Skip to content

Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥

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

devin-ai-integration[bot]1919799bed23
diff --git a/apps/python-sdk/firecrawl/__init__.py b/apps/python-sdk/firecrawl/__init__.py
index c66453af3..d27472b63 100644
--- a/apps/python-sdk/firecrawl/__init__.py
+++ b/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")
diff --git a/apps/python-sdk/firecrawl/__tests__/v1/e2e_withAuth/test.py b/apps/python-sdk/firecrawl/__tests__/v1/e2e_withAuth/test.py
index d99ee820c..db7301fe3 100644
--- a/apps/python-sdk/firecrawl/__tests__/v1/e2e_withAuth/test.py
+++ b/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
+
diff --git a/apps/python-sdk/firecrawl/firecrawl.py b/apps/python-sdk/firecrawl/firecrawl.py
index b425cff53..38ed8ace8 100644
--- a/apps/python-sdk/firecrawl/firecrawl.py
+++ b/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: