.includeHtml);
           processedUrls++;
           if (inProgress) {
             inProgress({
@@ -108,6 +109,7 @@ export class WebScraperDataProvider {
       maxCrawledLinks: this.maxCrawledLinks,
       limit: this.limit,
       generateImgAltText: this.generateImgAltText,
+      includeHtml: this.includeHtml,
     });
     let links = await crawler.start(inProgress, 5, this.limit);
     if (this.returnOnlyUrls) {
@@ -142,6 +144,7 @@ export class WebScraperDataProvider {
     });
     return links.map(url => ({
       content: "",
+      html: this.includeHtml ? "" : undefined,
       markdown: "",
       metadata: { sourceURL: url },
     }));
@@ -323,10 +326,10 @@ export class WebScraperDataProvider {
     this.limit = options.crawlerOptions?.limit ?? 10000;
     this.generateImgAltText =
       options.crawlerOptions?.generateImgAltText ?? false;
-    this.pageOptions = options.pageOptions ?? {onlyMainContent: false, toMarkdown: true};
+    this.pageOptions = options.pageOptions ?? {onlyMainContent: false };
     this.extractorOptions = options.extractorOptions ?? {mode: "markdown"}
     this.replaceAllPathsWithAbsolutePaths = options.crawlerOptions?.replaceAllPathsWithAbsolutePaths ?? false;
-
+    this.includeHtml = options?.includeHtml ?? 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
     this.excludes = this.excludes.filter((item) => item !== "");
 
diff --git a/apps/api/src/scraper/WebScraper/single_url.ts b/apps/api/src/scraper/WebScraper/single_url.ts
index b7fa07a..4d071db 100644
--- a/apps/api/src/scraper/WebScraper/single_url.ts
+++ b/apps/api/src/scraper/WebScraper/single_url.ts
@@ -103,8 +103,8 @@ export async function scrapWithPlaywright(url: string): Promise<string> {
 
 export async function scrapSingleUrl(
   urlToScrap: string,
-  toMarkdown: boolean = true,
-  pageOptions: PageOptions = { onlyMainContent: true }
+  pageOptions: PageOptions = { onlyMainContent: true },
+  includeHtml: boolean = false
 ): Promise<Document> {
   urlToScrap = urlToScrap.trim();
 
@@ -172,9 +172,7 @@ export async function scrapSingleUrl(
 
     //* TODO: add an optional to return markdown or structured/extracted content 
     let cleanedHtml = removeUnwantedElements(text, pageOptions);
-    if (toMarkdown === false) {
-      return [cleanedHtml, text];
-    }
+    
     return [await parseMarkdown(cleanedHtml), text];
   };
 
@@ -194,7 +192,8 @@ export async function scrapSingleUrl(
       return {
         url: urlToScrap,
         content: text,
-        markdown: pageOptions.toMarkdown === false ? undefined : text,
+        markdown: text,
+        html: includeHtml ? html : undefined,
         metadata: { ...metadata, sourceURL: urlToScrap },
       } as Document;
     }
@@ -217,14 +216,16 @@ export async function scrapSingleUrl(
 
     return {
       content: text,
-      markdown: pageOptions.toMarkdown === false ? undefined : text,
+      markdown: text,
+      html: includeHtml ? html : undefined,
       metadata: { ...metadata, sourceURL: urlToScrap },
     } as Document;
   } catch (error) {
     console.error(`Error: ${error} - Failed to fetch URL: ${urlToScrap}`);
     return {
       content: "",
-      markdown: pageOptions.toMarkdown === false ? undefined : "",
+      markdown: "",
+      html: "",
       metadata: { sourceURL: urlToScrap },
     } as Document;
   }
diff --git a/apps/api/src/types.ts b/apps/api/src/types.ts
index c1858f1..3fbdcdd 100644
--- a/apps/api/src/types.ts
+++ b/apps/api/src/types.ts
@@ -25,6 +25,7 @@ export interface WebScraperOptions {
   pageOptions: any;
   team_id: string;
   origin?: string;
+  includeHtml?: boolean;
 }
 
 export interface FirecrawlJob {
@@ -40,7 +41,8 @@ export interface FirecrawlJob {
   pageOptions?: any;
   origin: string;
   extractor_options?: ExtractorOptions,
-  num_tokens?: number
+  num_tokens?: number,
+  includeHtml?: boolean;
 }
 
 export enum RateLimiterMode {

From 6d5da358cca6f6ef3b9d047fec7c1eea63997664 Mon Sep 17 00:00:00 2001
From: Nicolas <nicolascamara29@gmail.com>
Date: Mon, 6 May 2024 17:16:43 -0700
Subject: [PATCH 13/17] Nick: cancel job

---
 apps/api/fly.toml                             |  15 +-
 .../src/__tests__/e2e_withAuth/index.test.ts  |  35 +++++
 apps/api/src/controllers/crawl-cancel.ts      |  50 ++++++
 apps/api/src/controllers/crawl.ts             |  13 +-
 apps/api/src/lib/entities.ts                  |   1 +
 apps/api/src/main/runWebScraper.ts            |   4 +
 apps/api/src/routes/v0.ts                     |   2 +
 apps/api/src/scraper/WebScraper/index.ts      | 148 ++++++++++++------
 apps/api/src/services/logging/crawl_log.ts    |  17 ++
 9 files changed, 236 insertions(+), 49 deletions(-)
 create mode 100644 apps/api/src/controllers/crawl-cancel.ts
 create mode 100644 apps/api/src/services/logging/crawl_log.ts

diff --git a/apps/api/fly.toml b/apps/api/fly.toml
index 1272f4b..ca619d1 100644
--- a/apps/api/fly.toml
+++ b/apps/api/fly.toml
@@ -22,6 +22,11 @@ kill_timeout = '5s'
   min_machines_running = 2
   processes = ['app']
 
+[http_service.concurrency]
+  type = "requests"
+  hard_limit = 200
+  soft_limit = 100
+
 [[services]]
   protocol = 'tcp'
   internal_port = 8080
@@ -38,10 +43,14 @@ kill_timeout = '5s'
 
   [services.concurrency]
     type = 'connections'
-    hard_limit = 45
-    soft_limit = 20
+    hard_limit = 75
+    soft_limit = 30
 
 [[vm]]
-  size = 'performance-1x'
+  size = 'performance-4x'
+  processes = ['app']
+
+
+
 
   
diff --git a/apps/api/src/__tests__/e2e_withAuth/index.test.ts b/apps/api/src/__tests__/e2e_withAuth/index.test.ts
index c6c59bc..78d20e4 100644
--- a/apps/api/src/__tests__/e2e_withAuth/index.test.ts
+++ b/apps/api/src/__tests__/e2e_withAuth/index.test.ts
@@ -252,6 +252,41 @@ describe("E2E Tests for API Routes", () => {
     }, 60000); // 60 seconds
   });
 
+  it("If someone cancels a crawl job, it should turn into failed status", async () => {
+    const crawlResponse = await request(TEST_URL)
+      .post("/v0/crawl")
+      .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
+      .set("Content-Type", "application/json")
+      .send({ url: "https://jestjs.io" });
+    expect(crawlResponse.statusCode).toBe(200);
+
+    
+
+    // wait for 30 seconds
+    await new Promise((r) => setTimeout(r, 10000));
+
+    const response = await request(TEST_URL)
+      .delete(`/v0/crawl/cancel/${crawlResponse.body.jobId}`)
+      .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
+    expect(response.statusCode).toBe(200);
+    expect(response.body).toHaveProperty("status");
+    expect(response.body.status).toBe("cancelled");
+
+    await new Promise((r) => setTimeout(r, 20000));
+
+    const completedResponse = await request(TEST_URL)
+      .get(`/v0/crawl/status/${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("failed");
+    expect(completedResponse.body.partial_data?.length ?? 0).toBeLessThanOrEqual(completedResponse.body.data?.length ?? 0);
+
+
+  }, 60000); // 60 seconds
+
+  
+
   describe("POST /v0/scrape with LLM Extraction", () => {
     it("should extract data using LLM extraction mode", async () => {
       const response = await request(TEST_URL)
diff --git a/apps/api/src/controllers/crawl-cancel.ts b/apps/api/src/controllers/crawl-cancel.ts
new file mode 100644
index 0000000..7523b78
--- /dev/null
+++ b/apps/api/src/controllers/crawl-cancel.ts
@@ -0,0 +1,50 @@
+import { Request, Response } from "express";
+import { authenticateUser } from "./auth";
+import { RateLimiterMode } from "../../src/types";
+import { addWebScraperJob } from "../../src/services/queue-jobs";
+import { getWebScraperQueue } from "../../src/services/queue-service";
+import { supabase_service } from "../../src/services/supabase";
+
+export async function crawlCancelController(req: Request, res: Response) {
+  try {
+    const { success, team_id, error, status } = await authenticateUser(
+      req,
+      res,
+      RateLimiterMode.CrawlStatus
+    );
+    if (!success) {
+      return res.status(status).json({ error });
+    }
+    const job = await getWebScraperQueue().getJob(req.params.jobId);
+    if (!job) {
+      return res.status(404).json({ error: "Job not found" });
+    }
+
+    // check if the job belongs to the team
+    const {data, error: supaError}= await supabase_service.from("bulljobs_teams").select("*").eq("job_id", req.params.jobId).eq("team_id", team_id);
+    if (supaError) {
+      return res.status(500).json({ error: supaError.message });
+    }
+
+    if (data.length === 0) {
+      return res.status(403).json({ error: "Unauthorized" });
+    }
+
+    try {
+    await job.moveToFailed(Error("Job cancelled by user"), true);
+        
+    } catch (error) {
+        console.error(error);
+        
+    }
+
+    const jobState = await job.getState();
+
+    res.json({
+      status: jobState === "failed" ? "cancelled" : "Cancelling...",
+    });
+  } catch (error) {
+    console.error(error);
+    return res.status(500).json({ error: error.message });
+  }
+}
diff --git a/apps/api/src/controllers/crawl.ts b/apps/api/src/controllers/crawl.ts
index 3d64f7f..8b5249b 100644
--- a/apps/api/src/controllers/crawl.ts
+++ b/apps/api/src/controllers/crawl.ts
@@ -6,6 +6,7 @@ import { authenticateUser } from "./auth";
 import { RateLimiterMode } from "../../src/types";
 import { addWebScraperJob } from "../../src/services/queue-jobs";
 import { isUrlBlocked } from "../../src/scraper/WebScraper/utils/blocklist";
+import { logCrawl } from "../../src/services/logging/crawl_log";
 
 export async function crawlController(req: Request, res: Response) {
   try {
@@ -30,9 +31,14 @@ export async function crawlController(req: Request, res: Response) {
     }
 
     if (isUrlBlocked(url)) {
-      return res.status(403).json({ error: "Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it." });
+      return res
+        .status(403)
+        .json({
+          error:
+            "Firecrawl currently does not support social media scraping due to policy restrictions. We're actively working on building support for it.",
+        });
     }
-    
+
     const mode = req.body.mode ?? "crawl";
     const crawlerOptions = req.body.crawlerOptions ?? {};
     const pageOptions = req.body.pageOptions ?? { onlyMainContent: false };
@@ -66,6 +72,7 @@ export async function crawlController(req: Request, res: Response) {
         return res.status(500).json({ error: error.message });
       }
     }
+
     const job = await addWebScraperJob({
       url: url,
       mode: mode ?? "crawl", // fix for single urls not working
@@ -75,6 +82,8 @@ export async function crawlController(req: Request, res: Response) {
       origin: req.body.origin ?? "api",
     });
 
+    await logCrawl(job.id.toString(), team_id);
+
     res.json({ jobId: job.id });
   } catch (error) {
     console.error(error);
diff --git a/apps/api/src/lib/entities.ts b/apps/api/src/lib/entities.ts
index 5b663f2..1bb9429 100644
--- a/apps/api/src/lib/entities.ts
+++ b/apps/api/src/lib/entities.ts
@@ -47,6 +47,7 @@ export type WebScraperOptions = {
   pageOptions?: PageOptions;
   extractorOptions?: ExtractorOptions;
   concurrentRequests?: number;
+  bullJobId?: string;
 };
 
 export interface DocumentUrl {
diff --git a/apps/api/src/main/runWebScraper.ts b/apps/api/src/main/runWebScraper.ts
index 827eec5..252f2e4 100644
--- a/apps/api/src/main/runWebScraper.ts
+++ b/apps/api/src/main/runWebScraper.ts
@@ -27,6 +27,7 @@ export async function startWebScraperPipeline({
       job.moveToFailed(error);
     },
     team_id: job.data.team_id,
+    bull_job_id: job.id.toString(),
   })) as { success: boolean; message: string; docs: Document[] };
 }
 export async function runWebScraper({
@@ -38,6 +39,7 @@ export async function runWebScraper({
   onSuccess,
   onError,
   team_id,
+  bull_job_id,
 }: {
   url: string;
   mode: "crawl" | "single_urls" | "sitemap";
@@ -47,6 +49,7 @@ export async function runWebScraper({
   onSuccess: (result: any) => void;
   onError: (error: any) => void;
   team_id: string;
+  bull_job_id: string;
 }): Promise<{
   success: boolean;
   message: string;
@@ -60,6 +63,7 @@ export async function runWebScraper({
         urls: [url],
         crawlerOptions: crawlerOptions,
         pageOptions: pageOptions,
+        bullJobId: bull_job_id,
       });
     } else {
       await provider.setOptions({
diff --git a/apps/api/src/routes/v0.ts b/apps/api/src/routes/v0.ts
index f84b974..42b8814 100644
--- a/apps/api/src/routes/v0.ts
+++ b/apps/api/src/routes/v0.ts
@@ -5,6 +5,7 @@ import { scrapeController } from "../../src/controllers/scrape";
 import { crawlPreviewController } from "../../src/controllers/crawlPreview";
 import { crawlJobStatusPreviewController } from "../../src/controllers/status";
 import { searchController } from "../../src/controllers/search";
+import { crawlCancelController } from "../../src/controllers/crawl-cancel";
 
 export const v0Router = express.Router();
 
@@ -12,6 +13,7 @@ v0Router.post("/v0/scrape", scrapeController);
 v0Router.post("/v0/crawl", crawlController);
 v0Router.post("/v0/crawlWebsitePreview", crawlPreviewController);
 v0Router.get("/v0/crawl/status/:jobId", crawlStatusController);
+v0Router.delete("/v0/crawl/cancel/:jobId", crawlCancelController);
 v0Router.get("/v0/checkJobStatus/:jobId", crawlJobStatusPreviewController);
 
 // Search routes
diff --git a/apps/api/src/scraper/WebScraper/index.ts b/apps/api/src/scraper/WebScraper/index.ts
index 1e28552..18624e1 100644
--- a/apps/api/src/scraper/WebScraper/index.ts
+++ b/apps/api/src/scraper/WebScraper/index.ts
@@ -1,4 +1,9 @@
-import { Document, ExtractorOptions, PageOptions, WebScraperOptions } from "../../lib/entities";
+import {
+  Document,
+  ExtractorOptions,
+  PageOptions,
+  WebScraperOptions,
+} from "../../lib/entities";
 import { Progress } from "../../lib/entities";
 import { scrapSingleUrl } from "./single_url";
 import { SitemapEntry, fetchSitemapData, getLinksFromSitemap } from "./sitemap";
@@ -6,11 +11,15 @@ import { WebCrawler } from "./crawler";
 import { getValue, setValue } from "../../services/redis";
 import { getImageDescription } from "./utils/imageDescription";
 import { fetchAndProcessPdf } from "./utils/pdfProcessor";
-import { replaceImgPathsWithAbsolutePaths, replacePathsWithAbsolutePaths } from "./utils/replacePaths";
+import {
+  replaceImgPathsWithAbsolutePaths,
+  replacePathsWithAbsolutePaths,
+} from "./utils/replacePaths";
 import { generateCompletions } from "../../lib/LLM-extraction";
-
+import { getWebScraperQueue } from "../../../src/services/queue-service";
 
 export class WebScraperDataProvider {
+  private bullJobId: string;
   private urls: string[] = [""];
   private mode: "single_urls" | "sitemap" | "crawl" = "single_urls";
   private includes: string[];
@@ -23,7 +32,8 @@ export class WebScraperDataProvider {
   private pageOptions?: PageOptions;
   private extractorOptions?: ExtractorOptions;
   private replaceAllPathsWithAbsolutePaths?: boolean = false;
-  private generateImgAltTextModel: "gpt-4-turbo" | "claude-3-opus" = "gpt-4-turbo";
+  private generateImgAltTextModel: "gpt-4-turbo" | "claude-3-opus" =
+    "gpt-4-turbo";
 
   authorize(): void {
     throw new Error("Method not implemented.");
@@ -39,7 +49,7 @@ export class WebScraperDataProvider {
   ): Promise<Document[]> {
     const totalUrls = urls.length;
     let processedUrls = 0;
-  
+
     const results: (Document | null)[] = new Array(urls.length).fill(null);
     for (let i = 0; i < urls.length; i += this.concurrentRequests) {
       const batchUrls = urls.slice(i, i + this.concurrentRequests);
@@ -53,12 +63,20 @@ export class WebScraperDataProvider {
               total: totalUrls,
               status: "SCRAPING",
               currentDocumentUrl: url,
-              currentDocument: result
+              currentDocument: result,
             });
           }
+
           results[i + index] = result;
         })
       );
+      const job = await getWebScraperQueue().getJob(this.bullJobId);
+      const jobStatus = await job.getState();
+      if (jobStatus === "failed") {
+        throw new Error(
+          "Job has failed or has been cancelled by the user. Stopping the job..."
+        );
+      }
     }
     return results.filter((result) => result !== null) as Document[];
   }
@@ -87,7 +105,9 @@ export class WebScraperDataProvider {
    * @param inProgress inProgress
    * @returns documents
    */
-  private async processDocumentsWithoutCache(inProgress?: (progress: Progress) => void): Promise<Document[]> {
+  private async processDocumentsWithoutCache(
+    inProgress?: (progress: Progress) => void
+  ): Promise<Document[]> {
     switch (this.mode) {
       case "crawl":
         return this.handleCrawlMode(inProgress);
@@ -100,7 +120,9 @@ export class WebScraperDataProvider {
     }
   }
 
-  private async handleCrawlMode(inProgress?: (progress: Progress) => void): Promise<Document[]> {
+  private async handleCrawlMode(
+    inProgress?: (progress: Progress) => void
+  ): Promise<Document[]> {
     const crawler = new WebCrawler({
       initialUrl: this.urls[0],
       includes: this.includes,
@@ -118,12 +140,16 @@ export class WebScraperDataProvider {
     return this.cacheAndFinalizeDocuments(documents, links);
   }
 
-  private async handleSingleUrlsMode(inProgress?: (progress: Progress) => void): Promise<Document[]> {
+  private async handleSingleUrlsMode(
+    inProgress?: (progress: Progress) => void
+  ): Promise<Document[]> {
     let documents = await this.processLinks(this.urls, inProgress);
     return documents;
   }
 
-  private async handleSitemapMode(inProgress?: (progress: Progress) => void): Promise<Document[]> {
+  private async handleSitemapMode(
+    inProgress?: (progress: Progress) => void
+  ): Promise<Document[]> {
     let links = await getLinksFromSitemap(this.urls[0]);
     if (this.returnOnlyUrls) {
       return this.returnOnlyUrlsResponse(links, inProgress);
@@ -133,68 +159,90 @@ export class WebScraperDataProvider {
     return this.cacheAndFinalizeDocuments(documents, links);
   }
 
-  private async returnOnlyUrlsResponse(links: string[], inProgress?: (progress: Progress) => void): Promise<Document[]> {
+  private async returnOnlyUrlsResponse(
+    links: string[],
+    inProgress?: (progress: Progress) => void
+  ): Promise<Document[]> {
     inProgress?.({
       current: links.length,
       total: links.length,
       status: "COMPLETED",
       currentDocumentUrl: this.urls[0],
     });
-    return links.map(url => ({
+    return links.map((url) => ({
       content: "",
       markdown: "",
       metadata: { sourceURL: url },
     }));
   }
 
-  private async processLinks(links: string[], inProgress?: (progress: Progress) => void): Promise<Document[]> {
-    let pdfLinks = links.filter(link => link.endsWith(".pdf"));
+  private async processLinks(
+    links: string[],
+    inProgress?: (progress: Progress) => void
+  ): Promise<Document[]> {
+    let pdfLinks = links.filter((link) => link.endsWith(".pdf"));
     let pdfDocuments = await this.fetchPdfDocuments(pdfLinks);
-    links = links.filter(link => !link.endsWith(".pdf"));
+    links = links.filter((link) => !link.endsWith(".pdf"));
 
     let documents = await this.convertUrlsToDocuments(links, inProgress);
     documents = await this.getSitemapData(this.urls[0], documents);
     documents = this.applyPathReplacements(documents);
     documents = await this.applyImgAltText(documents);
-    
-    if(this.extractorOptions.mode === "llm-extraction" && this.mode === "single_urls") {
-      documents = await generateCompletions(
-        documents,
-        this.extractorOptions
-      )
+
+    if (
+      this.extractorOptions.mode === "llm-extraction" &&
+      this.mode === "single_urls"
+    ) {
+      documents = await generateCompletions(documents, this.extractorOptions);
     }
     return documents.concat(pdfDocuments);
   }
 
   private async fetchPdfDocuments(pdfLinks: string[]): Promise<Document[]> {
-    return Promise.all(pdfLinks.map(async pdfLink => {
-      const pdfContent = await fetchAndProcessPdf(pdfLink);
-      return {
-        content: pdfContent,
-        metadata: { sourceURL: pdfLink },
-        provider: "web-scraper"
-      };
-    }));
+    return Promise.all(
+      pdfLinks.map(async (pdfLink) => {
+        const pdfContent = await fetchAndProcessPdf(pdfLink);
+        return {
+          content: pdfContent,
+          metadata: { sourceURL: pdfLink },
+          provider: "web-scraper",
+        };
+      })
+    );
   }
 
   private applyPathReplacements(documents: Document[]): Document[] {
-    return this.replaceAllPathsWithAbsolutePaths ? replacePathsWithAbsolutePaths(documents) : replaceImgPathsWithAbsolutePaths(documents);
+    return this.replaceAllPathsWithAbsolutePaths
+      ? replacePathsWithAbsolutePaths(documents)
+      : replaceImgPathsWithAbsolutePaths(documents);
   }
 
   private async applyImgAltText(documents: Document[]): Promise<Document[]> {
-    return this.generateImgAltText ? this.generatesImgAltText(documents) : documents;
+    return this.generateImgAltText
+      ? this.generatesImgAltText(documents)
+      : documents;
   }
 
-  private async cacheAndFinalizeDocuments(documents: Document[], links: string[]): Promise<Document[]> {
+  private async cacheAndFinalizeDocuments(
+    documents: Document[],
+    links: string[]
+  ): Promise<Document[]> {
     await this.setCachedDocuments(documents, links);
     documents = this.removeChildLinks(documents);
     return documents.splice(0, this.limit);
   }
 
-  private async processDocumentsWithCache(inProgress?: (progress: Progress) => void): Promise<Document[]> {
-    let documents = await this.getCachedDocuments(this.urls.slice(0, this.limit));
+  private async processDocumentsWithCache(
+    inProgress?: (progress: Progress) => void
+  ): Promise<Document[]> {
+    let documents = await this.getCachedDocuments(
+      this.urls.slice(0, this.limit)
+    );
     if (documents.length < this.limit) {
-      const newDocuments: Document[] = await this.getDocuments(false, inProgress);
+      const newDocuments: Document[] = await this.getDocuments(
+        false,
+        inProgress
+      );
       documents = this.mergeNewDocuments(documents, newDocuments);
     }
     documents = this.filterDocsExcludeInclude(documents);
@@ -202,9 +250,18 @@ export class WebScraperDataProvider {
     return documents.splice(0, this.limit);
   }
 
-  private mergeNewDocuments(existingDocuments: Document[], newDocuments: Document[]): Document[] {
-    newDocuments.forEach(doc => {
-      if (!existingDocuments.some(d => this.normalizeUrl(d.metadata.sourceURL) === this.normalizeUrl(doc.metadata?.sourceURL))) {
+  private mergeNewDocuments(
+    existingDocuments: Document[],
+    newDocuments: Document[]
+  ): Document[] {
+    newDocuments.forEach((doc) => {
+      if (
+        !existingDocuments.some(
+          (d) =>
+            this.normalizeUrl(d.metadata.sourceURL) ===
+            this.normalizeUrl(doc.metadata?.sourceURL)
+        )
+      ) {
         existingDocuments.push(doc);
       }
     });
@@ -285,7 +342,7 @@ export class WebScraperDataProvider {
         documents.push(cachedDocument);
 
         // get children documents
-        for (const childUrl of (cachedDocument.childrenLinks || [])) {
+        for (const childUrl of cachedDocument.childrenLinks || []) {
           const normalizedChildUrl = this.normalizeUrl(childUrl);
           const childCachedDocumentString = await getValue(
             "web-scraper-cache:" + normalizedChildUrl
@@ -313,6 +370,7 @@ export class WebScraperDataProvider {
       throw new Error("Urls are required");
     }
 
+    this.bullJobId = options.bullJobId;
     this.urls = options.urls;
     this.mode = options.mode;
     this.concurrentRequests = options.concurrentRequests ?? 20;
@@ -323,9 +381,10 @@ export class WebScraperDataProvider {
     this.limit = options.crawlerOptions?.limit ?? 10000;
     this.generateImgAltText =
       options.crawlerOptions?.generateImgAltText ?? false;
-    this.pageOptions = options.pageOptions ?? {onlyMainContent: false};
-    this.extractorOptions = options.extractorOptions ?? {mode: "markdown"}
-    this.replaceAllPathsWithAbsolutePaths = options.crawlerOptions?.replaceAllPathsWithAbsolutePaths ?? false;
+    this.pageOptions = options.pageOptions ?? { onlyMainContent: false };
+    this.extractorOptions = options.extractorOptions ?? { mode: "markdown" };
+    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
     this.excludes = this.excludes.filter((item) => item !== "");
@@ -396,8 +455,9 @@ export class WebScraperDataProvider {
               altText = await getImageDescription(
                 imageUrl,
                 backText,
-                frontText
-              , this.generateImgAltTextModel);
+                frontText,
+                this.generateImgAltTextModel
+              );
             }
 
             document.content = document.content.replace(
diff --git a/apps/api/src/services/logging/crawl_log.ts b/apps/api/src/services/logging/crawl_log.ts
new file mode 100644
index 0000000..76a0607
--- /dev/null
+++ b/apps/api/src/services/logging/crawl_log.ts
@@ -0,0 +1,17 @@
+import { supabase_service } from "../supabase";
+import "dotenv/config";
+
+export async function logCrawl(job_id: string, team_id: string) {
+  try {
+    const { data, error } = await supabase_service
+      .from("bulljobs_teams")
+      .insert([
+        {
+          job_id: job_id,
+          team_id: team_id,
+        },
+      ]);
+  } catch (error) {
+    console.error("Error logging crawl job:\n", error);
+  }
+}

From 2e3ff855092881d6371baae92251213654df6d53 Mon Sep 17 00:00:00 2001
From: Nicolas <nicolascamara29@gmail.com>
Date: Mon, 6 May 2024 17:22:16 -0700
Subject: [PATCH 14/17] Update crawl-cancel.ts

---
 apps/api/src/controllers/crawl-cancel.ts | 30 +++++++++++++++++-------
 1 file changed, 21 insertions(+), 9 deletions(-)

diff --git a/apps/api/src/controllers/crawl-cancel.ts b/apps/api/src/controllers/crawl-cancel.ts
index 7523b78..8e8ba31 100644
--- a/apps/api/src/controllers/crawl-cancel.ts
+++ b/apps/api/src/controllers/crawl-cancel.ts
@@ -4,6 +4,7 @@ import { RateLimiterMode } from "../../src/types";
 import { addWebScraperJob } from "../../src/services/queue-jobs";
 import { getWebScraperQueue } from "../../src/services/queue-service";
 import { supabase_service } from "../../src/services/supabase";
+import { billTeam } from "../../src/services/billing/credit_billing";
 
 export async function crawlCancelController(req: Request, res: Response) {
   try {
@@ -21,7 +22,11 @@ export async function crawlCancelController(req: Request, res: Response) {
     }
 
     // check if the job belongs to the team
-    const {data, error: supaError}= await supabase_service.from("bulljobs_teams").select("*").eq("job_id", req.params.jobId).eq("team_id", team_id);
+    const { data, error: supaError } = await supabase_service
+      .from("bulljobs_teams")
+      .select("*")
+      .eq("job_id", req.params.jobId)
+      .eq("team_id", team_id);
     if (supaError) {
       return res.status(500).json({ error: supaError.message });
     }
@@ -29,19 +34,26 @@ export async function crawlCancelController(req: Request, res: Response) {
     if (data.length === 0) {
       return res.status(403).json({ error: "Unauthorized" });
     }
+    const jobState = await job.getState();
+    const { partialDocs } = await job.progress();
 
-    try {
-    await job.moveToFailed(Error("Job cancelled by user"), true);
-        
-    } catch (error) {
-        console.error(error);
-        
+    if (partialDocs && partialDocs.length > 0 && jobState === "active") {
+      console.log("Billing team for partial docs...");
+      // Note: the credits that we will bill them here might be lower than the actual
+      // due to promises that are not yet resolved
+      await billTeam(team_id, partialDocs.length);
     }
 
-    const jobState = await job.getState();
+    try {
+      await job.moveToFailed(Error("Job cancelled by user"), true);
+    } catch (error) {
+      console.error(error);
+    }
+
+    const newJobState = await job.getState();
 
     res.json({
-      status: jobState === "failed" ? "cancelled" : "Cancelling...",
+      status: newJobState === "failed" ? "cancelled" : "Cancelling...",
     });
   } catch (error) {
     console.error(error);

From f46bf19fa53dc8a2dbe8fb8b8804f3ebd853f5fe Mon Sep 17 00:00:00 2001
From: Nicolas <nicolascamara29@gmail.com>
Date: Tue, 7 May 2024 09:26:52 -0700
Subject: [PATCH 15/17] Nick:

---
 .../src/__tests__/e2e_withAuth/index.test.ts   |  1 -
 apps/api/src/scraper/WebScraper/index.ts       | 18 +++++++++++-------
 2 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/apps/api/src/__tests__/e2e_withAuth/index.test.ts b/apps/api/src/__tests__/e2e_withAuth/index.test.ts
index 78d20e4..9a16073 100644
--- a/apps/api/src/__tests__/e2e_withAuth/index.test.ts
+++ b/apps/api/src/__tests__/e2e_withAuth/index.test.ts
@@ -280,7 +280,6 @@ describe("E2E Tests for API Routes", () => {
     expect(completedResponse.statusCode).toBe(200);
     expect(completedResponse.body).toHaveProperty("status");
     expect(completedResponse.body.status).toBe("failed");
-    expect(completedResponse.body.partial_data?.length ?? 0).toBeLessThanOrEqual(completedResponse.body.data?.length ?? 0);
 
 
   }, 60000); // 60 seconds
diff --git a/apps/api/src/scraper/WebScraper/index.ts b/apps/api/src/scraper/WebScraper/index.ts
index 18624e1..3a77843 100644
--- a/apps/api/src/scraper/WebScraper/index.ts
+++ b/apps/api/src/scraper/WebScraper/index.ts
@@ -70,13 +70,17 @@ export class WebScraperDataProvider {
           results[i + index] = result;
         })
       );
-      const job = await getWebScraperQueue().getJob(this.bullJobId);
-      const jobStatus = await job.getState();
-      if (jobStatus === "failed") {
-        throw new Error(
-          "Job has failed or has been cancelled by the user. Stopping the job..."
-        );
-      }
+      try {
+        if (this.mode === "crawl" && this.bullJobId) {
+          const job = await getWebScraperQueue().getJob(this.bullJobId);
+          const jobStatus = await job.getState();
+          if (jobStatus === "failed") {
+            throw new Error(
+              "Job has failed or has been cancelled by the user. Stopping the job..."
+            );
+          }
+        }
+      } catch (error) {}
     }
     return results.filter((result) => result !== null) as Document[];
   }

From e1f52c538fd8852fe977303fc929077b77faf77b Mon Sep 17 00:00:00 2001
From: rafaelsideguide <150964962+rafaelsideguide@users.noreply.github.com>
Date: Tue, 7 May 2024 13:40:24 -0300
Subject: [PATCH 16/17] nested includeHtml inside pageOptions

---
 apps/api/src/__tests__/e2e_withAuth/index.test.ts |  6 +++---
 apps/api/src/controllers/crawl.ts                 |  5 +----
 apps/api/src/controllers/crawlPreview.ts          |  4 +---
 apps/api/src/controllers/scrape.ts                |  7 +------
 apps/api/src/controllers/search.ts                |  7 ++-----
 apps/api/src/lib/entities.ts                      |  4 ++--
 apps/api/src/main/runWebScraper.ts                | 11 +++--------
 apps/api/src/scraper/WebScraper/crawler.ts        |  4 ----
 apps/api/src/scraper/WebScraper/index.ts          |  9 +++------
 apps/api/src/scraper/WebScraper/single_url.ts     |  7 +++----
 apps/api/src/types.ts                             |  2 --
 11 files changed, 19 insertions(+), 47 deletions(-)

diff --git a/apps/api/src/__tests__/e2e_withAuth/index.test.ts b/apps/api/src/__tests__/e2e_withAuth/index.test.ts
index e0f725e..644ad36 100644
--- a/apps/api/src/__tests__/e2e_withAuth/index.test.ts
+++ b/apps/api/src/__tests__/e2e_withAuth/index.test.ts
@@ -88,7 +88,7 @@ describe("E2E Tests for API Routes", () => {
         .post("/v0/scrape")
         .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
         .set("Content-Type", "application/json")
-        .send({ url: "https://firecrawl.dev", includeHtml: true });
+        .send({ url: "https://firecrawl.dev", pageOptions: { includeHtml: true }});
       expect(response.statusCode).toBe(200);
       expect(response.body).toHaveProperty("data");
       expect(response.body.data).toHaveProperty("content");
@@ -270,12 +270,12 @@ describe("E2E Tests for API Routes", () => {
       );
     }, 60000); // 60 seconds
 
-    it("should return a successful response for a valid crawl job with toMarkdown set to false option", async () => {
+    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", includeHtml: true });
+        .send({ url: "https://firecrawl.dev", pageOptions: { includeHtml: true } });
       expect(crawlResponse.statusCode).toBe(200);
 
       const response = await request(TEST_URL)
diff --git a/apps/api/src/controllers/crawl.ts b/apps/api/src/controllers/crawl.ts
index d432092..3ba9213 100644
--- a/apps/api/src/controllers/crawl.ts
+++ b/apps/api/src/controllers/crawl.ts
@@ -35,8 +35,7 @@ export async function crawlController(req: Request, res: Response) {
     
     const mode = req.body.mode ?? "crawl";
     const crawlerOptions = req.body.crawlerOptions ?? {};
-    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false };
-    const includeHtml = req.body.includeHtml || false;
+    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, includeHtml: false };
 
     if (mode === "single_urls" && !url.includes(",")) {
       try {
@@ -48,7 +47,6 @@ export async function crawlController(req: Request, res: Response) {
             returnOnlyUrls: true,
           },
           pageOptions: pageOptions,
-          includeHtml: includeHtml,
         });
 
         const docs = await a.getDocuments(false, (progress) => {
@@ -75,7 +73,6 @@ export async function crawlController(req: Request, res: Response) {
       team_id: team_id,
       pageOptions: pageOptions,
       origin: req.body.origin ?? "api",
-      includeHtml: includeHtml,
     });
 
     res.json({ jobId: job.id });
diff --git a/apps/api/src/controllers/crawlPreview.ts b/apps/api/src/controllers/crawlPreview.ts
index 2b1b676..d3e9afe 100644
--- a/apps/api/src/controllers/crawlPreview.ts
+++ b/apps/api/src/controllers/crawlPreview.ts
@@ -26,8 +26,7 @@ export async function crawlPreviewController(req: Request, res: Response) {
 
     const mode = req.body.mode ?? "crawl";
     const crawlerOptions = req.body.crawlerOptions ?? {};
-    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false };
-    const includeHtml = req.body.includeHtml ?? false;
+    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, includeHtml: false };
 
     const job = await addWebScraperJob({
       url: url,
@@ -36,7 +35,6 @@ export async function crawlPreviewController(req: Request, res: Response) {
       team_id: "preview",
       pageOptions: pageOptions,
       origin: "website-preview",
-      includeHtml: includeHtml,
     });
 
     res.json({ jobId: job.id });
diff --git a/apps/api/src/controllers/scrape.ts b/apps/api/src/controllers/scrape.ts
index 5bd61a5..021a9d0 100644
--- a/apps/api/src/controllers/scrape.ts
+++ b/apps/api/src/controllers/scrape.ts
@@ -15,7 +15,6 @@ export async function scrapeHelper(
   crawlerOptions: any,
   pageOptions: PageOptions,
   extractorOptions: ExtractorOptions,
-  includeHtml: boolean = false
 ): Promise<{
   success: boolean;
   error?: string;
@@ -41,7 +40,6 @@ export async function scrapeHelper(
     },
     pageOptions: pageOptions,
     extractorOptions: extractorOptions,
-    includeHtml: includeHtml
   });
 
   const docs = await a.getDocuments(false);
@@ -93,12 +91,11 @@ export async function scrapeController(req: Request, res: Response) {
       return res.status(status).json({ error });
     }
     const crawlerOptions = req.body.crawlerOptions ?? {};
-    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false };
+    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, includeHtml: false };
     const extractorOptions = req.body.extractorOptions ?? {
       mode: "markdown"
     }
     const origin = req.body.origin ?? "api";
-    const includeHtml = req.body.includeHtml ?? false;
 
     try {
       const { success: creditsCheckSuccess, message: creditsCheckMessage } =
@@ -117,7 +114,6 @@ export async function scrapeController(req: Request, res: Response) {
       crawlerOptions,
       pageOptions,
       extractorOptions,
-      includeHtml
     );
     const endTime = new Date().getTime();
     const timeTakenInSeconds = (endTime - startTime) / 1000;
@@ -137,7 +133,6 @@ export async function scrapeController(req: Request, res: Response) {
       origin: origin, 
       extractor_options: extractorOptions,
       num_tokens: numTokens,
-      includeHtml: includeHtml
     });
     return res.status(result.returnCode).json(result);
   } catch (error) {
diff --git a/apps/api/src/controllers/search.ts b/apps/api/src/controllers/search.ts
index 314e475..d98c08d 100644
--- a/apps/api/src/controllers/search.ts
+++ b/apps/api/src/controllers/search.ts
@@ -14,7 +14,6 @@ export async function searchHelper(
   crawlerOptions: any,
   pageOptions: PageOptions,
   searchOptions: SearchOptions,
-  includeHtml: boolean = false
 ): Promise<{
   success: boolean;
   error?: string;
@@ -60,7 +59,6 @@ export async function searchHelper(
   await a.setOptions({
     mode: "single_urls",
     urls: res.map((r) => r.url).slice(0, searchOptions.limit ?? 7),
-    includeHtml,
     crawlerOptions: {
       ...crawlerOptions,
     },
@@ -68,6 +66,7 @@ export async function searchHelper(
       ...pageOptions,
       onlyMainContent: pageOptions?.onlyMainContent ?? true,
       fetchPageContent: pageOptions?.fetchPageContent ?? true,
+      includeHtml: pageOptions?.includeHtml ?? false,
       fallback: false,
     },
   });
@@ -119,6 +118,7 @@ export async function searchController(req: Request, res: Response) {
     }
     const crawlerOptions = req.body.crawlerOptions ?? {};
     const pageOptions = req.body.pageOptions ?? {
+      includeHtml: false,
       onlyMainContent: true,
       fetchPageContent: true,
       fallback: false,
@@ -126,7 +126,6 @@ export async function searchController(req: Request, res: Response) {
     const origin = req.body.origin ?? "api";
 
     const searchOptions = req.body.searchOptions ?? { limit: 7 };
-    const includeHtml = req.body.includeHtml ?? false;
 
     try {
       const { success: creditsCheckSuccess, message: creditsCheckMessage } =
@@ -145,7 +144,6 @@ export async function searchController(req: Request, res: Response) {
       crawlerOptions,
       pageOptions,
       searchOptions,
-      includeHtml
     );
     const endTime = new Date().getTime();
     const timeTakenInSeconds = (endTime - startTime) / 1000;
@@ -161,7 +159,6 @@ export async function searchController(req: Request, res: Response) {
       crawlerOptions: crawlerOptions,
       pageOptions: pageOptions,
       origin: origin,
-      includeHtml,
     });
     return res.status(result.returnCode).json(result);
   } catch (error) {
diff --git a/apps/api/src/lib/entities.ts b/apps/api/src/lib/entities.ts
index b6340d8..0a6a90e 100644
--- a/apps/api/src/lib/entities.ts
+++ b/apps/api/src/lib/entities.ts
@@ -12,8 +12,9 @@ export interface Progress {
 
 export type PageOptions = {
   onlyMainContent?: boolean;
+  includeHtml?: boolean;
   fallback?: boolean;
-  fetchPageContent?: boolean;  
+  fetchPageContent?: boolean;
 };
 
 export type ExtractorOptions = {
@@ -46,7 +47,6 @@ export type WebScraperOptions = {
   pageOptions?: PageOptions;
   extractorOptions?: ExtractorOptions;
   concurrentRequests?: number;
-  includeHtml?: boolean;
 };
 
 export interface DocumentUrl {
diff --git a/apps/api/src/main/runWebScraper.ts b/apps/api/src/main/runWebScraper.ts
index 798bb65..189d500 100644
--- a/apps/api/src/main/runWebScraper.ts
+++ b/apps/api/src/main/runWebScraper.ts
@@ -26,8 +26,7 @@ export async function startWebScraperPipeline({
     onError: (error) => {
       job.moveToFailed(error);
     },
-    team_id: job.data.team_id,
-    includeHtml: job.data.includeHtml,
+    team_id: job.data.team_id
   })) as { success: boolean; message: string; docs: Document[] };
 }
 export async function runWebScraper({
@@ -39,7 +38,6 @@ export async function runWebScraper({
   onSuccess,
   onError,
   team_id,
-  includeHtml = false,
 }: {
   url: string;
   mode: "crawl" | "single_urls" | "sitemap";
@@ -49,7 +47,6 @@ export async function runWebScraper({
   onSuccess: (result: any) => void;
   onError: (error: any) => void;
   team_id: string;
-  includeHtml?: boolean;
 }): Promise<{
   success: boolean;
   message: string;
@@ -62,16 +59,14 @@ export async function runWebScraper({
         mode: mode,
         urls: [url],
         crawlerOptions: crawlerOptions,
-        pageOptions: pageOptions,
-        includeHtml: includeHtml,
+        pageOptions: pageOptions
       });
     } else {
       await provider.setOptions({
         mode: mode,
         urls: url.split(","),
         crawlerOptions: crawlerOptions,
-        pageOptions: pageOptions,
-        includeHtml: includeHtml,
+        pageOptions: pageOptions
       });
     }
     const docs = (await provider.getDocuments(false, (progress: Progress) => {
diff --git a/apps/api/src/scraper/WebScraper/crawler.ts b/apps/api/src/scraper/WebScraper/crawler.ts
index d3877b3..23cb629 100644
--- a/apps/api/src/scraper/WebScraper/crawler.ts
+++ b/apps/api/src/scraper/WebScraper/crawler.ts
@@ -19,7 +19,6 @@ export class WebCrawler {
   private robotsTxtUrl: string;
   private robots: any;
   private generateImgAltText: boolean;
-  private includeHtml: boolean;
 
   constructor({
     initialUrl,
@@ -28,7 +27,6 @@ export class WebCrawler {
     maxCrawledLinks,
     limit = 10000,
     generateImgAltText = false,
-    includeHtml = false,
   }: {
     initialUrl: string;
     includes?: string[];
@@ -36,7 +34,6 @@ export class WebCrawler {
     maxCrawledLinks?: number;
     limit?: number;
     generateImgAltText?: boolean;
-    includeHtml?: boolean;
   }) {
     this.initialUrl = initialUrl;
     this.baseUrl = new URL(initialUrl).origin;
@@ -48,7 +45,6 @@ export class WebCrawler {
     // Deprecated, use limit instead
     this.maxCrawledLinks = maxCrawledLinks ?? limit;
     this.generateImgAltText = generateImgAltText ?? false;
-    this.includeHtml = includeHtml ?? false;
   }
 
 
diff --git a/apps/api/src/scraper/WebScraper/index.ts b/apps/api/src/scraper/WebScraper/index.ts
index 2a3916b..ed49f1d 100644
--- a/apps/api/src/scraper/WebScraper/index.ts
+++ b/apps/api/src/scraper/WebScraper/index.ts
@@ -24,7 +24,6 @@ export class WebScraperDataProvider {
   private extractorOptions?: ExtractorOptions;
   private replaceAllPathsWithAbsolutePaths?: boolean = false;
   private generateImgAltTextModel: "gpt-4-turbo" | "claude-3-opus" = "gpt-4-turbo";
-  private includeHtml: boolean = false;
 
   authorize(): void {
     throw new Error("Method not implemented.");
@@ -46,7 +45,7 @@ export class WebScraperDataProvider {
       const batchUrls = urls.slice(i, i + this.concurrentRequests);
       await Promise.all(
         batchUrls.map(async (url, index) => {
-          const result = await scrapSingleUrl(url, this.pageOptions, this.includeHtml);
+          const result = await scrapSingleUrl(url, this.pageOptions);
           processedUrls++;
           if (inProgress) {
             inProgress({
@@ -109,7 +108,6 @@ export class WebScraperDataProvider {
       maxCrawledLinks: this.maxCrawledLinks,
       limit: this.limit,
       generateImgAltText: this.generateImgAltText,
-      includeHtml: this.includeHtml,
     });
     let links = await crawler.start(inProgress, 5, this.limit);
     if (this.returnOnlyUrls) {
@@ -144,7 +142,7 @@ export class WebScraperDataProvider {
     });
     return links.map(url => ({
       content: "",
-      html: this.includeHtml ? "" : undefined,
+      html: this.pageOptions?.includeHtml ? "" : undefined,
       markdown: "",
       metadata: { sourceURL: url },
     }));
@@ -326,10 +324,9 @@ export class WebScraperDataProvider {
     this.limit = options.crawlerOptions?.limit ?? 10000;
     this.generateImgAltText =
       options.crawlerOptions?.generateImgAltText ?? false;
-    this.pageOptions = options.pageOptions ?? {onlyMainContent: false };
+    this.pageOptions = options.pageOptions ?? { onlyMainContent: false, includeHtml: false };
     this.extractorOptions = options.extractorOptions ?? {mode: "markdown"}
     this.replaceAllPathsWithAbsolutePaths = options.crawlerOptions?.replaceAllPathsWithAbsolutePaths ?? false;
-    this.includeHtml = options?.includeHtml ?? 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
     this.excludes = this.excludes.filter((item) => item !== "");
 
diff --git a/apps/api/src/scraper/WebScraper/single_url.ts b/apps/api/src/scraper/WebScraper/single_url.ts
index 4d071db..a67ce31 100644
--- a/apps/api/src/scraper/WebScraper/single_url.ts
+++ b/apps/api/src/scraper/WebScraper/single_url.ts
@@ -103,8 +103,7 @@ export async function scrapWithPlaywright(url: string): Promise<string> {
 
 export async function scrapSingleUrl(
   urlToScrap: string,
-  pageOptions: PageOptions = { onlyMainContent: true },
-  includeHtml: boolean = false
+  pageOptions: PageOptions = { onlyMainContent: true, includeHtml: false },
 ): Promise<Document> {
   urlToScrap = urlToScrap.trim();
 
@@ -193,7 +192,7 @@ export async function scrapSingleUrl(
         url: urlToScrap,
         content: text,
         markdown: text,
-        html: includeHtml ? html : undefined,
+        html: pageOptions.includeHtml ? html : undefined,
         metadata: { ...metadata, sourceURL: urlToScrap },
       } as Document;
     }
@@ -217,7 +216,7 @@ export async function scrapSingleUrl(
     return {
       content: text,
       markdown: text,
-      html: includeHtml ? html : undefined,
+      html: pageOptions.includeHtml ? html : undefined,
       metadata: { ...metadata, sourceURL: urlToScrap },
     } as Document;
   } catch (error) {
diff --git a/apps/api/src/types.ts b/apps/api/src/types.ts
index 3fbdcdd..b9b5463 100644
--- a/apps/api/src/types.ts
+++ b/apps/api/src/types.ts
@@ -25,7 +25,6 @@ export interface WebScraperOptions {
   pageOptions: any;
   team_id: string;
   origin?: string;
-  includeHtml?: boolean;
 }
 
 export interface FirecrawlJob {
@@ -42,7 +41,6 @@ export interface FirecrawlJob {
   origin: string;
   extractor_options?: ExtractorOptions,
   num_tokens?: number,
-  includeHtml?: boolean;
 }
 
 export enum RateLimiterMode {

From 61d615c04b2aa629e33affd0afc6e400b863300d Mon Sep 17 00:00:00 2001
From: rafaelsideguide <150964962+rafaelsideguide@users.noreply.github.com>
Date: Tue, 7 May 2024 14:03:00 -0300
Subject: [PATCH 17/17] Added tests

---
 apps/api/src/__tests__/e2e_withAuth/index.test.ts | 9 +++++++--
 apps/api/src/scraper/WebScraper/index.ts          | 4 +++-
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/apps/api/src/__tests__/e2e_withAuth/index.test.ts b/apps/api/src/__tests__/e2e_withAuth/index.test.ts
index 9a16073..3e82fb4 100644
--- a/apps/api/src/__tests__/e2e_withAuth/index.test.ts
+++ b/apps/api/src/__tests__/e2e_withAuth/index.test.ts
@@ -280,8 +280,13 @@ describe("E2E Tests for API Routes", () => {
     expect(completedResponse.statusCode).toBe(200);
     expect(completedResponse.body).toHaveProperty("status");
     expect(completedResponse.body.status).toBe("failed");
-
-
+    expect(completedResponse.body).toHaveProperty("data");
+    expect(completedResponse.body.data).toEqual(null);
+    expect(completedResponse.body).toHaveProperty("partial_data");
+    expect(completedResponse.body.partial_data[0]).toHaveProperty("content");
+    expect(completedResponse.body.partial_data[0]).toHaveProperty("markdown");
+    expect(completedResponse.body.partial_data[0]).toHaveProperty("metadata");
+    
   }, 60000); // 60 seconds
 
   
diff --git a/apps/api/src/scraper/WebScraper/index.ts b/apps/api/src/scraper/WebScraper/index.ts
index 3a77843..96112f8 100644
--- a/apps/api/src/scraper/WebScraper/index.ts
+++ b/apps/api/src/scraper/WebScraper/index.ts
@@ -80,7 +80,9 @@ export class WebScraperDataProvider {
             );
           }
         }
-      } catch (error) {}
+      } catch (error) {
+        console.error(error);
+      }
     }
     return results.filter((result) => result !== null) as Document[];
   }