Transcript Downloader for Youtuber + Parser

parser.py

import os

def search_phrase_in_vtt_files(directory, phrase, output_file):
    found_files = []
    for filename in os.listdir(directory):
        if filename.endswith('.vtt'):
            with open(os.path.join(directory, filename), 'r', encoding='utf-8') as file:
                if phrase in file.read():
                    found_files.append(filename)

    with open(output_file, 'w', encoding='utf-8') as out_file:
        for file in found_files:
            print(f'Found in {file}')
            out_file.write(file + '\n')

if __name__ == "__main__":
    # Directory containing the VTT files
    vtt_directory = './transcripts'

    # Output file to write the names of files containing the phrase
    output_filename = 'found_files.txt'

    # Phrase to search for
    search_phrase = 'SEARCH_PHRASE'

    # Execute the search
    search_phrase_in_vtt_files(vtt_directory, search_phrase, output_filename)
    print(f"Files containing the phrase '{search_phrase}' have been listed in {output_filename}")

transcripts.py

import os
import subprocess
import sys

def install_ytdlp():
    subprocess.check_call([sys.executable, "-m", "pip", "install", "yt-dlp"])

def get_video_ids(channel_url):
    print('Getting the Video IDS')
    command = f"yt-dlp --get-id {channel_url}"
    result = subprocess.run(command, shell=True, capture_output=True, text=True)
    if result.returncode != 0:
        print(f"Error fetching video IDs: {result.stderr}")
        sys.exit(1)
    return result.stdout.split()

def download_transcripts(video_ids):
    for video_id in video_ids:
        print(f'Downloading Transcript for {video_id}')
        command = f"yt-dlp --skip-download --write-auto-sub --sub-lang en https://www.youtube.com/watch?v={video_id}"
        subprocess.run(command, shell=True)

if __name__ == "__main__":
    # # Install yt-dlp if not already installed
    # install_ytdlp()

    # Replace with the actual YouTube channel URL
    channel_url = "https://www.youtube.com/@CHANNEL/videos"

    # Get all video IDs from the channel
    video_ids = get_video_ids(channel_url)

    # Download transcripts of all videos
    download_transcripts(video_ids)