oliver/rss-news
1
0
Fork 0
Code Issues 3 Pull requests Projects Releases 12 Packages Wiki Activity Actions

🔖 Release v1.4.5

Browse source
This commit is contained in:
Oliver 2025-07-07 11:37:22 +02:00
parent 691c9e00b6
commit e7d98dba3a
10 changed files with 1322 additions and 147 deletions
Download patch file Download diff file Expand all files Collapse all files

43
utils/image_extractor.py
View file

@ -1,51 +1,60 @@
# utils/image_extractor.py
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
import logging
def extract_images_with_metadata(article_url):
"""
Versucht, Bilder mit Bildunterschrift und Copyright aus dem Originalartikel zu extrahieren.
Gibt eine Liste mit Dictionaries zurück: {url, alt, copyright_text, copyright_link}
Gibt eine Liste mit Dictionaries zurück: {url, alt, copyright, copyright_url, caption}
"""
images = []
try:
logging.info(f"📷 Extrahiere Bilder von {article_url}")
response = requests.get(article_url, timeout=10)
if response.status_code != 200:
logging.warning(f"Keine gültige Antwort von {article_url} (Status {response.status_code})")
return []
soup = BeautifulSoup(response.content, "html.parser")
images = []
for img_tag in soup.find_all("img"):
src = img_tag.get("src")
if not src:
continue
# Vollständige URL bauen
img_url = urljoin(article_url, src)
alt_text = img_tag.get("alt", "").strip()
# Copyright-Hinweis suchen: z. B. umgebender <figure> oder <div>
copyright_text = ""
copyright_link = ""
copyright_text = "Unbekannt"
copyright_link = article_url
caption = alt_text or "Bild aus Originalartikel"
parent = img_tag.find_parent(["figure", "div"])
if parent:
caption = parent.find("figcaption")
if caption:
copyright_text = caption.get_text(strip=True)
link_tag = caption.find("a")
figcaption = parent.find("figcaption")
if figcaption:
caption = figcaption.get_text(strip=True)
link_tag = figcaption.find("a")
if link_tag and link_tag.has_attr("href"):
copyright_link = link_tag["href"]
copyright_text = link_tag.get_text(strip=True)
images.append({
image_data = {
"url": img_url,
"alt": alt_text or "Bild aus Originalartikel",
"copyright_text": copyright_text or "Unbekannt",
"copyright_link": copyright_link or article_url
})
"alt": alt_text,
"caption": caption or "Kein Bildtitel vorhanden",
"copyright": copyright_text or "Unbekannt",
"copyright_url": copyright_link or article_url
}
images.append(image_data)
logging.info(f"{len(images)} Bilder gefunden bei {article_url}")
return images
except Exception as e:
print(f"[extract_images_with_metadata] Fehler bei {article_url}: {e}")
return []
logging.exception(f"Fehler bei der Bildextraktion aus {article_url}:")
return []