Update obsidian-kb skill and add find-skills

- obsidian-kb: Add OCR processors (easyocr, tesseract) - obsidian-kb: Fix subtitle detection with test files - obsidian-kb: Add cookie verification script - Add find-skills skill for discovering capabilities - Add video processing scripts - Update clawhub lock file
2026-02-09 11:53:42 +08:00
parent d66eade77e
commit e0a2b323d9
33 changed files with 3555 additions and 36 deletions
@@ -0,0 +1,85 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+测试B站字幕提取 - 测试多个视频
+"""
+import asyncio
+import json
+from playwright.async_api import async_playwright
+
+async def test_video(bvid):
+    """测试单个视频"""
+    url = f"https://www.bilibili.com/video/{bvid}"
+
+    async with async_playwright() as playwright:
+        browser = await playwright.chromium.launch(headless=True)
+        context = await browser.new_context()
+        page = await context.new_page()
+
+        # 使用 API 获取视频信息
+        api_url = "https://api.bilibili.com/x/web-interface/view"
+        response = await page.request.get(api_url, params={'bvid': bvid})
+        data = await response.json()
+
+        if data.get('code') == 0:
+            video_data = data.get('data', {})
+            title = video_data.get('title', '')
+            cid = video_data.get('cid', '')
+            print(f"\n视频: {title}")
+            print(f"BV号: {bvid}")
+            print(f"cid: {cid}")
+
+            # 获取字幕
+            if cid:
+                player_url = "https://api.bilibili.com/x/player/v2"
+                player_response = await page.request.get(player_url, params={'bvid': bvid, 'cid': cid})
+                player_data = await player_response.json()
+
+                if player_data.get('code') == 0:
+                    subtitle_info = player_data.get('data', {}).get('subtitle', {})
+                    subtitles_list = subtitle_info.get('subtitles', [])
+
+                    if subtitles_list:
+                        print(f"✅ 找到 {len(subtitles_list)} 个字幕")
+                        for i, sub in enumerate(subtitles_list[:3]):
+                            print(f"  [{i+1}] {sub.get('lan_doc')} - {sub.get('subtitle_url')}")
+
+                        # 获取第一个字幕内容
+                        subtitle_url = subtitles_list[0].get('subtitle_url', '')
+                        if subtitle_url:
+                            full_url = f"https:{subtitle_url}"
+                            sub_response = await page.request.get(full_url)
+                            if sub_response.ok:
+                                sub_data = await sub_response.json()
+                                body = sub_data.get('body', [])
+                                print(f"\n字幕示例 (前3条):")
+                                for i, item in enumerate(body[:3]):
+                                    from_time = item.get('from', 0)
+                                    to_time = item.get('to', 0)
+                                    content = item.get('content', '')
+                                    print(f"  [{i+1}] [{from_time:.1f} - {to_time:.1f}] {content}")
+                            else:
+                                print(f"❌ 获取字幕内容失败: {sub_response.status}")
+                    else:
+                        print("❌ 该视频没有字幕")
+        else:
+            print(f"❌ 获取视频信息失败: {data.get('message')}")
+
+        await browser.close()
+
+async def main():
+    """测试多个视频"""
+    # 测试视频列表（包含不同类型的视频）
+    test_videos = [
+        "BV1XX4y1C7tF",  # 教程类视频，可能有字幕
+        "BV1GJ411x7h7",  # TED演讲，通常有字幕
+        "BV1uA411H7K4",  # 科技类视频
+        "BV1MnFNz5EDL",  # 之前的测试视频
+    ]
+
+    for bvid in test_videos:
+        await test_video(bvid)
+        await asyncio.sleep(1)
+
+if __name__ == '__main__':
+    asyncio.run(main())