feat: add YouTube segments CLI using yt-dlp

src/cli/downloader.ts

@@ -0,0 +1,176 @@
+import { spawn } from "child_process";
+import { writeFileSync, mkdirSync, existsSync } from "fs";
+import { join } from "path";
+
+export interface DownloadOptions {
+  url: string;
+  outputDir: string;
+  format: string;
+  extractChapters: boolean;
+}
+
+interface Chapter {
+  title: string;
+  start: number;
+  end: number;
+}
+
+async function getVideoInfo(url: string): Promise<{ title: string; chapters: Chapter[] }> {
+  return new Promise((resolve, reject) => {
+    const ytDlp = spawn("yt-dlp", [
+      "--dump-json",
+      "--no-download",
+      url,
+    ]);
+
+    let stdout = "";
+    let stderr = "";
+
+    ytDlp.stdout.on("data", (data) => {
+      stdout += data.toString();
+    });
+
+    ytDlp.stderr.on("data", (data) => {
+      stderr += data.toString();
+    });
+
+    ytDlp.on("close", (code) => {
+      if (code !== 0) {
+        reject(new Error(`yt-dlp failed: ${stderr}`));
+        return;
+      }
+
+      try {
+        const info = JSON.parse(stdout);
+        const chapters: Chapter[] = [];
+
+        if (info.chapters && Array.isArray(info.chapters)) {
+          for (const chapter of info.chapters) {
+            chapters.push({
+              title: chapter.title || `Chapter ${chapters.length + 1}`,
+              start: chapter.start_time || 0,
+              end: chapter.end_time || 0,
+            });
+          }
+        }
+
+        resolve({
+          title: info.title || "video",
+          chapters,
+        });
+      } catch (parseError) {
+        reject(new Error(`Failed to parse video info: ${parseError}`));
+      }
+    });
+
+    ytDlp.on("error", (err) => {
+      reject(new Error(`Failed to run yt-dlp: ${err.message}`));
+    });
+  });
+}
+
+async function downloadSection(
+  url: string,
+  outputPath: string,
+  section: string,
+  format: string
+): Promise<void> {
+  return new Promise((resolve, reject) => {
+    const ytDlp = spawn("yt-dlp", [
+      "-f", format,
+      "--download-sections", section,
+      "-o", outputPath,
+      url,
+    ]);
+
+    let stderr = "";
+
+    ytDlp.stderr.on("data", (data) => {
+      stderr += data.toString();
+    });
+
+    ytDlp.on("close", (code) => {
+      if (code !== 0) {
+        reject(new Error(`yt-dlp failed: ${stderr}`));
+        return;
+      }
+      resolve();
+    });
+
+    ytDlp.on("error", (err) => {
+      reject(new Error(`Failed to run yt-dlp: ${err.message}`));
+    });
+  });
+}
+
+function sanitizeFilename(filename: string): string {
+  return filename
+    .replace(/[^a-zA-Z0-9\s\-_]/g, "")
+    .replace(/\s+/g, "_")
+    .substring(0, 100);
+}
+
+function formatTime(seconds: number): string {
+  const mins = Math.floor(seconds / 60);
+  const secs = Math.floor(seconds % 60);
+  return `${mins}:${secs.toString().padStart(2, "0")}`;
+}
+
+export async function downloadVideoSegments(options: DownloadOptions): Promise<void> {
+  const { url, outputDir, format } = options;
+
+  // Create output directory if it doesn't exist
+  if (!existsSync(outputDir)) {
+    mkdirSync(outputDir, { recursive: true });
+  }
+
+  // Skip chapter extraction if not requested
+  if (!options.extractChapters) {
+    console.log("Downloading full video (chapters disabled)...");
+    const safeTitle = sanitizeFilename("video");
+    const outputPath = join(outputDir, `${safeTitle}.%(ext)s`);
+    await downloadSection(url, outputPath, "*", format);
+    return;
+  }
+
+  // Get video info including chapters
+  console.log("Fetching video information...");
+  const { title, chapters } = await getVideoInfo(url);
+  const safeTitle = sanitizeFilename(title);
+
+  console.log(`Video: ${title}`);
+  console.log(`Found ${chapters.length} chapters\n`);
+
+  if (chapters.length === 0) {
+    console.log("No chapters found. Downloading full video...");
+    const outputPath = join(outputDir, `${safeTitle}.%(ext)s`);
+    await downloadSection(url, outputPath, "*", format);
+    return;
+  }
+
+  // Download each chapter as a separate segment
+  for (let i = 0; i < chapters.length; i++) {
+    const chapter = chapters[i];
+    const segmentNumber = (i + 1).toString().padStart(2, "0");
+    const outputPath = join(outputDir, `${safeTitle}_${segmentNumber}_${sanitizeFilename(chapter.title)}.%(ext)s`);
+    const section = `*${formatTime(chapter.start)}-${formatTime(chapter.end)}`;
+
+    console.log(`[${i + 1}/${chapters.length}] Downloading: ${chapter.title} (${formatTime(chapter.end - chapter.start)})`);
+
+    await downloadSection(url, outputPath, section, format);
+  }
+
+  // Also download the full video
+  console.log("\nDownloading full video...");
+  const fullVideoPath = join(outputDir, `${safeTitle}_full.%(ext)s`);
+  await downloadSection(url, fullVideoPath, "*", format);
+
+  // Save chapter list
+  const chapterListPath = join(outputDir, `${safeTitle}_chapters.txt`);
+  let chapterList = `# ${title}\n\n`;
+  for (const chapter of chapters) {
+    chapterList += `${formatTime(chapter.start)} - ${chapter.title}\n`;
+  }
+  writeFileSync(chapterListPath, chapterList);
+  console.log(`Chapter list saved to: ${chapterListPath}`);
+}