Merge pull request #36 from hockyy/feature/34

[#34] Add support to watch youtube video in Miteiru

copy.js

@@ -0,0 +1,9 @@
+const fs = require('fs-extra');
+const path = require('path');
+
+const sourceDir = path.join(__dirname, 'renderer', 'public');
+const destDir = path.join(__dirname, 'app');
+
+fs.copy(sourceDir, destDir)
+  .then(() => console.log('Files copied successfully!'))
+  .catch(err => console.error(err));

main/background.ts

@@ -13,6 +13,7 @@ import {
 import fs from "fs";
 import path from "path";
 import {getTokenizer} from "kuromojin";
+import {getSubtitles} from "./helpers/getSubtitles";
 
 
 const isProd: boolean = process.env.NODE_ENV === 'production';
@@ -118,6 +119,16 @@ if (isProd) {
   ipcMain.handle('tags', (event) => {
     return JMDict.tags;
   })
+  ipcMain.handle('getYoutubeSubtitle', async (event, videoID, lang) => {
+    // Fetching Subtitles
+    try {
+      return await getSubtitles({videoID, lang})
+    } catch (error) {
+      console.error('Error fetching subtitles:', error);
+      return []
+    }
+
+  })
   ipcMain.handle('pickDirectory', async (event) => {
     return await dialog.showOpenDialog({
       properties:
@@ -160,7 +171,7 @@ if (isProd) {
     if (filePath && !canceled) {
       fs.writeFile(filePath, saveData, (err) => {
         if (err) throw err;
-        console.log('The file has been saved!');
+        console.info('The file has been saved!');
       });
     }
 
@@ -271,7 +282,7 @@ if (isProd) {
   getTokenizer({dicPath: path.join(__dirname, 'dict/')}).then(loadedTokenizer => {
     tokenizer = loadedTokenizer;
   }).catch(e => {
-    console.log(e)
+    console.error(e)
   })
   ipcMain.handle('tokenizeUsingKuromoji', async (event, sentence) => {
     return tokenizer.tokenizeForSentence(sentence);

main/helpers/getSubtitles.ts

@@ -0,0 +1,70 @@
+/* @flow */
+
+import axios from 'axios';
+import {find} from 'lodash';
+import {decode} from 'html-entities';
+
+function stripTags(input, allowedTags = [], replacement = '') {
+  // Create a string of allowed tags, joined by '|'
+  let tags = allowedTags.join('|');
+
+  // Create a new RegExp object
+  let regex = new RegExp(`<(?!\/?(${tags})[^>]*)\/?.*?>`, 'g');
+
+  // Replace disallowed tags with replacement string
+  return input.replace(regex, replacement);
+}
+
+export async function getSubtitles({videoID, lang = 'ja'}) {
+  const {data} = await axios.get(
+      `https://youtube.com/watch?v=${videoID}`
+  );
+
+  // * ensure we have access to captions data
+  if (!data.includes('captionTracks'))
+    throw new Error(`Could not find captions for video: ${videoID}`);
+
+  const regex = /({"captionTracks":.*isTranslatable":(true|false)}])/;
+  const [match] = regex.exec(data);
+  const {captionTracks} = JSON.parse(`${match}}`);
+
+  const subtitle =
+      find(captionTracks, {
+        vssId: `.${lang}`,
+      }) ||
+      find(captionTracks, {
+        vssId: `a.${lang}`,
+      }) ||
+      find(captionTracks, ({vssId}) => vssId && vssId.match(`.${lang}`));
+
+  // * ensure we have found the correct subtitle lang
+  if (!subtitle || (subtitle && !subtitle.baseUrl))
+    throw new Error(`Could not find ${lang} captions for ${videoID}`);
+
+  const {data: transcript} = await axios.get(subtitle.baseUrl);
+  return transcript
+  .replace('<?xml version="1.0" encoding="utf-8" ?><transcript>', '')
+  .replace('</transcript>', '')
+  .split('</text>')
+  .filter(line => line && line.trim())
+  .map(line => {
+    const startRegex = /start="([\d.]+)"/;
+    const durRegex = /dur="([\d.]+)"/;
+
+    const [, start] = startRegex.exec(line);
+    const [, dur] = durRegex.exec(line);
+
+    const htmlText = line
+    .replace(/<text.+>/, '')
+    .replace(/&amp;/gi, '&')
+    .replace(/<\/?[^>]+(>|$)/g, '');
+    const decodedText = decode(htmlText);
+    const text = stripTags(decodedText);
+
+    return {
+      start,
+      dur,
+      text,
+    };
+  });
+}