Floke
e684f33bed
- 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.
28 lines
826 B
Python
28 lines
826 B
Python
|
|
import requests
|
|
from bs4 import BeautifulSoup
|
|
|
|
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)
|
|
|
|
soup = BeautifulSoup(response.content, 'html.parser')
|
|
|
|
print(f"Page Title: {soup.title.string if soup.title else 'No Title'}")
|
|
|
|
print("\n--- All Links (First 50) ---")
|
|
count = 0
|
|
for a in soup.find_all('a', href=True):
|
|
text = a.get_text().strip().replace('\n', ' ')
|
|
href = a['href']
|
|
print(f"[{count}] {text[:30]}... -> {href}")
|
|
count += 1
|
|
if count > 50: break
|
|
|
|
except Exception as e:
|
|
print(f"Error: {e}")
|
|
|