JimLiu/baoyu-skills / skills/baoyu-youtube-transcript
baoyu-youtube-transcript
VerifiedDownloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面", "视频封面", "video thumbnail", "video cover image", or provides a YouTube URL and wants the transcript/subtitle text or cover image extracted.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.5 KB |
| prompts/speaker-transcript.md | markdown | 4.6 KB |
| scripts/main.test.ts | script | 8.5 KB |
| scripts/main.ts | script | 8.4 KB |
| scripts/shared.ts | script | 3.4 KB |
| scripts/storage.ts | script | 1.9 KB |
| scripts/transcript.ts | script | 13.5 KB |
| scripts/types.ts | script | 2.4 KB |
| scripts/youtube.ts | script | 22.4 KB |
scripts/main.test.ts
View on GitHubimport test from "node:test";
import assert from "node:assert/strict";
import { findTranscript, parseTranscriptJson3, parseTranscriptXml, parseWebVtt, segmentIntoSentences } from "./transcript.ts";
import { buildTranscriptListFromYtDlp, fetchTranscriptWithFallback, resolveVideoSource, selectYtDlpTrack } from "./youtube.ts";
test("selectYtDlpTrack prefers json3 over xml and vtt", () => {
const track = selectYtDlpTrack([
{ ext: "vtt", url: "https://example.com/subs.vtt" },
{ ext: "srv3", url: "https://example.com/subs.srv3" },
{ ext: "json3", url: "https://example.com/subs.json3" },
]);
assert.equal(track?.ext, "json3");
});
test("buildTranscriptListFromYtDlp keeps manual and generated tracks separate", () => {
const transcripts = buildTranscriptListFromYtDlp({
subtitles: {
en: [
{ ext: "json3", url: "https://example.com/en.json3", name: "English" },
],
},
automatic_captions: {
"zh-Hans": [
{ ext: "json3", url: "https://example.com/zh.json3", name: "Chinese (Simplified)" },
],
},
});
assert.equal(transcripts.length, 2);
assert.equal(transcripts[0].isGenerated, false);
assert.equal(transcripts[1].isGenerated, true);
assert.equal(transcripts[0].translationLanguages[0]?.languageCode, "zh-Hans");
const translated = findTranscript(transcripts, ["zh-Hans"], false, false);
assert.equal(translated.languageCode, "zh-Hans");
assert.equal(translated.isGenerated, true);
});
test("parseTranscriptJson3 reads youtube timedtext json3 payloads", () => {
const snippets = parseTranscriptJson3(JSON.stringify({
events: [
{
tStartMs: 80,
dDurationMs: 3120,
segs: [{ utf8: "hello\nworld" }],
},
{
tStartMs: 4000,
dDurationMs: 1800,
segs: [{ utf8: "again" }],
},
],
}));
assert.deepEqual(snippets, [
{ text: "hello world", start: 0.08, duration: 3.12 },
{ text: "again", start: 4, duration: 1.8 },
]);
});
test("parseTranscriptXml reads current timedtext format 3 paragraphs", () => {
const snippets = parseTranscriptXml(`<?xml version="1.0" encoding="utf-8" ?>
<timedtext format="3"><body>
<p t="80" d="3120"><s ac="0">Hello</s><s t="400" ac="0"> world</s></p>
<p t="4000" d="1800">Again & again</p>
</body></timedtext>`);
assert.deepEqual(snippets, [
{ text: "Hello world", start: 0.08, duration: 3.12 },
{ text: "Again & again", start: 4, duration: 1.8 },
]);
});
test("parseWebVtt strips tags and cue settings", () => {
const snippets = parseWebVtt(`WEBVTT
00:00:00.080 --> 00:00:03.200 align:start position:0%
<c.colorE5E5E5>Hello</c> world
00:00:04.000 --> 00:00:05.800
Again
`);
assert.equal(snippets.length, 2);
assert.equal(snippets[0].text, "Hello world");
assert.equal(snippets[0].start, 0.08);
assert.equal(snippets[0].duration, 3.12);
assert.equal(snippets[1].text, "Again");
assert.equal(snippets[1].start, 4);
assert.equal(Number(snippets[1].duration.toFixed(1)), 1.8);
});
test("resolveVideoSource prefers primary InnerTube result before fallback", async () => {
let fallbackCalled = false;
const source = await resolveVideoSource(
"video12345ab",
async () => ({ kind: "innertube", data: { videoDetails: { title: "Primary" } }, transcripts: [] }),
() => {
fallbackCalled = true;
return {
subtitles: {
en: [{ ext: "json3", url: "https://example.com/en.json3", name: "English" }],
},
};
},
() => {}
);
assert.equal(source.kind, "innertube");
assert.equal(fallbackCalled, false);
});
test("resolveVideoSource falls back to yt-dlp only after fallback-eligible errors", async () => {
let fallbackCalled = false;
const source = await resolveVideoSource(
"video12345ab",
async () => {
const error = new Error("Request blocked for video12345ab: bot detected");
(error as Error & { code?: string }).code = "BOT_DETECTED";
throw error;
},
() => {
fallbackCalled = true;
return {
automatic_captions: {
en: [{ ext: "json3", url: "https://example.com/en.json3", name: "English (auto-generated)" }],
},
};
},
() => {}
);
assert.equal(source.kind, "yt-dlp");
assert.equal(fallbackCalled, true);
assert.equal(source.transcripts[0].languageCode, "en");
});
test("fetchTranscriptWithFallback retries with yt-dlp when InnerTube transcript payload is empty", async () => {
const warnings: string[] = [];
let fallbackCalled = false;
const result = await fetchTranscriptWithFallback(
"video12345ab",
{
kind: "innertube",
data: { videoDetails: { title: "Primary" } },
transcripts: [{
language: "English",
languageCode: "en",
isGenerated: false,
isTranslatable: false,
baseUrl: "https://www.youtube.com/api/timedtext?v=video12345ab&lang=en&fmt=json3",
translationLanguages: [],
}],
},
{
languages: ["en"],
translate: "",
excludeGenerated: false,
excludeManual: false,
},
async (info) => {
if (info.baseUrl.includes("youtube.com/api/timedtext")) {
return { snippets: [], language: info.language, languageCode: info.languageCode };
}
return {
snippets: [{ text: "Recovered subtitle", start: 0, duration: 2 }],
language: info.language,
languageCode: info.languageCode,
};
},
async () => {
fallbackCalled = true;
return {
kind: "yt-dlp",
info: { title: "Fallback" },
transcripts: [{
language: "English",
languageCode: "en",
isGenerated: false,
isTranslatable: false,
baseUrl: "https://example.com/subtitles.en.json3",
translationLanguages: [],
}],
};
},
(message) => warnings.push(message),
async (_videoId, _source, transcript) => ({
snippets: [{ text: "Recovered subtitle", start: 0, duration: 2 }],
language: transcript.language,
languageCode: transcript.languageCode,
})
);
assert.equal(fallbackCalled, true);
assert.equal(result.source.kind, "yt-dlp");
assert.equal(result.snippets.length, 1);
assert.equal(result.snippets[0].text, "Recovered subtitle");
assert.match(warnings[0] || "", /Retrying with yt-dlp fallback/);
});
test("fetchTranscriptWithFallback lets yt-dlp download cookie-bound subtitle tracks", async () => {
let directFetches = 0;
let ytDlpFetches = 0;
const result = await fetchTranscriptWithFallback(
"video12345ab",
{
kind: "yt-dlp",
info: { title: "Fallback" },
transcripts: [{
language: "English (auto-generated)",
languageCode: "en",
isGenerated: true,
isTranslatable: false,
baseUrl: "https://www.youtube.com/api/timedtext?expire=signed",
translationLanguages: [],
}],
},
{
languages: ["en"],
translate: "",
excludeGenerated: false,
excludeManual: false,
},
async () => {
directFetches += 1;
throw new Error("HTTP 429 fetching transcript");
},
async () => {
throw new Error("fallback source should not be requested twice");
},
() => {},
async (_videoId, _source, transcript) => {
ytDlpFetches += 1;
return {
snippets: [{ text: "Cookie-authenticated subtitle", start: 0, duration: 2 }],
language: transcript.language,
languageCode: transcript.languageCode,
};
}
);
assert.equal(directFetches, 0);
assert.equal(ytDlpFetches, 1);
assert.equal(result.snippets[0].text, "Cookie-authenticated subtitle");
});
test("segmentIntoSentences preserves spaces between Korean snippets", () => {
const sentences = segmentIntoSentences([
{ text: "저희는", start: 0, duration: 1 },
{ text: "그런 문제점을", start: 1, duration: 1 },
{ text: "해결했습니다.", start: 2, duration: 1 },
]);
assert.equal(sentences[0].text, "저희는 그런 문제점을 해결했습니다.");
});
test("segmentIntoSentences keeps Chinese and Japanese snippets unspaced", () => {
const chinese = segmentIntoSentences([
{ text: "我们", start: 0, duration: 1 },
{ text: "解决了", start: 1, duration: 1 },
{ text: "问题。", start: 2, duration: 1 },
]);
const japanese = segmentIntoSentences([
{ text: "これは", start: 0, duration: 1 },
{ text: "テストです。", start: 1, duration: 1 },
]);
assert.equal(chinese[0].text, "我们解决了问题。");
assert.equal(japanese[0].text, "これはテストです。");
});
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |