Clawd BotandClaude Opus 4.6
ca9b510922
- Reset master to upstream/main (16,697 commits) - Overlay 2,271 local-only files (skills, tools, workspace, configs, apps) - Restore IDENTITY.md and USER.md templates - Build verified, gateway running, Discord working Co-Authored-By: Claude Opus 4.6 <[email protected]>
43 lines
1.3 KiB
Python
43 lines
1.3 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Scrapling CLI helper — til brug fra OpenClaw agenter.
|
|
Usage: python3 scrape.py <url> [css_selector]
|
|
"""
|
|
import sys
|
|
import json
|
|
|
|
def main():
|
|
if len(sys.argv) < 2:
|
|
print("Usage: python3 scrape.py <url> [css_selector]")
|
|
sys.exit(1)
|
|
|
|
url = sys.argv[1]
|
|
selector = sys.argv[2] if len(sys.argv) > 2 else None
|
|
|
|
try:
|
|
from scrapling import Fetcher
|
|
except ImportError:
|
|
print("Scrapling ikke installeret. Kør: pip install 'scrapling[ai]' --break-system-packages")
|
|
sys.exit(1)
|
|
|
|
page = Fetcher().get(url, stealthy_headers=True)
|
|
|
|
if selector:
|
|
elements = page.css(selector)
|
|
results = [e.get().extract() for e in elements]
|
|
print(json.dumps(results, ensure_ascii=False, indent=2))
|
|
else:
|
|
# Returner title + meta description + h1/h2 overskrifter
|
|
out = {
|
|
'url': url,
|
|
'status': page.status,
|
|
'title': (page.css('title').get() or '').extract() if page.css('title').get() else '',
|
|
'h1': [e.get().extract() for e in page.css('h1')],
|
|
'h2': [e.get().extract() for e in page.css('h2')][:5],
|
|
'links': [e.get().extract() for e in page.css('a')][:20],
|
|
}
|
|
print(json.dumps(out, ensure_ascii=False, indent=2))
|
|
|
|
if __name__ == '__main__':
|
|
main()
|