fix: QC-Ratings aus 7 älteren Artikeln entfernt (CHECK 10)
This commit is contained in:
@@ -0,0 +1,31 @@
|
||||
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'<h[23][^>]*>(.*?)</h[23]>', 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/[^"]+)"[^>]*>([^<]+)</a>', 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()
|
||||
Reference in New Issue
Block a user