Video Sitemap Browser enables you to browse and search video sitemap XML files for titles and meta content, allowing you to conveniently download video from a user-friendly menu.

vsb.py

#!/usr/bin/python3

import json
import os
import readline
import requests
import subprocess
import xml.etree.ElementTree as ET
from rich.console import Console
console = Console()

version = "1.1"
# Fixed bug of crashing if there are no existing sitemaps.
# Now on first run, all sitemaps will be downloaded automatically.

#     https://gist.github.com/av1d/
#     ◍◍ ╭┅┅┅┅┅┅┅┅┅┅┅┅┅┅┅┅┅┅┅┅┅┅┅┅╮
#    ╭┅┅┅╯ ▄       ▄▄▄▄▄    ███   │
#    ┇      █     █     ▀▄  █  █  │
#    ┇ █     █  ▄  ▀▀▀▀▄    █ ▀ ▄ │
#    ┇  █    █   ▀▄▄▄▄▀     █  ▄▀ │
#    ┇   █  █              ███    │
#    ┇    █▐                      │
#    ┇    ▐ ╭Video Sitemap Browser╯
#    ┗┅┅┅┅┅┅╯            by av1d ◍◍
#
#    Enables you to browse and search
#    video sitemap XML files for titles
#    and meta content, allowing you to
#    conveniently download them from a
#    user-friendly menu.
#
#
# You can locate video-sitemap.xml files by searching like this:
#   - https://www.google.com/search?q=%22video-sitemap.xml%22+filetype%3Axml
#   - https://www.google.com/search?q=inurl%3A%22video-sitemap.xml%22
# Or, just try somerandomwebsite.com/video-sitemap.xml and see if they have one.
#
#
# INSTALLATION:
#
# If you are using the download feature, you must install yt-dlp:
#   - https://github.com/yt-dlp/yt-dlp
#
# Install the Python modules:
#     pip install gnureadline requests rich
#
# CONFIGURATION:
#
# This is where the URLs to your sitemaps will go. They're currently
# stored here so they can be updated from within the program. Filenames
# must be unique or will overwrite each other. The format is:
#     URL : local filename
urls = {
    'https://videosite.zzz/video-sitemap.xml': 'videosite-video-sitemap.xml',
    'https://anothervideosite.zzz/video-sitemap.xml': 'anothervideosite-video-sitemap.xml'
}

# That's it! You're done!

def clear_screen():
    os.system('cls' if os.name == 'nt' else 'clear')

def parse_sitemap(file_path):
    tree = ET.parse(file_path)
    root = tree.getroot()

    videos = []
    for url in root.findall('.//{http://www.sitemaps.org/schemas/sitemap/0.9}url'):
        for video in url.findall('.//{http://www.google.com/schemas/sitemap-video/1.1}video'):
            title_elem = video.find('.//{http://www.google.com/schemas/sitemap-video/1.1}title')
            player_loc_elem = video.find('.//{http://www.google.com/schemas/sitemap-video/1.1}player_loc')
            description_elem = video.find('.//{http://www.google.com/schemas/sitemap-video/1.1}description')
            thumbnail_loc_elem = video.find('.//{http://www.google.com/schemas/sitemap-video/1.1}thumbnail_loc')
            tag_elems = video.findall('.//{http://www.google.com/schemas/sitemap-video/1.1}tag')

            title = title_elem.text if title_elem is not None else "No title"
            player_loc = player_loc_elem.text if player_loc_elem is not None else "No player link available"
            description = description_elem.text if description_elem is not None else "No description"
            thumbnail_loc = thumbnail_loc_elem.text if thumbnail_loc_elem is not None else "No thumbnail"
            tags = [tag.text for tag in tag_elems if tag.text]

            videos.append({
                'title': title,
                'player_loc': player_loc,
                'description': description,
                'thumbnail_loc': thumbnail_loc,
                'tags': tags
            })

    return sorted(videos, key=lambda x: x['title'].lower())

def display_titles(videos, start_index, per_page):
    for i, video in enumerate(videos[start_index:start_index+per_page], start=start_index+1):
        console.print(f"[bold]{i}[/bold]. {video['title']}", markup=True, highlight=False)

def search_videos(videos, query):
    return [video for video in videos if query.lower() in video['title'].lower()]

def search_video_meta(videos, query):
    return [video for video in videos if
            (video['description'] != "No description" and query.lower() in video['description'].lower()) or
            any(query.lower() in tag.lower() for tag in video['tags'])]

"""
def download_sitemaps():
    print("Updating sitemaps ...")
    for url, filename in urls.items():
        try:
            response = requests.get(url)
            response.raise_for_status()
            with open(filename, 'wb') as file:
                file.write(response.content)
            print(f"Successfully downloaded and saved {filename}")
            input("\nPress Enter to continue...")
            return True
        except requests.exceptions.RequestException as e:
            print(f"Error downloading {url}: {e}")
            input("\nPress Enter to continue...")
            return False
"""

def download_sitemaps():
    print("Updating sitemaps ...")
    success = True
    for url, filename in urls.items():
        try:
            response = requests.get(url)
            response.raise_for_status()
            with open(filename, 'wb') as file:
                file.write(response.content)
            print(f"Successfully downloaded and saved {filename}")
        except requests.exceptions.RequestException as e:
            print(f"Error downloading {url}: {e}")
            success = False

    input("\nPress Enter to continue...")
    return success


def choose_sitemap():
    while True:
        clear_screen()
        print("Choose sitemap:")
        keys = list(urls.keys())
        for map_num, sitemap_value in enumerate(urls.values(), start=1):
            console.print(f"[bold]{map_num}[/bold]. {sitemap_value}", markup=True, highlight=False)
        choice = input("Enter your choice: ").strip()
        if choice.isdigit() and 1 <= int(choice) <= len(keys):
            return urls[keys[int(choice) - 1]]
        else:
            print("Invalid choice. Please try again.")
            input("\nPress Enter to continue...")

def download_video(url):
    try:
        # Get video info without downloading
        print(f"Fetching video info for: {url}")
        process = subprocess.Popen(['yt-dlp', '-J', '--no-playlist', url],
                                   stdout=subprocess.PIPE, stderr=subprocess.PIPE,
                                   universal_newlines=True)
        stdout, stderr = process.communicate()

        if process.returncode != 0:
            print(f"Error fetching video info: {stderr.strip()}")
            if "404" in stderr:
                print("The video is not available (404 Not Found).")
            return

        try:
            video_info = json.loads(stdout)
        except json.JSONDecodeError:
            print("Error parsing video information. The video might be unavailable.")
            return

        # check if the video is available
        if 'title' in video_info and 'duration' in video_info:
            # video seems to be available, proceed with download
            print(f"Downloading: {video_info['title']}")
            download_process = subprocess.Popen(['yt-dlp', '-P', '.', '--no-playlist', url],
                                                 stdout=subprocess.PIPE, stderr=subprocess.PIPE,
                                                 universal_newlines=True)

            # print download progress
            while True:
                output = download_process.stdout.readline()
                if output == '' and download_process.poll() is not None:
                    break
                if output:
                    print(output.strip())

            if download_process.returncode == 0:
                print(f"Successfully downloaded video: {video_info['title']}")
            else:
                print("Download failed.")
                stderr_output = download_process.stderr.read()
                print(f"Error output during download: {stderr_output.strip()}")
        else:
            print("The video appears to be unavailable or deleted.")

    except FileNotFoundError:
        print("yt-dlp is not installed or not in the system PATH")
    except Exception as e:
        print(f"An unexpected error occurred: {str(e)}")

    input("\nPress Enter to continue...")

def handle_command_history(event):

    line = readline.get_line_buffer()

    if event.keyname == 'up':
        try:
            index = command_history.index(line)
            if index > 0:
                readline.insert_text(command_history[index - 1])
                readline.redisplay()
        except ValueError:
            pass
    elif event.keyname == 'down':
        try:
            index = command_history.index(line)
            if index < len(command_history) - 1:
                readline.insert_text(command_history[index + 1])
                readline.redisplay()
        except ValueError:
            pass

    return readline.parse_and_bind_default_key_bindings(event)

def main():
    file_path = choose_sitemap()
    #videos = parse_sitemap(file_path)
    try:
        videos = parse_sitemap(file_path)
    except:
        print("Sitemaps not found. Downloading...")
        download_sitemaps()
        videos = parse_sitemap(file_path)

    page = 0
    per_page = 10

    command_history = []
    readline.parse_and_bind('up-history: handle_command_history')
    readline.parse_and_bind('down-history: handle_command_history')

    while True:
        clear_screen()
        console.print(f"Video Sitemap Browser - [bold]{file_path}[/bold]")
        print("=" * 40)
        display_titles(videos, page * per_page, per_page)
        console.print("\nCommands: ([bold]↑↓[/bold] recalls command history)")
        console.print("[bold]n[/bold] - Next page")
        console.print("[bold]p[/bold] - Previous page")
        console.print("[bold]s <query>[/bold] - Search video titles", markup=True, highlight=False)
        console.print("[bold]m <query>[/bold] - Search video meta", markup=True, highlight=False)
        console.print("[bold]l <number>[/bold] - Show video player link", markup=True, highlight=False)
        console.print("[bold]d <number>[/bold] - Download video", markup=True, highlight=False)
        console.print("[bold]u[/bold] - Update sitemaps")
        console.print("[bold]c[/bold] - Switch to another sitemap")
        console.print("[bold]q[/bold] - Quit")

        command = input("\nEnter command: ").strip().lower()
        command_history.append(command)

        if command == 'n':
            if (page + 1) * per_page < len(videos):
                page += 1
        elif command == 'p':
            if page > 0:
                page -= 1
        elif command.startswith('l ') or command.startswith('d '):
            try:
                index = int(command.split()[1]) - 1
                if 0 <= index < len(videos):
                    print(f"\nVideo: '{videos[index]['title']}'")
                    print(f"Link: {videos[index]['player_loc']}")
                    if command.startswith('d '):
                        download_video(videos[index]['player_loc'])
                    else:
                        input("\nPress Enter to continue...")
                else:
                    print("Invalid number.")
                    input("\nPress Enter to continue...")
            except ValueError:
                print("Invalid input. Please enter a number.")
                input("\nPress Enter to continue...")
        elif command.startswith('s '):
            query = command[2:]
            search_results = search_videos(videos, query)
            if search_results:
                print(f"\nSearch results for title '{query}':")
                for i, video in enumerate(search_results, start=1):
                    print(f"{i}. {video['title']}")
                input("\nPress Enter to continue...")
            else:
                print(f"No title results found for '{query}'")
                input("\nPress Enter to continue...")
        elif command.startswith('m '):
            query = command[2:]
            search_results = search_video_meta(videos, query)
            if search_results:
                print(f"\nSearch results for metadata '{query}':")
                for i, video in enumerate(search_results, start=1):
                    print(f"{i}. {video['title']}")

                    if query.lower() in video['description'].lower():
                        print(f"   Description Match: {video['description']}")

                    matching_tags = [tag for tag in video['tags'] if query.lower() in tag.lower()]
                    if matching_tags:
                        print(f"   Matching Tags: {', '.join(matching_tags)}")

                input("\nPress Enter to continue...")
            else:
                print(f"No metadata results found for '{query}'")
                input("\nPress Enter to continue...")
        elif command == 'u':
            download_sitemaps()
            videos = parse_sitemap(file_path)
            page = 0
        elif command == 'c':
            file_path = choose_sitemap()
            videos = parse_sitemap(file_path)
            page = 0
        elif command == 'q':
            break
        else:
            print("Invalid command.")
            input("\nPress Enter to continue...")

if __name__ == "__main__":
    main()