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

fix: pdf processing to target only css_selector, thereby give users a choice to discard unnecssary element from page in pdf generated

Browse Source
This commit is contained in:
Aravind Karnam
2025-12-18 16:32:16 +05:30
parent a87e8c1c9e
commit d5a0866e03
1 changed files with 47 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
crawl4ai/async_crawler_strategy.py
View File

@@ -989,8 +989,53 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
mhtml_data = None mhtml_data = None
if config.pdf: if config.pdf:
pdf_data = await self.export_pdf(page) if config.css_selector:
# Extract content with styles and fixed image URLs
content_with_styles = await page.evaluate(f"""
() => {{
const element = document.querySelector("{config.css_selector}");
const clone = element.cloneNode(true);
// Fix all image URLs to absolute
clone.querySelectorAll('img').forEach(img => {{
if (img.src) img.src = img.src; // This converts to absolute URL
}});
// Get all styles
const styles = Array.from(document.styleSheets)
.map(sheet => {{
try {{
return Array.from(sheet.cssRules).map(rule => rule.cssText).join('\\n');
}} catch(e) {{
return '';
}}
}}).join('\\n');
return {{
html: clone.outerHTML,
styles: styles,
baseUrl: window.location.origin
}};
}}
""")
# Create page with base URL for relative resources
temp_page = await context.new_page()
await temp_page.goto(content_with_styles['baseUrl']) # Set the base URL
await temp_page.set_content(f"""
<html>
<head>
<base href="{content_with_styles['baseUrl']}">
<style>{content_with_styles['styles']}</style>
</head>
<body>{content_with_styles['html']}</body>
</html>
""")
pdf_data = await self.export_pdf(temp_page)
await temp_page.close()
else:
pdf_data = await self.export_pdf(page)
if config.capture_mhtml: if config.capture_mhtml:
mhtml_data = await self.capture_mhtml(page) mhtml_data = await self.capture_mhtml(page)