firecrawl 2.14.0__tar.gz → 2.16.0__tar.gz

{firecrawl-2.14.0 → firecrawl-2.16.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: firecrawl
-Version: 2.14.0
+Version: 2.16.0
 Summary: Python SDK for Firecrawl API
 Home-page: https://github.com/mendableai/firecrawl
 Author: Mendable.ai

{firecrawl-2.14.0 → firecrawl-2.16.0}/firecrawl/__init__.py

@@ -13,7 +13,7 @@ import os
 
 from .firecrawl import FirecrawlApp, AsyncFirecrawlApp, JsonConfig, ScrapeOptions, ChangeTrackingOptions # noqa
 
-__version__ = "2.14.0"
+__version__ = "2.16.0"
 
 # Define the logger for the Firecrawl project
 logger: logging.Logger = logging.getLogger("firecrawl")

{firecrawl-2.14.0 → firecrawl-2.16.0}/firecrawl/firecrawl.py

@@ -23,8 +23,6 @@ import websockets
 import aiohttp
 import asyncio
 from pydantic import Field
-import ssl
-import certifi
 
 # Suppress Pydantic warnings about attribute shadowing
 warnings.filterwarnings("ignore", message="Field name \"json\" in \"FirecrawlDocument\" shadows an attribute in parent \"BaseModel\"")
@@ -466,6 +464,7 @@ class FirecrawlApp:
             url: str,
             *,
             formats: Optional[List[Literal["markdown", "html", "rawHtml", "content", "links", "screenshot", "screenshot@fullPage", "extract", "json", "changeTracking"]]] = None,
+            headers: Optional[Dict[str, str]] = None,
             include_tags: Optional[List[str]] = None,
             exclude_tags: Optional[List[str]] = None,
             only_main_content: Optional[bool] = None,
@@ -492,6 +491,7 @@ class FirecrawlApp:
         Args:
           url (str): Target URL to scrape
           formats (Optional[List[Literal["markdown", "html", "rawHtml", "content", "links", "screenshot", "screenshot@fullPage", "extract", "json"]]]): Content types to retrieve (markdown/html/etc)
+          headers (Optional[Dict[str, str]]): Custom HTTP headers
           include_tags (Optional[List[str]]): HTML tags to include
           exclude_tags (Optional[List[str]]): HTML tags to exclude
           only_main_content (Optional[bool]): Extract main content only
@@ -520,7 +520,7 @@ class FirecrawlApp:
         Raises:
           Exception: If scraping fails
         """
-        headers = self._prepare_headers()
+        _headers = self._prepare_headers()
 
         # Build scrape parameters
         scrape_params = {
@@ -531,6 +531,8 @@ class FirecrawlApp:
         # Add optional parameters if provided
         if formats:
             scrape_params['formats'] = formats
+        if headers:
+            scrape_params['headers'] = headers
         if include_tags:
             scrape_params['includeTags'] = include_tags
         if exclude_tags:
@@ -586,7 +588,7 @@ class FirecrawlApp:
         # Make request
         response = requests.post(
             f'{self.api_url}/v1/scrape',
-            headers=headers,
+            headers=_headers,
             json=scrape_params,
             timeout=(timeout + 5000 if timeout else None)
         )
@@ -2769,8 +2771,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
             aiohttp.ClientError: If the request fails after all retries.
             Exception: If max retries are exceeded or other errors occur.
         """
-        ssl_context = ssl.create_default_context(cafile=certifi.where())
-        async with aiohttp.ClientSession(ssl=ssl_context) as session:
+        async with aiohttp.ClientSession() as session:
             for attempt in range(retries):
                 try:
                     async with session.request(
@@ -2966,6 +2967,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
             url: str,
             *,
             formats: Optional[List[Literal["markdown", "html", "rawHtml", "content", "links", "screenshot", "screenshot@fullPage", "extract", "json", "changeTracking"]]] = None,
+            headers: Optional[Dict[str, str]] = None,
             include_tags: Optional[List[str]] = None,
             exclude_tags: Optional[List[str]] = None,
             only_main_content: Optional[bool] = None,
@@ -2988,6 +2990,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
         Args:
           url (str): Target URL to scrape
           formats (Optional[List[Literal["markdown", "html", "rawHtml", "content", "links", "screenshot", "screenshot@fullPage", "extract", "json"]]]): Content types to retrieve (markdown/html/etc)
+          headers (Optional[Dict[str, str]]): Custom HTTP headers
           include_tags (Optional[List[str]]): HTML tags to include
           exclude_tags (Optional[List[str]]): HTML tags to exclude
           only_main_content (Optional[bool]): Extract main content only
@@ -3022,7 +3025,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
         # Validate any additional kwargs
         self._validate_kwargs(kwargs, "scrape_url")
 
-        headers = self._prepare_headers()
+        _headers = self._prepare_headers()
 
         # Build scrape parameters
         scrape_params = {
@@ -3033,6 +3036,8 @@ class AsyncFirecrawlApp(FirecrawlApp):
         # Add optional parameters if provided and not None
         if formats:
             scrape_params['formats'] = formats
+        if headers:
+            scrape_params['headers'] = headers
         if include_tags:
             scrape_params['includeTags'] = include_tags
         if exclude_tags:
@@ -3080,7 +3085,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
         response = await self._async_post_request(
             f'{self.api_url}{endpoint}',
             scrape_params,
-            headers
+            _headers
         )
 
         if response.get('success') and 'data' in response:

{firecrawl-2.14.0 → firecrawl-2.16.0}/firecrawl.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: firecrawl
-Version: 2.14.0
+Version: 2.16.0
 Summary: Python SDK for Firecrawl API
 Home-page: https://github.com/mendableai/firecrawl
 Author: Mendable.ai

{firecrawl-2.14.0 → firecrawl-2.16.0}/setup.py

@@ -34,8 +34,7 @@ setup(
         'asyncio',
         'nest-asyncio',
         'pydantic',
-        'aiohttp',
-        'certifi'
+        'aiohttp'
     ],
     python_requires=">=3.8",
     classifiers=[