YTS scraper/downloader

yts.py

#!/usr/bin/python3

import requests
from bs4 import BeautifulSoup
from sys import argv
from os import getcwd
import subprocess


def ask_yes_no_question(question):
    while True:
        user_response = input(question + " (yes/no): ").strip().lower()
        if user_response == "yes":
            return True
        elif user_response == "no":
            return False
        else:
            print("Please enter 'yes' or 'no'.")


def download_torrent(torrent_url, download_directory):
    # Build the aria2c command with necessary options
    command = [
        'aria2c',
        '--dir', download_directory,  # Specify the download directory
        torrent_url,  # URL of the torrent file or magnet link
    ]

    try:
        # Run the aria2c command
        subprocess.run(command, check=True)
        print("Torrent download completed successfully!")
    except subprocess.CalledProcessError as e:
        print(f"Error: {e}")



def get_movie_info(query):
    # URL with the query parameter
    url = f"https://yts.mx/browse-movies/{query}/all/all/0/latest/0/all"

    movie_info_dict = {}  # Initialize an empty dictionary to store the movie information

    try:
        # Send an HTTP GET request
        response = requests.get(url)

        # Check if the request was successful
        if response.status_code == 200:
            # Parse the HTML content of the page
            soup = BeautifulSoup(response.text, 'html.parser')

            # Find all div elements whose class attribute starts with "browse-movie-wrap"
            movie_wraps = soup.find_all('div', class_=lambda x: x and x.startswith("browse-movie-wrap"))

            # Loop through the movie wraps and extract information
            for movie_wrap in movie_wraps:
                # Find the a tag within the movie wrap
                movie_link = movie_wrap.find('a')

                # Get the href attribute of the a tag
                href = movie_link['href']

                # Find the figure tag under the movie wrap
                figure = movie_wrap.find('figure')

                # Find the img tag under the figure
                img = figure.find('img')

                # Get the src and alt attributes of the img tag
                img_src = img['src']
                img_alt = img['alt']

                # Strip the title and remove "download" from the last part
                img_alt = img_alt.strip().rsplit(" download", 1)[0]

                # Add the title and link to the dictionary
                movie_info_dict[img_alt] = href

            return movie_info_dict

        else:
            print(f"Failed to retrieve data. Status code: {response.status_code}")

    except requests.exceptions.RequestException as e:
        print(f"An error occurred: {e}")

    return {}

def get_movie_torrent_links(movie_link):
    try:
        # Send an HTTP GET request to the movie link
        response = requests.get(movie_link)

        # Check if the request was successful
        if response.status_code == 200:
            # Parse the HTML content of the page
            soup = BeautifulSoup(response.text, 'html.parser')

            # Find all <a> tags whose href attributes start with "https://yts.mx/torrent/download/"
            torrent_links = soup.find_all('a', href=lambda x: x and x.startswith("https://yts.mx/torrent/download/"))

            # Create a list of dictionaries to store the links and their text
            torrent_info_list = []

            # Keep track of encountered torrent links
            encountered_links = set()

            for torrent_link in torrent_links:
                # Get the href and text of the <a> tag
                href = torrent_link['href']
                text = torrent_link.get_text()

                # Check if the link is not a duplicate
                if text != "Download" and href not in encountered_links:
                    # Add the href and text to the list as a dictionary
                    torrent_info_list.append({'torrent': href, 'quality': text})

                    # Add the link to the set of encountered links
                    encountered_links.add(href)

            return torrent_info_list

        else:
            print(f"Failed to retrieve data from {movie_link}. Status code: {response.status_code}")

    except requests.exceptions.RequestException as e:
        print(f"An error occurred: {e}")

    return []

# Example usage:
query = input("Enter a movie query: ")
movies_info = get_movie_info(query)

if not movies_info:
    print("No movies found.")
else:
    # Display a numbered list of movie titles
    for i, movie_title in enumerate(movies_info.keys(), 1):
        print(f"{i} - {movie_title}")

    # Let the user select a movie by entering the corresponding number
    selection = int(input("Enter the number of the movie you want to select: "))

    # Get the selected movie's link
    selected_movie = list(movies_info.values())[selection - 1]

    # Get torrent links for the selected movie
    torrent_links = get_movie_torrent_links(selected_movie)

    if not torrent_links:
        print("No torrent links found for the selected movie.")
    else:
        # Display a numbered list of torrent qualities
        for i, torrent_info in enumerate(torrent_links, 1):
            print(f"{i} - Quality: {torrent_info['quality']}")

        # Let the user select a torrent quality by entering the corresponding number
        quality_selection = int(input("Enter the number of the torrent quality you want to download: "))
        selected_torrent = torrent_links[quality_selection - 1]

        print(f"Selected torrent quality: {selected_torrent['quality']}")
        print(f"Download link: {selected_torrent['torrent']}")
        if ask_yes_no_question("Download this torrent using aria2c?"):
            print("Downloading torrent using aria2c...")
            download_torrent(selected_torrent['torrent'], getcwd())