Get YouTube captions
Building on Sergiu Mare's suggestion, I wrote an encapsulated function that can return the captions in the console.
This is written in pure JavaScript (ES6) and you can test it out below, or you can copy everything below and paste it in the console of any video that has captions.
Updated version
OOP approach
const main = async () => {
const
defaultId = 'fJ9rUzIMcZQ', /* Queen – Bohemian Rhapsody */
json = await YouTubeCaptionUtil
.fetchCaptions(YouTubeCaptionUtil.videoId() || defaultId),
csv = CsvUtil.fromJson(json);
console.log(csv);
};
class YouTubeCaptionUtil {
static async fetchCaptions(videoId, options) {
const
opts = { ...YouTubeCaptionUtil.defaultOptions, ...options },
response = await fetch(YouTubeCaptionUtil.__requestUrl(videoId, opts)),
json = await response.json();
return YouTubeCaptionUtil.__parseTranscript(json);
}
static videoId() {
const video_id = window.location.search.split('v=')[1];
if (video_id != null) {
const ampersandPosition = video_id.indexOf('&');
if (ampersandPosition != -1) {
return video_id.substring(0, ampersandPosition);
}
}
return null;
}
static __requestUrl(videoId, { baseUrl, languageId }) {
return `${baseUrl}?lang=${languageId}&v=${videoId}&fmt=json3`;
}
static __parseTranscript({events}) {
return events.map(({tStartMs, dDurationMs, segs: [{utf8}]}) => ({
start: YouTubeCaptionUtil.__formatTime(tStartMs),
dur: YouTubeCaptionUtil.__formatTime(dDurationMs),
text: utf8
}));
}
static __formatTime(seconds) {
const date = new Date(null);
date.setSeconds(seconds);
return date.toISOString().substr(11, 8);
};
}
YouTubeCaptionUtil.defaultOptions = {
baseUrl: 'https://video.google.com/timedtext',
languageId: 'en'
};
class CsvUtil {
static fromJson(json, options) {
const
opts = { ...CsvUtil.defaultOptions, ...options },
keys = Object.keys(json[0]).filter(key =>
opts.ignoreKeys.indexOf(key) === -1),
lines = [];
if (opts.includeHeader) lines.push(keys.join(opts.delimiter));
return lines.concat(json
.map(entry => keys.map(key => entry[key]).join(opts.delimiter)))
.join('\n');
}
}
CsvUtil.defaultOptions = {
includeHeader: false,
ignoreKeys: ['dur'],
delimiter: '\t'
};
main();.as-console-wrapper { top: 0; max-height: 100% !important; }Functional approach
const main = async() => {
const defaultId = 'fJ9rUzIMcZQ'; // Queen – Bohemian Rhapsody (default ID)
const json = await loadYouTubeSubtitles(getYouTubeVideoId() || defaultId);
const csv = jsonToCsv(json, {
includeHeader: false,
ignoreKeys: ['dur'],
delimiter: '\t',
});
console.log(csv);
};
const parseTranscript = ({ events }) => {
return events.map(({ tStartMs, dDurationMs, segs: [{ utf8 }] }) => ({
start: formatTime(tStartMs),
dur: formatTime(dDurationMs),
text: utf8
}));
};
const formatTime = (seconds) => {
let date = new Date(null);
date.setSeconds(seconds);
return date.toISOString().substr(11, 8);
};
const getYouTubeVideoId = () => {
var video_id = window.location.search.split('v=')[1];
if (video_id != null) {
var ampersandPosition = video_id.indexOf('&');
if (ampersandPosition != -1) {
return video_id.substring(0, ampersandPosition);
}
}
return null;
};
const loadYouTubeSubtitles = async(videoId, options) => {
options = Object.assign({
baseUrl: 'https://video.google.com/timedtext',
languageId: 'en',
}, options || {});
const requestUrl = `${options.baseUrl}?lang=${options.languageId}&v=${videoId}&fmt=json3`;
const response = await fetch(requestUrl);
const json = await response.json();
return parseTranscript(json);
};
const jsonToCsv = (json, options) => {
options = Object.assign({
includeHeader: true,
delimiter: ',',
ignoreKeys: []
}, options || {});
let keys = Object.keys(json[0]).filter(key => options.ignoreKeys.indexOf(key) === -1);
let lines = [];
if (options.includeHeader) {
lines.push(keys.join(options.delimiter));
}
return lines.concat(json
.map(entry => keys.map(key => entry[key]).join(options.delimiter)))
.join('\n');
};
main();.as-console-wrapper { top: 0; max-height: 100% !important; }Original response
This response creates an XMLHttpRequest.
loadYouTubeSubtitles((getYouTubeVideoId() || 'fJ9rUzIMcZQ'), {
callbackFn : function(json) {
console.log(jsonToCsv(json, {
includeHeader : false,
ignoreKeys : [ 'dur' ],
delimiter : '\t',
}));
}
}); // Queen – Bohemian Rhapsody (default ID)
function getYouTubeVideoId() {
var video_id = window.location.search.split('v=')[1];
if (video_id != null) {
var ampersandPosition = video_id.indexOf('&');
if (ampersandPosition != -1) {
return video_id.substring(0, ampersandPosition);
}
}
return null;
}
function loadYouTubeSubtitles(videoId, options) {
options = Object.assign({
baseUrl : 'https://video.google.com/timedtext',
languageId : 'en',
callbackFn : function(json) { console.log(json); } // Default
}, options || {});
// https://stackoverflow.com/a/9609450/1762224
var decodeHTML = (function() {
let el = document.createElement('div');
function __decode(str) {
if (str && typeof str === 'string') {
str = str.replace(/<script[^>]*>([\S\s]*?)<\/script>/gmi, '')
.replace(/<\/?\w(?:[^"'>]|"[^"]*"|'[^']*')*>/gmi, '');
el.innerHTML = str;
str = el.textContent;
el.textContent = '';
}
return str;
}
removeElement(el); // Clean-up
return __decode;
})();
function removeElement(el) {
el && el.parentNode && el.parentNode.removeChild(el);
}
function parseTranscriptAsJSON(xml) {
return [].slice.call(xml.querySelectorAll('transcript text'))
.map(text => ({
start : formatTime(Math.floor(text.getAttribute('start'))),
dur : formatTime(Math.floor(text.getAttribute('dur'))),
text : decodeHTML(text.textContent).replace(/\s+/g, ' ')
}));
}
function formatTime(seconds) {
let date = new Date(null);
date.setSeconds(seconds);
return date.toISOString().substr(11, 8);
}
let xhr = new XMLHttpRequest();
xhr.open('POST', `${options.baseUrl}?lang=${options.languageId}&v=${videoId}`, true);
xhr.responseType = 'document';
xhr.onload = function() {
if (this.status >= 200 && this.status < 400) {
options.callbackFn(parseTranscriptAsJSON(this.response));
} else {
console.log('Error: ' + this.status);
}
};
xhr.onerror = function() {
console.log('Error!');
};
xhr.send();
}
function jsonToCsv(json, options) {
options = Object.assign({
includeHeader : true,
delimiter : ',',
ignoreKeys : []
}, options || {});
let keys = Object.keys(json[0]).filter(key => options.ignoreKeys.indexOf(key) === -1);
let lines = [];
if (options.includeHeader) { lines.push(keys.join(options.delimiter)); }
return lines.concat(json
.map(entry => keys.map(key => entry[key]).join(options.delimiter)))
.join('\n');
}.as-console-wrapper { top: 0; max-height: 100% !important; }UPDATES: The URL from google stopped working. This approach is paused at the moment.
Solution: How I managed to get the captions from a youtube video is by making a simple request to this url https://video.google.com/timedtext?lang={LANG}&v={videoId}
I have tried to use the Youtube API v3 but at the moment it doesn't work. When you do a request with the Youtube API v3 on a certain video you need that the person which uploaded the video to approve the caption's download, if not you'll have a 403 error in the console. It's normal to have the error, the server doesn't receive the approval so it returns an error.
You can download the captions from your own video with the Youtube API v3.
Something similar to this will do the job. The response will come in an XML format:
$.ajax({
type: "POST",
url: "https://video.google.com/timedtext?lang=en&v=5MgBikgcWnY"
}).done(function (response) {
console.log(response);
}).fail(function (response) {
console.log();
});