feat(python-sdk): add parsePDF parameter support (#1713)

* feat(python-sdk): add parsePDF parameter support

- Add parsePDF field to ScrapeOptions class for Search API usage
- Add parse_pdf parameter to both sync and async scrape_url methods
- Add parameter handling logic to pass parsePDF to API requests
- Add comprehensive tests for parsePDF functionality
- Maintain backward compatibility with existing API

The parsePDF parameter controls PDF processing behavior:
- When true (default): PDF content extracted and converted to markdown
- When false: PDF returned in base64 encoding with flat credit rate

Resolves missing parsePDF support in Python SDK v2.9.0

Co-Authored-By: Micah Stairs <micah@sideguide.dev>

* Update __init__.py

* Update test.py

* Update __init__.py

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Micah Stairs <micah@sideguide.dev>
Co-authored-by: Nicolas <nicolascamara29@gmail.com>

apps/python-sdk/firecrawl/__init__.py

@@ -13,7 +13,7 @@ import os
 
 from .firecrawl import FirecrawlApp, AsyncFirecrawlApp, JsonConfig, ScrapeOptions, ChangeTrackingOptions # noqa
 
-__version__ = "2.9.0"
+__version__ = "2.10.0"
 
 # Define the logger for the Firecrawl project
 logger: logging.Logger = logging.getLogger("firecrawl")

apps/python-sdk/firecrawl/__tests__/v1/e2e_withAuth/test.py

@@ -437,4 +437,29 @@ def test_search_with_invalid_params():
         app.search("test query", {"invalid_param": "value"})
     assert "ValidationError" in str(e.value)
 
+# def test_scrape_url_with_parse_pdf_true():
+#     if TEST_API_KEY:
+#         app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY)
+#         response = app.scrape_url('https://arxiv.org/pdf/astro-ph/9301001.pdf', parse_pdf=True)
+#         assert response is not None
+#         assert 'markdown' in response
+#         assert len(response['markdown']) > 100
+
+# def test_scrape_url_with_parse_pdf_false():
+#     if TEST_API_KEY:
+#         app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY)
+#         response = app.scrape_url('https://arxiv.org/pdf/astro-ph/9301001.pdf', parse_pdf=False)
+#         assert response is not None
+#         assert 'markdown' in response
+#         assert 'h7uKu14adDL6yGfnGf2qycY5uq8kC3OKCWkPxm' in response['markdown']
+
+# def test_scrape_options_with_parse_pdf():
+#     if TEST_API_KEY:
+#         from firecrawl.firecrawl import ScrapeOptions
+#         app = FirecrawlApp(api_url=API_URL, api_key=TEST_API_KEY)
+#         scrape_options = ScrapeOptions(parsePDF=False, formats=['markdown'])
+#         response = app.search("firecrawl", limit=1, scrape_options=scrape_options)
+#         assert response is not None
+#         assert 'data' in response
+
 

apps/python-sdk/firecrawl/firecrawl.py

@@ -160,6 +160,7 @@ class ScrapeOptions(pydantic.BaseModel):
     changeTrackingOptions: Optional[ChangeTrackingOptions] = None
     maxAge: Optional[int] = None
     storeInCache: Optional[bool] = None
+    parsePDF: Optional[bool] = None
 
 class WaitAction(pydantic.BaseModel):
     """Wait action to perform during scraping."""
@@ -465,6 +466,7 @@ class FirecrawlApp:
             remove_base64_images: Optional[bool] = None,
             block_ads: Optional[bool] = None,
             proxy: Optional[Literal["basic", "stealth", "auto"]] = None,
+            parse_pdf: Optional[bool] = None,
             extract: Optional[JsonConfig] = None,
             json_options: Optional[JsonConfig] = None,
             actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction]]] = None,
@@ -538,6 +540,8 @@ class FirecrawlApp:
             scrape_params['blockAds'] = block_ads
         if proxy:
             scrape_params['proxy'] = proxy
+        if parse_pdf is not None:
+            scrape_params['parsePDF'] = parse_pdf
         if extract is not None:
             extract = self._ensure_schema_dict(extract)
             if isinstance(extract, dict) and "schema" in extract:
@@ -2904,6 +2908,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
             remove_base64_images: Optional[bool] = None,
             block_ads: Optional[bool] = None,
             proxy: Optional[Literal["basic", "stealth", "auto"]] = None,
+            parse_pdf: Optional[bool] = None,
             extract: Optional[JsonConfig] = None,
             json_options: Optional[JsonConfig] = None,
             actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction]]] = None,
@@ -2981,6 +2986,8 @@ class AsyncFirecrawlApp(FirecrawlApp):
             scrape_params['blockAds'] = block_ads
         if proxy:
             scrape_params['proxy'] = proxy
+        if parse_pdf is not None:
+            scrape_params['parsePDF'] = parse_pdf
         if extract is not None:
             extract = self._ensure_schema_dict(extract)
             if isinstance(extract, dict) and "schema" in extract: