feat: add weixin article download adapter & abstract download helpers (#280)

- New: src/clis/weixin/download.ts — WeChat article to Markdown adapter
- New: src/download/article-download.ts — shared article download helper
  (TurndownService, image localization, frontmatter, customizable labels)
- New: src/download/media-download.ts — shared media download helper
  (batch download, ProgressTracker, yt-dlp routing, auto cookie export)
- Refactor: migrate zhihu/download to use downloadArticle()
- Refactor: migrate xiaohongshu/download to use downloadMedia()
- Refactor: migrate twitter/download to use downloadMedia()
- Refactor: migrate bilibili/download to use downloadMedia()
- Docs: add weixin to README, README.zh-CN, download docs, adapter docs

Author: jackwener

README.md

@@ -115,6 +115,7 @@ Run `opencli list` for the live registry.
 | **apple-podcasts** | `search` `episodes` `top` | Public |
 | **xiaoyuzhou** | `podcast` `podcast-episodes` `episode` | Public |
 | **zhihu** | `hot` `search` `question` `download` | Browser |
+| **weixin** | `download` | Browser |
 | **youtube** | `search` `video` `transcript` | Browser |
 | **boss** | `search` `detail` `recommend` `joblist` `greet` `batchgreet` `send` `chatlist` `chatmsg` `invite` `mark` `exchange` `resume` `stats` | Browser |
 | **coupang** | `search` `add-to-cart` | Browser |
@@ -192,6 +193,7 @@ OpenCLI supports downloading images, videos, and articles from supported platfor
 | **bilibili** | Videos | Requires `yt-dlp` installed |
 | **twitter** | Images, Videos | Downloads from user media tab or single tweet |
 | **zhihu** | Articles (Markdown) | Exports articles with optional image download |
+| **weixin** | Articles (Markdown) | Exports WeChat Official Account articles |
 
 ### Prerequisites
 
@@ -225,6 +227,9 @@ opencli zhihu download "https://zhuanlan.zhihu.com/p/xxx" --output ./zhihu
 
 # Export with local images
 opencli zhihu download "https://zhuanlan.zhihu.com/p/xxx" --download-images
+
+# Export WeChat article to Markdown
+opencli weixin download --url "https://mp.weixin.qq.com/s/xxx" --output ./weixin
 ```
 
 

README.zh-CN.md

@@ -117,6 +117,7 @@ npm install -g @jackwener/opencli@latest
 | **apple-podcasts** | `search` `episodes` `top` | 公开 |
 | **xiaoyuzhou** | `podcast` `podcast-episodes` `episode` | 公开 |
 | **zhihu** | `hot` `search` `question` `download` | 浏览器 |
+| **weixin** | `download` | 浏览器 |
 | **youtube** | `search` `video` `transcript` | 浏览器 |
 | **boss** | `search` `detail` `recommend` `joblist` `greet` `batchgreet` `send` `chatlist` `chatmsg` `invite` `mark` `exchange` `resume` `stats` | 浏览器 |
 | **coupang** | `search` `add-to-cart` | 浏览器 |
@@ -194,6 +195,7 @@ OpenCLI 支持从各平台下载图片、视频和文章。
 | **B站** | 视频 | 需要安装 `yt-dlp` |
 | **Twitter/X** | 图片、视频 | 从用户媒体页或单条推文下载 |
 | **知乎** | 文章（Markdown） | 导出文章，可选下载图片到本地 |
+| **微信公众号** | 文章（Markdown） | 导出微信公众号文章为 Markdown |
 
 ### 前置依赖
 
@@ -227,6 +229,9 @@ opencli zhihu download "https://zhuanlan.zhihu.com/p/xxx" --output ./zhihu
 
 # 导出并下载图片
 opencli zhihu download "https://zhuanlan.zhihu.com/p/xxx" --download-images
+
+# 导出微信公众号文章为 Markdown
+opencli weixin download --url "https://mp.weixin.qq.com/s/xxx" --output ./weixin
 ```
 
 

docs/adapters/browser/weixin.md

@@ -0,0 +1,33 @@
+# WeChat (微信公众号)
+
+**Mode**: 🔐 Browser · **Domain**: `mp.weixin.qq.com`
+
+## Commands
+
+| Command | Description |
+|---------|-------------|
+| `opencli weixin download` | 下载微信公众号文章为 Markdown 格式 |
+
+## Usage Examples
+
+```bash
+# Export article to Markdown
+opencli weixin download --url "https://mp.weixin.qq.com/s/xxx" --output ./weixin
+
+# Export with locally downloaded images
+opencli weixin download --url "https://mp.weixin.qq.com/s/xxx" --download-images
+
+# Export without images
+opencli weixin download --url "https://mp.weixin.qq.com/s/xxx" --no-download-images
+```
+
+## Output
+
+Downloads to `<output>/<article-title>/`:
+- `<article-title>.md` — Markdown with frontmatter (title, author, publish time, source URL)
+- `images/` — Downloaded images (if `--download-images` is enabled, default: true)
+
+## Prerequisites
+
+- Chrome running and **logged into** mp.weixin.qq.com (for articles behind login wall)
+- [Browser Bridge extension](/guide/browser-bridge) installed

docs/advanced/download.md

@@ -10,6 +10,7 @@ OpenCLI supports downloading images, videos, and articles from supported platfor
 | **bilibili** | Videos | Requires `yt-dlp` installed |
 | **twitter** | Images, Videos | Downloads from user media tab or single tweet |
 | **zhihu** | Articles (Markdown) | Exports articles with optional image download |
+| **weixin** | Articles (Markdown) | Exports WeChat Official Account articles |
 
 ## Prerequisites
 
@@ -43,6 +44,9 @@ opencli zhihu download "https://zhuanlan.zhihu.com/p/xxx" --output ./zhihu
 
 # Export with local images
 opencli zhihu download "https://zhuanlan.zhihu.com/p/xxx" --download-images
+
+# Export WeChat article to Markdown
+opencli weixin download --url "https://mp.weixin.qq.com/s/xxx" --output ./weixin
 ```
 
 ## Pipeline Step (YAML Adapters)

src/clis/bilibili/download.ts

@@ -8,18 +8,9 @@
  *   - yt-dlp must be installed: pip install yt-dlp
  */
 
-import * as fs from 'node:fs';
-import * as path from 'node:path';
 import { cli, Strategy } from '../../registry.js';
-import {
-  ytdlpDownload,
-  checkYtdlp,
-  sanitizeFilename,
-  getTempDir,
-  exportCookiesToNetscape,
-  formatCookieHeader,
-} from '../../download/index.js';
-import { DownloadProgressTracker, formatBytes } from '../../download/progress.js';
+import { checkYtdlp, sanitizeFilename } from '../../download/index.js';
+import { downloadMedia } from '../../download/media-download.js';
 
 cli({
   site: 'bilibili',
@@ -63,21 +54,8 @@ cli({
 
     const title = sanitizeFilename(data?.title || 'video');
 
-    // Extract cookies for authenticated downloads
-    const cookies = await page.getCookies({ domain: 'bilibili.com' });
-    const cookieString = formatCookieHeader(cookies);
-
-    // Create output directory
-    fs.mkdirSync(output, { recursive: true });
-
-    // Export cookies to Netscape format for yt-dlp
-    let cookiesFile: string | undefined;
-    if (cookies.length > 0) {
-      const tempDir = getTempDir();
-      fs.mkdirSync(tempDir, { recursive: true });
-      cookiesFile = path.join(tempDir, `bilibili_cookies_${Date.now()}.txt`);
-      exportCookiesToNetscape(cookies, cookiesFile);
-    }
+    // Extract cookies for yt-dlp
+    const browserCookies = await page.getCookies({ domain: 'bilibili.com' });
 
     // Build yt-dlp format string based on quality
     let format = 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best';
@@ -89,62 +67,26 @@ cli({
       format = 'bestvideo[height<=480][ext=mp4]+bestaudio[ext=m4a]/best[height<=480]';
     }
 
-    const destPath = path.join(output, `${bvid}_${title}.mp4`);
-
-    const tracker = new DownloadProgressTracker(1, true);
-    const progressBar = tracker.onFileStart(`${bvid}.mp4`, 0);
-
-    try {
-      const result = await ytdlpDownload(
-        `https://www.bilibili.com/video/${bvid}`,
-        destPath,
-        {
-          cookiesFile,
-          format,
-          extraArgs: [
-            '--merge-output-format', 'mp4',
-            '--embed-thumbnail',
-          ],
-          onProgress: (percent) => {
-            if (progressBar) progressBar.update(percent, 100);
-          },
-        },
-      );
-
-      if (progressBar) {
-        progressBar.complete(result.success, result.success ? formatBytes(result.size) : undefined);
-      }
-
-      tracker.onFileComplete(result.success);
-      tracker.finish();
-
-      // Cleanup cookies file
-      if (cookiesFile && fs.existsSync(cookiesFile)) {
-        fs.unlinkSync(cookiesFile);
-      }
-
-      return [{
-        bvid,
-        title: data?.title || 'video',
-        status: result.success ? 'success' : 'failed',
-        size: result.success ? formatBytes(result.size) : (result.error || 'unknown error'),
-      }];
-    } catch (err: any) {
-      if (progressBar) progressBar.fail(err.message);
-      tracker.onFileComplete(false);
-      tracker.finish();
-
-      // Cleanup cookies file
-      if (cookiesFile && fs.existsSync(cookiesFile)) {
-        fs.unlinkSync(cookiesFile);
-      }
-
-      return [{
-        bvid,
-        title: data?.title || 'video',
-        status: 'failed',
-        size: err.message,
-      }];
-    }
+    const videoUrl = `https://www.bilibili.com/video/${bvid}`;
+    const filename = `${bvid}_${title}.mp4`;
+
+    const results = await downloadMedia(
+      [{ type: 'video-ytdlp', url: videoUrl, filename }],
+      {
+        output,
+        browserCookies,
+        filenamePrefix: bvid,
+        ytdlpExtraArgs: ['-f', format, '--merge-output-format', 'mp4', '--embed-thumbnail'],
+      },
+    );
+
+    // Map results to bilibili-specific columns
+    const r = results[0] || { status: 'failed', size: '-' };
+    return [{
+      bvid,
+      title: data?.title || 'video',
+      status: r.status,
+      size: r.size,
+    }];
   },
 });

src/clis/twitter/download.ts

@@ -6,19 +6,9 @@
  *   opencli twitter download --tweet-url https://x.com/xxx/status/123 --output ./twitter
  */
 
-import * as fs from 'node:fs';
-import * as path from 'node:path';
 import { cli, Strategy } from '../../registry.js';
-import {
-  httpDownload,
-  ytdlpDownload,
-  checkYtdlp,
-  sanitizeFilename,
-  getTempDir,
-  exportCookiesToNetscape,
-  formatCookieHeader,
-} from '../../download/index.js';
-import { DownloadProgressTracker, formatBytes } from '../../download/progress.js';
+import { formatCookieHeader } from '../../download/index.js';
+import { downloadMedia } from '../../download/media-download.js';
 
 cli({
   site: 'twitter',
@@ -101,32 +91,11 @@ cli({
     `);
 
     if (!data || data.length === 0) {
-      return [{
-        index: 0,
-        type: '-',
-        status: 'failed',
-        size: 'No media found',
-      }];
+      return [{ index: 0, type: '-', status: 'failed', size: 'No media found' }];
     }
 
     // Extract cookies
-    const cookies = await page.getCookies({ domain: 'x.com' });
-    const cookieString = formatCookieHeader(cookies);
-
-    // Create output directory
-    const outputDir = tweetUrl
-      ? path.join(output, 'tweets')
-      : path.join(output, username || 'media');
-    fs.mkdirSync(outputDir, { recursive: true });
-
-    // Export cookies for yt-dlp
-    let cookiesFile: string | undefined;
-    if (cookies.length > 0) {
-      const tempDir = getTempDir();
-      fs.mkdirSync(tempDir, { recursive: true });
-      cookiesFile = path.join(tempDir, `twitter_cookies_${Date.now()}.txt`);
-      exportCookiesToNetscape(cookies, cookiesFile);
-    }
+    const browserCookies = await page.getCookies({ domain: 'x.com' });
 
     // Deduplicate media
     const seen = new Set<string>();
@@ -136,81 +105,14 @@ cli({
       return true;
     }).slice(0, limit);
 
-    const tracker = new DownloadProgressTracker(uniqueMedia.length, true);
-    const results: any[] = [];
-
-    for (let i = 0; i < uniqueMedia.length; i++) {
-      const media = uniqueMedia[i];
-      const ext = media.type === 'image' ? 'jpg' : 'mp4';
-      const filename = `${username || 'tweet'}_${i + 1}.${ext}`;
-      const destPath = path.join(outputDir, filename);
-
-      const progressBar = tracker.onFileStart(filename, i);
-
-      try {
-        let result: { success: boolean; size: number; error?: string };
-
-        if (media.type === 'video-tweet' && checkYtdlp()) {
-          // Use yt-dlp for video tweets
-          result = await ytdlpDownload(media.url, destPath, {
-            cookiesFile,
-            extraArgs: ['--merge-output-format', 'mp4'],
-            onProgress: (percent) => {
-              if (progressBar) progressBar.update(percent, 100);
-            },
-          });
-        } else if (media.type === 'image') {
-          // Direct HTTP download for images
-          result = await httpDownload(media.url, destPath, {
-            cookies: cookieString,
-            timeout: 30000,
-            onProgress: (received, total) => {
-              if (progressBar) progressBar.update(received, total);
-            },
-          });
-        } else {
-          // Direct HTTP download for direct video URLs
-          result = await httpDownload(media.url, destPath, {
-            cookies: cookieString,
-            timeout: 60000,
-            onProgress: (received, total) => {
-              if (progressBar) progressBar.update(received, total);
-            },
-          });
-        }
-
-        if (progressBar) {
-          progressBar.complete(result.success, result.success ? formatBytes(result.size) : undefined);
-        }
-
-        tracker.onFileComplete(result.success);
-
-        results.push({
-          index: i + 1,
-          type: media.type === 'video-tweet' ? 'video' : media.type,
-          status: result.success ? 'success' : 'failed',
-          size: result.success ? formatBytes(result.size) : (result.error || 'unknown error'),
-        });
-      } catch (err: any) {
-        if (progressBar) progressBar.fail(err.message);
-        tracker.onFileComplete(false);
-
-        results.push({
-          index: i + 1,
-          type: media.type,
-          status: 'failed',
-          size: err.message,
-        });
-      }
-    }
-
-    tracker.finish();
-
-    // Cleanup cookies file
-    if (cookiesFile && fs.existsSync(cookiesFile)) {
-      fs.unlinkSync(cookiesFile);
-    }
-
-    return results;
+    const subdir = tweetUrl ? 'tweets' : (username || 'media');
+    return downloadMedia(uniqueMedia, {
+      output,
+      subdir,
+      cookies: formatCookieHeader(browserCookies),
+      browserCookies,
+      filenamePrefix: username || 'tweet',
+      ytdlpExtraArgs: ['--merge-output-format', 'mp4'],
+    });
   },
 });