I’m trying to write a script that finds emails from WeTransfer, downloads the attached files and deposits them to a directory on my computer. The code i have detects only one email from WeTransfer, says that the link is invalid and that it failed to extract download link. I’m stumped. Is my email parsing code somehow not correct?

import imaplib
import email
from email.header import decode_header
import requests
from bs4 import BeautifulSoup
import os
import shutil
from urllib.parse import urlparse, parse_qs

# Email credentials and IMAP server configuration for Yahoo Mail
EMAIL = 'xxxxxx.com'
PASSWORD = 'xxxxxx' # Use Yahoo account password or an App Password if you have 2FA enabled
IMAP_SERVER = 'imap.mail.yahoo.com'
IMAP_PORT = 993

# Define the folder to save the files
DOWNLOAD_DIR = '/home/JPW/Downloads'
ARCHIVE_DIR = '/home/JPW/archives'


def extract_download_link(we_transfer_url):
    # Parse the WeTransfer URL
    parsed_url = urlparse(we_transfer_url)
    if parsed_url.hostname == 'wetransfer.com' and parsed_url.path.startswith('/downloads'):
        # Extract the unique ID from the URL
        unique_id = parsed_url.path.split('/')[-1]
        # Construct the download URL using the unique ID
        download_url = f"https://wetransfer.com/api/v4/transfers/{unique_id}/download"
        return download_url
    else:
        print("Invalid WeTransfer URL. Only WeTransfer download links are supported.")
        return None


def download_file(url, download_dir):
    response = requests.get(url)
    if response.status_code == 200:
        filename = os.path.basename(url)
        filepath = os.path.join(download_dir, filename)
        with open(filepath, 'wb') as f:
            f.write(response.content)
        print("File downloaded successfully.")
        return filepath
    else:
        print("Failed to download the file.")
        return None

def move_file(src_path, dest_dir):
    if not os.path.exists(dest_dir):
        os.makedirs(dest_dir)
    shutil.move(src_path, dest_dir)

def get_latest_wetransfer_link():
    mail = imaplib.IMAP4_SSL(IMAP_SERVER, IMAP_PORT)
    mail.login(EMAIL, PASSWORD)
    mail.select('inbox')

    status, messages = mail.search(None, '(FROM "[email protected]")')
    email_ids = messages[0].split()

    if not email_ids:
        print("No mails from Eugene found.")
        return None

    latest_email_id = email_ids[-1]

    status, msg_data = mail.fetch(latest_email_id, '(RFC822)')
    msg = email.message_from_bytes(msg_data[0][1])

    mail.logout()

    for part in msg.walk():
        if part.get_content_type() == 'text/html':
            html_content = part.get_payload(decode=True).decode()
            soup = BeautifulSoup(html_content, 'html.parser')
            all_links = soup.find_all('a', href=True)
            for a in all_links:
                if 'wetransfer.com/downloads' in a['href']:
                    print("WeTransfer link found:", a['href'])
                    return a['href']
    print("No WeTransfer link found in the latest email.")
    return None

if __name__ == "__main__":
    link = get_latest_wetransfer_link()
    if link:
        download_link = extract_download_link(link)  # Calling extract_download_link here
        if download_link:
            downloaded_file = download_file(download_link, DOWNLOAD_DIR)
            if downloaded_file:
                move_file(downloaded_file, ARCHIVE_DIR)
                print(f"File moved to {ARCHIVE_DIR}")
            else:
                print("Failed to download the file.")
        else:
            print("Failed to extract download link.")
    else:
        print("No WeTransfer link found in the latest email.")

Thanks!

Jair-Rohm