Youtube_transcript_playlist

Youtube transcript playlist

import { YoutubeTranscript } from 'youtube-transcript';
import puppeteer from 'puppeteer';
import fs from 'fs';
import readline from 'readline';

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout
});


rl.question('Veuillez entrer l\'URL de la playlist YouTube : ', async (playlistUrl) => {
  const browser = await puppeteer.launch({ headless: true });
  const page = await browser.newPage();

  await page.goto(playlistUrl, { waitUntil: 'networkidle2' });

  await page.waitForSelector('#wc-endpoint');

  const titlePlaylist = await page.evaluate(() => {
    const title = document.querySelectorAll("#header-description")[2].firstElementChild
    return title.textContent.replaceAll(" ", "_").trim();
  })

  const videos = await page.evaluate(() => {
    const videoData = [];
    
    document.querySelectorAll("#wc-endpoint").forEach(element => {
      const url = element.href; 
      const titleElement = element.querySelector('#video-title'); 
      const title = titleElement ? titleElement.textContent.trim() : 'Titre non trouvé'; 
      videoData.push({ url, title });
    });
    
    return videoData;
  });

  await browser.close();

  const finalDoc = [];

  await Promise.all(videos.map(async (element) => {
    try {
      const response = await YoutubeTranscript.fetchTranscript(element.url);
      let alltext = "";
      response.forEach(text => alltext += `${text.text} `);

      finalDoc.push({ url: element.url, title: element.title, transcription: alltext });
    } catch (error) {
      console.error(`Erreur lors de la récupération de la transcription pour ${element.url}:`, error);
    }
  }));

  const data = JSON.stringify(finalDoc, null, 2); 
  fs.writeFile(`${titlePlaylist}.txt`, data, (err) => {
    if (err) {
      console.error("Erreur lors de l'écriture du fichier", err);
    } else {
      console.log(`Fichier ${titlePlaylist}.txt créé avec succès`);
    }
  });

  rl.close();
});