import re
import os
import requests
from time import sleep
from urllib.parse import urlparse

with open('/tmp/db/database.sql', 'r') as file:
   sql_content = file.read()

url_pattern = r'https?://(?:www\.)?abload\.de/(?:\S+?)\.(?:png|jpe?g|gif)'
matches = re.findall(url_pattern, sql_content, re.IGNORECASE)

downloaded_urls = set()

for url in matches:
   try:
       url = url.replace("http://", "https://")
       url = url.replace("image.php?img=", "img/")

       headers = {
           'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:97.0) Gecko/20100101 Firefox/97.0'
       }

       if "/thumb/" in url:
           print(f"Skipping {url} - Contains '/thumb/'")
           continue

       if url in downloaded_urls:
           print(f"Skipping {url} - Already downloaded")
           continue

       if os.path.exists(os.path.join('/tmp/abload/abload-backup', url.split('/')[-1])):
           print(f"Skipping {url} - File already exists")
           continue

       response = requests.get(url, headers=headers, allow_redirects=True)

       if response.status_code == 200 and response.headers.get('Content-Type', '').startswith('image'):
           print(f"Downloading {url}")

           file_extension = urlparse(url).path.split('.')[-1]
           
           with open(f"{url.split('/')[-1]}", 'wb') as file:
               file.write(response.content)

           downloaded_urls.add(url)
           sleep(1)
       else:
           print(f"Skipping {url} - Not an image or failed to fetch. Status code: {response.status_code}")

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