Download links

link_downloader.py

import requests
import os
import time
from urllib.parse import urlparse
from cvs import cvs

# Fake user agent to mimic a real browser
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
}


# Directory where files will be saved
download_directory = "downloaded_files"

# Create the download directory if it doesn't exist
if not os.path.exists(download_directory):
    os.makedirs(download_directory)
    print(f"Created directory: {download_directory}")

print(
    f"Attempting to download files to: {os.path.abspath(download_directory)}")

for url in cvs:
    try:
        # Parse the URL to get the filename
        parsed_url = urlparse(url)
        # Get the last part of the path, which should be the filename
        filename = os.path.basename(parsed_url.path)

        # If the filename is empty (e.g., URL ends with a slash), try to generate one
        if not filename:
            # A simple fallback: use a hash or a generic name
            filename = f"downloaded_file_{abs(hash(url))}.pdf"
            print(
                f"Warning: Could not determine filename from URL '{url}'. Using '{filename}'."
            )

        file_path = os.path.join(download_directory, filename)

        # Check if the file already exists
        if os.path.exists(file_path):
            print(
                f"Skipping: File '{filename}' already exists at '{file_path}'."
            )
            continue

        print(f"Downloading: {url} to {file_path}")

        # Send a GET request to the URL with SSL verification disabled for problematic certificates
        response = requests.get(url, stream=True, verify=False, headers=headers)
        response.raise_for_status(
        )  # Raise an HTTPError for bad responses (4xx or 5xx)

        # Open the file in binary write mode and save the content
        with open(file_path, 'wb') as f:
            for chunk in response.iter_content(chunk_size=8192):
                f.write(chunk)

        print(f"Successfully downloaded: {filename}")

    except requests.exceptions.SSLError as e:
        print(f"SSL Certificate error downloading {url}: {e}")
    except requests.exceptions.ConnectionError as e:
        print(f"Connection error downloading {url}: {e}")
    except requests.exceptions.RequestException as e:
        print(f"Request error downloading {url}: {e}")
    except Exception as e:
        print(f"An unexpected error occurred for {url}: {e}")
    
    # Add a 1-second timeout between requests
    time.sleep(1)

print("\nDownload process completed.")