Fix: Corrige mensagem de erro de IP bloqueado no VideoMind quando o vídeo simplesmente não possui legendas

2026-06-05 20:56:39 +00:00
parent 7a2ba56699
commit 281005a8bc
1086 changed files with 46356 additions and 7 deletions
@@ -0,0 +1,80 @@
+/* @flow */
+
+import he from 'he';
+import axios from 'axios';
+import { find } from 'lodash';
+import striptags from 'striptags';
+
+const fetchData =
+  typeof fetch === 'function'
+    ? async function fetchData(url) {
+        const response = await fetch(url);
+        return await response.text();
+      }
+    : async function fetchData(url) {
+        const { data } = await axios.get(url);
+        return data;
+      };
+
+export async function getSubtitles({
+  videoID,
+  lang = 'en',
+}: {
+  videoID: string,
+  lang: 'en' | 'de' | 'fr' | void,
+}) {
+  const data = await fetchData(
+    `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":(\[.*?\])/;
+  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 ${videoID}`);
+
+  const transcript = await fetchData(subtitle.baseUrl);
+  const lines = transcript
+    .replace('<?xml version="1.0" encoding="utf-8" ?><transcript>', '')
+    .replace('</transcript>', '')
+    .split('</text>')
+    .filter(line => line && line.trim())
+    .map(line => {
+      const startRegex = /start="([\d.]+)"/;
+      const durRegex = /dur="([\d.]+)"/;
+
+      const [, start] = startRegex.exec(line);
+      const [, dur] = durRegex.exec(line);
+
+      const htmlText = line
+        .replace(/<text.+>/, '')
+        .replace(/&amp;/gi, '&')
+        .replace(/<\/?[^>]+(>|$)/g, '');
+
+      const decodedText = he.decode(htmlText);
+      const text = striptags(decodedText);
+
+      return {
+        start,
+        dur,
+        text,
+      };
+    });
+
+  return lines;
+}