ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs + fix: Update example for full page screenshot & PDF export. Fix the bug Error: crawl4ai.async_webcrawler.AsyncWebCrawler.aprocess_html() got multiple values for keyword argument - for screenshot param. https://github.com/unclecode/crawl4ai/issues/822#issuecomment-2732602118

Browse Source
This commit is contained in:
Aravind Karnam
2025-03-18 17:20:24 +05:30
parent 529a79725e
commit 4359b12003
2 changed files with 12 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
crawl4ai/async_webcrawler.py
View File

@@ -398,7 +398,7 @@ class AsyncWebCrawler:
html=html,
extracted_content=extracted_content,
config=config, # Pass the config object instead of individual parameters
screenshot=screenshot_data,
screenshot_data=screenshot_data,
pdf_data=pdf_data,
verbose=config.verbose,
is_raw_html=True if url.startswith("raw:") else False,
@@ -482,7 +482,7 @@ class AsyncWebCrawler:
html: str,
extracted_content: str,
config: CrawlerRunConfig,
screenshot: str,
screenshot_data: str,
pdf_data: str,
verbose: bool,
**kwargs,
@@ -495,7 +495,7 @@ class AsyncWebCrawler:
html: Raw HTML content
extracted_content: Previously extracted content (if any)
config: Configuration object controlling processing behavior
screenshot: Screenshot data (if any)
screenshot_data: Screenshot data (if any)
pdf_data: PDF data (if any)
verbose: Whether to enable verbose logging
**kwargs: Additional parameters for backwards compatibility
@@ -620,10 +620,6 @@ class AsyncWebCrawler:
params={"url": _url, "timing": time.perf_counter() - t1},
)
# Handle screenshot and PDF data
screenshot_data = None if not screenshot else screenshot
pdf_data = None if not pdf_data else pdf_data
# Apply HTML formatting if requested
if config.prettiify:
cleaned_html = fast_format_html(cleaned_html)