import pypdf
import re

pdf_path = 'cologne_duesseldorf_data/duesseldorf_innungen.pdf'

def extract_emails_direct():
    try:
        reader = pypdf.PdfReader(pdf_path)
        print(f"PDF matches {len(reader.pages)} pages.")
        
        full_text = ""
        for i, page in enumerate(reader.pages):
            text = page.extract_text()
            full_text += text + "\n"
            print(f"--- Page {i+1} Text Sample (First 200 chars) ---")
            print(text[:200])
            print("------------------------------------------------")
            
        emails = re.findall(r'[\w\.-]+@[\w\.-]+\.\w+', full_text)
        print(f"Total extracted text length: {len(full_text)}")
        print(f"Found {len(emails)} emails.")
        
        for email in emails:
            print(f"Email: {email}")
            # Find context
            idx = full_text.find(email)
            start = max(0, idx - 50)
            end = min(len(full_text), idx + 50 + len(email))
            print(f"Context: {full_text[start:end].replace(chr(10), ' ')}")

    except Exception as e:
        print(f"Error: {e}")

if __name__ == "__main__":
    extract_emails_direct()