firecrawl 1.2.3__tar.gz → 1.3.0__tar.gz

{firecrawl-1.2.3 → firecrawl-1.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: firecrawl
-Version: 1.2.3
+Version: 1.3.0
 Summary: Python SDK for Firecrawl API
 Home-page: https://github.com/mendableai/firecrawl
 Author: Mendable.ai
@@ -36,7 +36,6 @@ License-File: LICENSE
 Requires-Dist: requests
 Requires-Dist: python-dotenv
 Requires-Dist: websockets
-Requires-Dist: asyncio
 Requires-Dist: nest-asyncio
 
 # Firecrawl Python SDK

{firecrawl-1.2.3 → firecrawl-1.3.0}/firecrawl/__init__.py

@@ -13,7 +13,7 @@ import os
 
 from .firecrawl import FirecrawlApp
 
-__version__ = "1.2.3"
+__version__ = "1.3.0"
 
 # Define the logger for the Firecrawl project
 logger: logging.Logger = logging.getLogger("firecrawl")

{firecrawl-1.2.3 → firecrawl-1.3.0}/firecrawl/firecrawl.py

@@ -13,7 +13,6 @@ import logging
 import os
 import time
 from typing import Any, Dict, Optional, List
-import asyncio
 import json
 
 import requests
@@ -192,6 +191,23 @@ class FirecrawlApp:
             }
         else:
             self._handle_error(response, 'check crawl status')
+    
+    def cancel_crawl(self, id: str) -> Dict[str, Any]:
+        """
+        Cancel an asynchronous crawl job using the Firecrawl API.
+
+        Args:
+            id (str): The ID of the crawl job to cancel.
+
+        Returns:
+            Dict[str, Any]: The response from the cancel crawl request.
+        """
+        headers = self._prepare_headers()
+        response = self._delete_request(f'{self.api_url}/v1/crawl/{id}', headers)
+        if response.status_code == 200:
+            return response.json()
+        else:
+            self._handle_error(response, "cancel crawl job")
 
     def crawl_url_and_watch(self, url: str, params: Optional[Dict[str, Any]] = None, idempotency_key: Optional[str] = None) -> 'CrawlWatcher':
         """
@@ -229,7 +245,7 @@ class FirecrawlApp:
         json_data = {'url': url}
         if params:
             json_data.update(params)
-        
+
         # Make the POST request with the prepared headers and JSON data
         response = requests.post(
             f'{self.api_url}{endpoint}',
@@ -239,7 +255,7 @@ class FirecrawlApp:
         if response.status_code == 200:
             response = response.json()
             if response['success'] and 'links' in response:
-                return response['links']
+                return response
             else:
                 raise Exception(f'Failed to map URL. Error: {response["error"]}')
         else:
@@ -322,6 +338,33 @@ class FirecrawlApp:
             else:
                 return response
         return response
+    
+    def _delete_request(self, url: str,
+                        headers: Dict[str, str],
+                        retries: int = 3,
+                        backoff_factor: float = 0.5) -> requests.Response:
+        """
+        Make a DELETE request with retries.
+
+        Args:
+            url (str): The URL to send the DELETE request to.
+            headers (Dict[str, str]): The headers to include in the DELETE request.
+            retries (int): Number of retries for the request.
+            backoff_factor (float): Backoff factor for retries.
+
+        Returns:
+            requests.Response: The response from the DELETE request.
+
+        Raises:
+            requests.RequestException: If the request fails after the specified retries.
+        """
+        for attempt in range(retries):
+            response = requests.delete(url, headers=headers)
+            if response.status_code == 502:
+                time.sleep(backoff_factor * (2 ** attempt))
+            else:
+                return response
+        return response
 
     def _monitor_job_status(self, id: str, headers: Dict[str, str], poll_interval: int) -> Any:
         """
@@ -435,4 +478,4 @@ class CrawlWatcher:
                 self.dispatch_event('document', doc)
         elif msg['type'] == 'document':
             self.data.append(msg['data'])
-            self.dispatch_event('document', msg['data'])
+            self.dispatch_event('document', msg['data'])

{firecrawl-1.2.3 → firecrawl-1.3.0}/firecrawl.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: firecrawl
-Version: 1.2.3
+Version: 1.3.0
 Summary: Python SDK for Firecrawl API
 Home-page: https://github.com/mendableai/firecrawl
 Author: Mendable.ai
@@ -36,7 +36,6 @@ License-File: LICENSE
 Requires-Dist: requests
 Requires-Dist: python-dotenv
 Requires-Dist: websockets
-Requires-Dist: asyncio
 Requires-Dist: nest-asyncio
 
 # Firecrawl Python SDK

{firecrawl-1.2.3 → firecrawl-1.3.0}/firecrawl.egg-info/requires.txt

@@ -1,5 +1,4 @@
 requests
 python-dotenv
 websockets
-asyncio
 nest-asyncio

{firecrawl-1.2.3 → firecrawl-1.3.0}/pyproject.toml

@@ -12,8 +12,7 @@ dependencies = [
     "requests",
     "python-dotenv",
     "websockets",
-    "asyncio",
-"nest-asyncio"
+    "nest-asyncio"
 ]
 authors = [{name = "Mendable.ai",email = "nick@mendable.ai"}]
 maintainers = [{name = "Mendable.ai",email = "nick@mendable.ai"}]