import sys, re, gzip data = sys.stdin.buffer.read() if data[:2] == b'\x1f\x8b': data = gzip.decompress(data) text = data.decode('utf-8', errors='replace') # Find article titles in BGG titles = re.findall(r']*>(.*?)', text, re.DOTALL) for t in titles[:25]: clean = re.sub(r'<[^>]+>', '', t).strip() link = re.search(r'href="([^"]+)"', t) if clean and len(clean) > 10: url = '' if link: u = link.group(1) url = 'https://boardgamegeek.com' + u if u.startswith('/') else u print(f'TITLE: {clean}') if url: print(f'URL: {url}') print() # Also try article/link patterns links = re.findall(r'href="(/blogpost/[^"]+)"[^>]*>([^<]+)', text) for url, title in links[:20]: clean = title.strip() if len(clean) > 10: print(f'BLOG: {clean}') print(f'URL: https://boardgamegeek.com{url}') print()