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

Merge pull request #178 from mattjoyce/main

Browse Source 
Fix FIRECRAWL_API_URL bug, also various PyLint fixes
This commit is contained in:
Nicolas 2024-05-24 09:49:42 -07:00 committed by GitHub
commit 605ba4c031
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 149 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
apps/python-sdk/.pylintrc Normal file
View File

@ -0,0 +1,2 @@
[FORMAT]
max-line-length = 120

154
apps/python-sdk/firecrawl/firecrawl.py
View File

@ -1,18 +1,50 @@
"""
FirecrawlApp Module
This module provides a class `FirecrawlApp` for interacting with the Firecrawl API.
It includes methods to scrape URLs, perform searches, initiate and monitor crawl jobs,
and check the status of these jobs. The module uses requests for HTTP communication
and handles retries for certain HTTP status codes.
Classes:
- FirecrawlApp: Main class for interacting with the Firecrawl API.
"""
import os
from typing import Any, Dict, Optional
import requests
import time
from typing import Any, Dict, Optional
import requests
class FirecrawlApp:
def __init__(self, api_key=None, api_url='https://api.firecrawl.dev'):
"""
Initialize the FirecrawlApp instance.
Args:
api_key (Optional[str]): API key for authenticating with the Firecrawl API.
api_url (Optional[str]): Base URL for the Firecrawl API.
"""
def __init__(self, api_key: Optional[str] = None, api_url: Optional[str] = None) -> None:
self.api_key = api_key or os.getenv('FIRECRAWL_API_KEY')
if self.api_key is None:
raise ValueError('No API key provided')
self.api_url = api_url or os.getenv('FIRECRAWL_API_URL')
self.api_url = api_url or os.getenv('FIRECRAWL_API_URL', 'https://api.firecrawl.dev')
def scrape_url(self, url: str, params: Optional[Dict[str, Any]] = None) -> Any:
"""
Scrape the specified URL using the Firecrawl API.
Args:
url (str): The URL to scrape.
params (Optional[Dict[str, Any]]): Additional parameters for the scrape request.
Returns:
Any: The scraped data if the request is successful.
Raises:
Exception: If the scrape request fails.
"""
headers = {
'Content-Type': 'application/json',
'Authorization': f'Bearer {self.api_key}'
@ -41,7 +73,7 @@ class FirecrawlApp:
response = requests.post(
f'{self.api_url}/v0/scrape',
headers=headers,
json=scrape_params
json=scrape_params,
)
if response.status_code == 200:
response = response.json()
@ -56,6 +88,19 @@ class FirecrawlApp:
raise Exception(f'Failed to scrape URL. Status code: {response.status_code}')
def search(self, query, params=None):
"""
Perform a search using the Firecrawl API.
Args:
query (str): The search query.
params (Optional[Dict[str, Any]]): Additional parameters for the search request.
Returns:
Any: The search results if the request is successful.
Raises:
Exception: If the search request fails.
"""
headers = {
'Content-Type': 'application/json',
'Authorization': f'Bearer {self.api_key}'
@ -70,6 +115,7 @@ class FirecrawlApp:
)
if response.status_code == 200:
response = response.json()
if response['success'] and 'data' in response:
return response['data']
else:
@ -82,6 +128,21 @@ class FirecrawlApp:
raise Exception(f'Failed to search. Status code: {response.status_code}')
def crawl_url(self, url, params=None, wait_until_done=True, timeout=2):
"""
Initiate a crawl job for the specified URL using the Firecrawl API.
Args:
url (str): The URL to crawl.
params (Optional[Dict[str, Any]]): Additional parameters for the crawl request.
wait_until_done (bool): Whether to wait until the crawl job is completed.
timeout (int): Timeout between status checks when waiting for job completion.
Returns:
Any: The crawl job ID or the crawl results if waiting until completion.
Raises:
Exception: If the crawl job initiation or monitoring fails.
"""
headers = self._prepare_headers()
json_data = {'url': url}
if params:
@ -97,6 +158,18 @@ class FirecrawlApp:
self._handle_error(response, 'start crawl job')
def check_crawl_status(self, job_id):
"""
Check the status of a crawl job using the Firecrawl API.
Args:
job_id (str): The ID of the crawl job.
Returns:
Any: The status of the crawl job.
Raises:
Exception: If the status check request fails.
"""
headers = self._prepare_headers()
response = self._get_request(f'{self.api_url}/v0/crawl/status/{job_id}', headers)
if response.status_code == 200:
@ -105,12 +178,34 @@ class FirecrawlApp:
self._handle_error(response, 'check crawl status')
def _prepare_headers(self):
"""
Prepare the headers for API requests.
Returns:
Dict[str, str]: The headers including content type and authorization.
"""
return {
'Content-Type': 'application/json',
'Authorization': f'Bearer {self.api_key}'
}
def _post_request(self, url, data, headers, retries=3, backoff_factor=0.5):
"""
Make a POST request with retries.
Args:
url (str): The URL to send the POST request to.
data (Dict[str, Any]): The JSON data to include in the POST request.
headers (Dict[str, str]): The headers to include in the POST request.
retries (int): Number of retries for the request.
backoff_factor (float): Backoff factor for retries.
Returns:
requests.Response: The response from the POST request.
Raises:
requests.RequestException: If the request fails after the specified retries.
"""
for attempt in range(retries):
response = requests.post(url, headers=headers, json=data)
if response.status_code == 502:
@ -120,6 +215,21 @@ class FirecrawlApp:
return response
def _get_request(self, url, headers, retries=3, backoff_factor=0.5):
"""
Make a GET request with retries.
Args:
url (str): The URL to send the GET request to.
headers (Dict[str, str]): The headers to include in the GET request.
retries (int): Number of retries for the request.
backoff_factor (float): Backoff factor for retries.
Returns:
requests.Response: The response from the GET request.
Raises:
requests.RequestException: If the request fails after the specified retries.
"""
for attempt in range(retries):
response = requests.get(url, headers=headers)
if response.status_code == 502:
@ -129,7 +239,20 @@ class FirecrawlApp:
return response
def _monitor_job_status(self, job_id, headers, timeout):
import time
"""
Monitor the status of a crawl job until completion.
Args:
job_id (str): The ID of the crawl job.
headers (Dict[str, str]): The headers to include in the status check requests.
timeout (int): Timeout between status checks.
Returns:
Any: The crawl results if the job is completed successfully.
Raises:
Exception: If the job fails or an error occurs during status checks.
"""
while True:
status_response = self._get_request(f'{self.api_url}/v0/crawl/status/{job_id}', headers)
if status_response.status_code == 200:
@ -140,8 +263,7 @@ class FirecrawlApp:
else:
raise Exception('Crawl job completed but no data was returned')
elif status_data['status'] in ['active', 'paused', 'pending', 'queued']:
if timeout < 2:
timeout = 2
timeout=max(timeout,2)
time.sleep(timeout) # Wait for the specified timeout before checking again
else:
raise Exception(f'Crawl job failed or was stopped. Status: {status_data["status"]}')
@ -149,6 +271,16 @@ class FirecrawlApp:
self._handle_error(status_response, 'check crawl status')
def _handle_error(self, response, action):
"""
Handle errors from API responses.
Args:
response (requests.Response): The response object from the API request.
action (str): Description of the action that was being performed.
Raises:
Exception: An exception with a message containing the status code and error details from the response.
"""
if response.status_code in [402, 408, 409, 500]:
error_message = response.json().get('error', 'Unknown error occurred')
raise Exception(f'Failed to {action}. Status code: {response.status_code}. Error: {error_message}')