Floke
601593c65c
- Updated version to v0.3.0 (UI & Backend) to clear potential caching confusion. - Enhanced Impressum scraper to extract VAT ID (Umsatzsteuer-ID). - Implemented 2-Hop scraping strategy: Looks for 'Kontakt' page if Impressum isn't on the start page. - Added VAT ID display to the Legal Data block in Inspector.
35 lines
1.1 KiB
Python
35 lines
1.1 KiB
Python
|
|
import requests
|
|
from bs4 import BeautifulSoup
|
|
from urllib.parse import urljoin
|
|
|
|
url = "https://www.igepa.de/"
|
|
print(f"Fetching {url}...")
|
|
|
|
try:
|
|
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'}
|
|
response = requests.get(url, headers=headers, verify=False, timeout=15)
|
|
print(f"Status: {response.status_code}")
|
|
|
|
soup = BeautifulSoup(response.content, 'html.parser')
|
|
|
|
print("\n--- Searching for Impressum Candidates ---")
|
|
keywords = ["impressum", "imprint", "legal notice", "anbieterkennzeichnung", "rechtliches", "legal", "disclaimer"]
|
|
|
|
found = False
|
|
for a in soup.find_all('a', href=True):
|
|
text = a.get_text().strip().lower()
|
|
href = a['href'].lower()
|
|
|
|
# print(f"Link: '{text}' -> {href}") # Verbose
|
|
|
|
if any(kw in text for kw in keywords) or any(kw in href for kw in keywords):
|
|
print(f"MATCH: Text='{text}' | Href='{href}'")
|
|
found = True
|
|
|
|
if not found:
|
|
print("No matches found.")
|
|
|
|
except Exception as e:
|
|
print(f"Error: {e}")
|