"""Check all GitHub links on live pages"""
import urllib.request
import re

pages = ['entity.html', 'media.html', 'gfil-faq.html', 'about-gfil.html']

for page in pages:
    url = f'https://blog.quant-view.xyz/tools/{page}'
    try:
        r = urllib.request.urlopen(url, timeout=15)
        html = r.read().decode()
        gh_links = re.findall(r'href="(https://github\.com/[^"]+)"', html)
        gh_text = re.findall(r'github\.com/[\w\-/]+', html)
        print(f'\n=== {page} ===')
        print(f'GitHub href links: {len(gh_links)}')
        for link in set(gh_links):
            print(f'  href: {link}')
        print(f'GitHub text refs: {len(gh_text)}')
        for t in set(gh_text):
            print(f'  text: {t}')
        # Also check for liudecai or liudapao
        if 'liudecai' in html:
            for line in html.split('\n'):
                if 'liudecai' in line:
                    print(f'  LIUDECAI: {line.strip()[:200]}')
        if 'liudapao' in html:
            for line in html.split('\n'):
                if 'liudapao' in line:
                    print(f'  LIUDAPAO: {line.strip()[:200]}')
    except Exception as e:
        print(f'{page}: ERROR {e}')