import pypdf
import re

pdf_path = 'cologne_duesseldorf_data/duesseldorf_innungen.pdf'

try:
    reader = pypdf.PdfReader(pdf_path)
    text = ""
    for page in reader.pages:
        text += page.extract_text() + "\n"
    
    print(f"Extracted {len(text)} characters.")
    print("--- PREVIEW ---")
    print(text[:1000])
    print("--- END PREVIEW ---")
    
    # Simple regex check for emails
    emails = re.findall(r'[\w\.-]+@[\w\.-]+', text)
    print(f"Found {len(emails)} potential email addresses.")
    
except Exception as e:
    print(f"Error reading PDF: {e}")