maciejpi/nordabiz
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

fix: Naprawiono wyciek połączeń HTTP w fix_google_news_images.py

Browse Source 
- Dodano context manager (with) dla sesji requests
- Jawne zamykanie odpowiedzi HTTP (response.close())
- Dodano flush=True do print dla natychmiastowego outputu
- Rozwiązuje problem 725+ otwartych połączeń

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Maciej Pienczyn 2026-01-15 07:40:00 +01:00
parent 07171b46b7
commit af4c0d157a
1 changed files with 26 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
scripts/fix_google_news_images.py
View File

@ -96,26 +96,28 @@ def decode_google_news_url(google_url: str) -> str | None:
# Metoda 2: Podążaj za przekierowaniami
try:
session = requests.Session()
session.headers.update(HEADERS)
# Użyj context manager żeby zamknąć sesję po użyciu
with requests.Session() as session:
session.headers.update(HEADERS)
response = session.get(google_url, timeout=REQUEST_TIMEOUT, allow_redirects=True)
final_url = response.url
response = session.get(google_url, timeout=REQUEST_TIMEOUT, allow_redirects=True)
final_url = response.url
response.close() # Jawne zamknięcie odpowiedzi
# Jeśli wylądowaliśmy na consent.google.com, szukaj URL w parametrach
if 'consent.google.com' in final_url:
parsed = urlparse(final_url)
params = parse_qs(parsed.query)
if 'continue' in params:
continue_url = unquote(params['continue'][0])
# Rekurencyjnie dekoduj
if 'news.google.com' in continue_url:
return decode_google_news_url(continue_url)
return continue_url
# Jeśli wylądowaliśmy na consent.google.com, szukaj URL w parametrach
if 'consent.google.com' in final_url:
parsed = urlparse(final_url)
params = parse_qs(parsed.query)
if 'continue' in params:
continue_url = unquote(params['continue'][0])
# Rekurencyjnie dekoduj
if 'news.google.com' in continue_url:
return decode_google_news_url(continue_url)
return continue_url
# Jeśli to nie jest Google, mamy oryginalny URL
if 'google.com' not in final_url:
return final_url
# Jeśli to nie jest Google, mamy oryginalny URL
if 'google.com' not in final_url:
return final_url
except Exception as e:
pass
@ -126,10 +128,12 @@ def decode_google_news_url(google_url: str) -> str | None:
def extract_og_image(url: str) -> str | None:
"""Pobierz og:image z podanej strony."""
try:
response = requests.get(url, headers=HEADERS, timeout=REQUEST_TIMEOUT)
response.raise_for_status()
# Użyj context manager i zamknij połączenie
with requests.get(url, headers=HEADERS, timeout=REQUEST_TIMEOUT, stream=False) as response:
response.raise_for_status()
html_content = response.text
soup = BeautifulSoup(response.text, 'html.parser')
soup = BeautifulSoup(html_content, 'html.parser')
# Szukaj og:image
og_image = soup.find('meta', property='og:image')
@ -200,10 +204,10 @@ def main():
}
for i, news in enumerate(news_items, 1):
print(f"[{i}/{len(news_items)}] {news.title[:55]}...")
print(f"[{i}/{len(news_items)}] {news.title[:55]}...", flush=True)
# Dekoduj URL Google News
print(f" → Dekodowanie URL...")
print(f" → Dekodowanie URL...", flush=True)
original_url = decode_google_news_url(news.url)
if not original_url: