Live and Shorts URL Support (#1)

* Add support for live and shorts URL. Add more test coverage.

* Bump version to 1.0.1

.gitignore

@@ -1,7 +1,8 @@
 .DS_Store
 node_modules
 /dist
-repomix*.txt
+coverage/
+repomix-output.txt
 
 # local env files
 .env.local
@@ -23,5 +24,4 @@ yarn-error.log*
 *.sw?
 .editorconfig
 /storybook-static
-.npmrc
-repomix-output.txt
+.npmrc

.prettierignore

@@ -1,4 +1,4 @@
 node_modules/
 dist/
 coverage/
-repomix*.txt
+repomix-output.txt

jest.config.js

@@ -7,4 +7,7 @@ export default {
   transform: {
     '^.+\\.ts$': 'ts-jest',
   },
+  collectCoverage: true,
+  coverageDirectory: 'coverage',
+  coverageReporters: ['text', 'lcov'],
 };

package.json

@@ -1,6 +1,6 @@
 {
   "name": "youtube-transcript-plus",
-  "version": "1.0.0",
+  "version": "1.0.1",
   "description": "Fetch transcript from a youtube video",
   "type": "module",
   "main": "dist/youtube-transcript-plus.js",

src/__tests__/cache/fs-cache.test.ts

@@ -44,3 +44,24 @@ describe('FsCache', () => {
     expect(await cache.get('invalid-key')).toBeNull();
   });
 });
+
+describe('FsCache Expiry', () => {
+  const cacheDir = './test-cache';
+  let cache: FsCache;
+
+  beforeEach(async () => {
+    await fs.mkdir(cacheDir, { recursive: true });
+    cache = new FsCache(cacheDir, 1000); // 1 second TTL
+  });
+
+  afterEach(async () => {
+    await fs.rm(cacheDir, { recursive: true, force: true });
+  });
+
+  it('should return null after the TTL has expired', async () => {
+    await cache.set('key1', 'value1');
+    expect(await cache.get('key1')).toBe('value1');
+    await new Promise((resolve) => setTimeout(resolve, 1100)); // Wait for TTL to expire
+    expect(await cache.get('key1')).toBeNull();
+  });
+});

src/__tests__/cache/in-memory-cache.test.ts

@@ -30,3 +30,18 @@ describe('InMemoryCache', () => {
     expect(await cache.get('key1')).toBeNull();
   });
 });
+
+describe('InMemoryCache Expiry', () => {
+  let cache: InMemoryCache;
+
+  beforeEach(() => {
+    cache = new InMemoryCache(1000); // 1 second TTL
+  });
+
+  it('should return null after the TTL has expired', async () => {
+    await cache.set('key1', 'value1');
+    expect(await cache.get('key1')).toBe('value1');
+    await new Promise((resolve) => setTimeout(resolve, 1100)); // Wait for TTL to expire
+    expect(await cache.get('key1')).toBeNull();
+  });
+});

src/__tests__/index.test.ts

@@ -3,7 +3,10 @@ import {
   YoutubeTranscriptInvalidVideoIdError,
   YoutubeTranscriptDisabledError,
   YoutubeTranscriptNotAvailableLanguageError,
+  YoutubeTranscriptTooManyRequestError,
+  YoutubeTranscriptNotAvailableError,
 } from '../errors';
+import { retrieveVideoId } from '../utils';
 
 describe('YoutubeTranscript', () => {
   it('should fetch transcript successfully', async () => {
@@ -38,3 +41,74 @@ describe('YoutubeTranscript', () => {
     );
   });
 });
+
+describe('retrieveVideoId', () => {
+  it('should return the video ID from a valid YouTube URL', () => {
+    const url = 'https://www.youtube.com/watch?v=dQw4w9WgXcQ';
+    expect(retrieveVideoId(url)).toBe('dQw4w9WgXcQ');
+  });
+
+  it('should return the video ID from a short YouTube URL', () => {
+    const url = 'https://youtu.be/dQw4w9WgXcQ';
+    expect(retrieveVideoId(url)).toBe('dQw4w9WgXcQ');
+  });
+
+  it('should return the video ID from an embedded YouTube URL', () => {
+    const url = 'https://www.youtube.com/embed/dQw4w9WgXcQ';
+    expect(retrieveVideoId(url)).toBe('dQw4w9WgXcQ');
+  });
+
+  it('should return the video ID from a live YouTube URL', () => {
+    const url = 'https://www.youtube.com/live/dQw4w9WgXcQ';
+    expect(retrieveVideoId(url)).toBe('dQw4w9WgXcQ');
+  });
+
+  it('should return the video ID from a YouTube Shorts URL', () => {
+    const url = 'https://youtube.com/shorts/dQw4w9WgXcQ';
+    expect(retrieveVideoId(url)).toBe('dQw4w9WgXcQ');
+  });
+
+  it('should throw an error for an invalid YouTube URL', () => {
+    const url = 'https://www.youtube.com/watch?v=invalid';
+    expect(() => retrieveVideoId(url)).toThrow(YoutubeTranscriptInvalidVideoIdError);
+  });
+
+  it('should throw an error for a non-YouTube URL', () => {
+    const url = 'https://www.google.com';
+    expect(() => retrieveVideoId(url)).toThrow(YoutubeTranscriptInvalidVideoIdError);
+  });
+});
+
+describe('YoutubeTranscript Error Handling', () => {
+  it('should throw YoutubeTranscriptTooManyRequestError when too many requests are made', async () => {
+    const transcriptFetcher = new YoutubeTranscript();
+    const videoId = 'dQw4w9WgXcQ';
+    // Mock a response that indicates too many requests
+    jest.spyOn(global, 'fetch').mockResolvedValueOnce({
+      ok: true,
+      text: () => Promise.resolve('<div class="g-recaptcha"></div>'),
+    } as Response);
+
+    await expect(transcriptFetcher.fetchTranscript(videoId)).rejects.toThrow(
+      YoutubeTranscriptTooManyRequestError,
+    );
+  });
+
+  it('should throw YoutubeTranscriptNotAvailableError when no transcript is available', async () => {
+    const transcriptFetcher = new YoutubeTranscript();
+    const videoId = 'dQw4w9WgXcQ';
+    // Mock a response that indicates no transcript is available
+    jest.spyOn(global, 'fetch').mockResolvedValueOnce({
+      ok: true,
+      status: 404,
+      text: () =>
+        Promise.resolve(
+          '  <div id="player">{"captions":{"playerCaptionsTracklistRenderer":{"visibility":"UNKNOWN"}},"videoDetails"</div>',
+        ),
+    } as Response);
+
+    await expect(transcriptFetcher.fetchTranscript(videoId)).rejects.toThrow(
+      YoutubeTranscriptNotAvailableError,
+    );
+  });
+});

src/constants.ts

@@ -2,6 +2,6 @@ export const DEFAULT_USER_AGENT =
   'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36';
 
 export const RE_YOUTUBE =
-  /(?:youtube\.com\/(?:[^\/]+\/.+\/|(?:v|e(?:mbed)?)\/|.*[?&]v=)|youtu\.be\/)([^"&?\/\s]{11})/i;
+  /(?:v=|\/|v\/|embed\/|watch\?.*v=|youtu\.be\/|\/v\/|e\/|watch\?.*vi?=|\/embed\/|\/v\/|vi?\/|watch\?.*vi?=|youtu\.be\/|\/vi?\/|\/e\/)([a-zA-Z0-9_-]{11})/i;
 
 export const RE_XML_TRANSCRIPT = /<text start="([^"]*)" dur="([^"]*)">([^<]*)<\/text>/g;