chore: first commit

.babelrc

@@ -0,0 +1,7 @@
+{
+  "presets": [
+    ["env", { "targets": { "node": "6" } }], 
+    "flow",
+    "stage-0"
+  ]
+}

.eslintrc.js

@@ -0,0 +1,3 @@
+module.exports = {
+  extends: 'algolia/flowtype'
+}

.gitignore

@@ -0,0 +1,5 @@
+node_modules
+dist
+
+*.log
+.DS_Store

README.md

@@ -0,0 +1,42 @@
+# Youtube Captions Scrapper
+
+> Scrap youtube user defined and auto-generated captions
+
+## Installation
+
+* `> npm install -S youtube-captions-scrapper` OR
+* `> yarn add youtube-captions-scrapper`
+
+## Usage
+
+```js
+// ES6 / TypeScript
+import { getSubtitles } from 'youtube-captions-scrapper';
+
+getSubtitles({
+  videoID: 'XXXXX', // youtube video id
+  lang: 'fr' // default: `en`
+}).then(captions => {
+  console.log(captions);
+});
+
+// ES5
+var getSubtitles = require('youtube-captions-scrapper').getSubtitles;
+
+getSubtitles({
+  videoID: 'XXXXX', // youtube video id
+  lang: 'fr' // default: `en`
+}).then(function(captions) {
+  console.log(captions);
+});
+```
+
+Captions will be an array of object of this format:
+
+```js
+{
+  "start": Number,
+  "dur": Number,
+  "text": String
+}
+```

package.json

@@ -0,0 +1,45 @@
+{
+  "name": "youtube-captions-scrapper",
+  "version": "1.0.0",
+  "description": "Scrap youtube auto-generated captions",
+  "main": "dist/index.js",
+  "author": {
+    "name": "Algolia, Inc.",
+    "url": "https://www.algolia.com"
+  },
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/algolia/youtube-captions-scrapper.git"
+  },
+  "homepage": "https://github.com/algolia/youtube-captions-scrapper",
+  "bugs": {
+    "url": "https://github.com/algolia/youtube-captions-scrapper/issues"
+  },
+  "license": "MIT",
+  "scripts": {
+    "build": "rm -rf dist && babel src -d dist",
+    "prepublish": "npm run build"
+  },
+  "devDependencies": {
+    "babel-cli": "^6.26.0",
+    "babel-eslint": "^8.0.2",
+    "babel-preset-env": "^1.6.1",
+    "babel-preset-flow": "^6.23.0",
+    "babel-preset-stage-0": "^6.24.1",
+    "babel-watch": "^2.0.7",
+    "eslint": "^4.11.0",
+    "eslint-config-algolia": "^12.0.0",
+    "eslint-config-prettier": "^2.8.0",
+    "eslint-plugin-flowtype": "^2.39.1",
+    "eslint-plugin-import": "^2.8.0",
+    "eslint-plugin-prettier": "^2.3.1",
+    "flow-bin": "^0.59.0",
+    "flow-typed": "^2.2.3",
+    "prettier": "^1.8.2"
+  },
+  "dependencies": {
+    "axios": "^0.17.1",
+    "he": "^1.1.1",
+    "lodash": "^4.17.4"
+  }
+}

src/index.js

@@ -0,0 +1,60 @@
+/* @flow */
+
+import he from 'he';
+import axios from 'axios';
+import { find } from 'lodash';
+
+export async function getSubtitles({
+  videoID,
+  lang = 'en',
+}: {
+  videoID: string,
+  lang: 'en',
+}) {
+  const { data } = await axios.get(
+    `https://youtube.com/get_video_info?video_id=${videoID}`
+  );
+
+  const decodedData = decodeURIComponent(data);
+
+  // * ensure we have access to captions data
+  if (!decodedData.includes('captionTracks'))
+    throw new Error(`Could not find captions for video: ${videoID}`);
+
+  const regex = /({"captionTracks":.*isTranslatable":(true|false)}])/;
+  const [match] = regex.exec(decodedData);
+  const { captionTracks } = JSON.parse(`${match}}`);
+
+  const subtitle =
+    find(captionTracks, { vssId: `.${lang}` }) ||
+    find(captionTracks, { vssId: `a.${lang}` });
+
+  // * ensure we have found the correct subtitle lang
+  if (!subtitle || (subtitle && !subtitle.baseUrl))
+    throw new Error(`Could not find ${lang} captions for ${videoID}`);
+
+  const { data: transcript } = await axios.get(subtitle.baseUrl);
+  const lines = transcript
+    .replace('<?xml version="1.0" encoding="utf-8" ?><transcript>', '')
+    .replace('</transcript>', '')
+    .split('</text>')
+    .filter(line => line && line.trim())
+    .map(line => {
+      const startRegex = /start="([\d.]+)"/;
+      const durRegex = /dur="([\d.]+)"/;
+
+      const [, start] = startRegex.exec(line);
+      const [, dur] = durRegex.exec(line);
+
+      const htmlText = line
+        .replace(/<text.+>/, '')
+        .replace(/&amp;/gi, '&')
+        .replace(/<\/?[^>]+(>|$)/g, '');
+
+      const text = he.decode(htmlText);
+
+      return { start, dur, text };
+    });
+
+  return lines;
+}