extract_email_content.py

import email
import os
from email import policy
from email.parser import BytesParser

def extract_email_content(eml_file):
    """Extract plain text content from email file."""
    with open(eml_file, 'rb') as f:
        msg = BytesParser(policy=policy.default).parse(f)
    
    # Get plain text content
    if msg.is_multipart():
        for part in msg.iter_parts():
            if part.get_content_type() == 'text/plain':
                return part.get_content()
    else:
        if msg.get_content_type() == 'text/plain':
            return msg.get_content()
    
    return None

def process_emails():
    """Process all .eml files and create markdown files."""
    # Get all .eml files in current directory
    eml_files = [f for f in os.listdir('.') if f.endswith('.eml')]
    
    for eml_file in eml_files:
        # Extract content
        content = extract_email_content(eml_file)
        if content:
            # Create markdown filename
            md_filename = os.path.splitext(eml_file)[0] + '.md'
            
            # Write content to markdown file
            with open(md_filename, 'w', encoding='utf-8') as f:
                f.write(content)
            
            print(f"Processed: {eml_file} -> {md_filename}")

if __name__ == '__main__':
    process_emails()