Strip decoded text

src/index.js

@@ -2,8 +2,10 @@
 
 import he from 'he';
 import axios from 'axios';
-import { find } from 'lodash';
-// import striptags from 'striptags';
+import {
+  find
+} from 'lodash';
+import striptags from 'striptags';
 
 export async function getSubtitles({
   videoID,
@@ -12,7 +14,9 @@ export async function getSubtitles({
     videoID: string,
     lang: 'en',
   }) {
-  const { data } = await axios.get(
+  const {
+    data
+  } = await axios.get(
       `https://youtube.com/get_video_info?video_id=${videoID}`
     );
 
@@ -24,17 +28,25 @@ export async function getSubtitles({
 
   const regex = /({"captionTracks":.*isTranslatable":(true|false)}])/;
   const [match] = regex.exec(decodedData);
-  const { captionTracks } = JSON.parse(`${match}}`);
+  const {
+    captionTracks
+  } = JSON.parse(`${match}}`);
 
   const subtitle =
-    find(captionTracks, { vssId: `.${lang}` }) ||
-    find(captionTracks, { vssId: `a.${lang}` });
+    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 {
+    data: transcript
+  } = await axios.get(subtitle.baseUrl);
   const lines = transcript
     .replace('<?xml version="1.0" encoding="utf-8" ?><transcript>', '')
     .replace('</transcript>', '')
@@ -44,21 +56,22 @@ export async function getSubtitles({
       const startRegex = /start="([\d.]+)"/;
       const durRegex = /dur="([\d.]+)"/;
 
-      const fontTag = new RegExp('<'+'font'+'[^><]*>|<.'+'font'+'[^><]*>','g');
       const [, start] = startRegex.exec(line);
       const [, dur] = durRegex.exec(line);
 
       const htmlText = line
         .replace(/<text.+>/, '')
         .replace(/&amp;/gi, '&')
-        .replace(/<\/?[^>]+(>|$)/g, '')
-        .replace(fontTag, '');
+        .replace(/<\/?[^>]+(>|$)/g, '');
 
-      // const strippedText = striptags(htmlText);
+      const decodedText = he.decode(htmlText);
+      const text = striptags(decodedText);
 
-      const text = he.decode(htmlText);
-
-      return { start, dur, text };
+      return {
+        start,
+        dur,
+        text
+      };
     });
 
   return lines;

yarn.lock

@@ -2956,6 +2956,10 @@ strip-json-comments@~2.0.1:
   version "2.0.1"
   resolved "https://registry.yarnpkg.com/strip-json-comments/-/strip-json-comments-2.0.1.tgz#3c531942e908c2697c0ec344858c286c7ca0a60a"
 
+striptags@^3.1.0:
+  version "3.1.0"
+  resolved "https://registry.yarnpkg.com/striptags/-/striptags-3.1.0.tgz#763e534338d9cf542f004a4b1eb099e32d295e44"
+
 supports-color@^2.0.0:
   version "2.0.0"
   resolved "https://registry.yarnpkg.com/supports-color/-/supports-color-2.0.0.tgz#535d045ce6b6363fa40117084629995e9df324c7"