openclaw-skills/test_wbi_subtitle.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
测试 B站 WBI API 字幕提取
"""
import asyncio
import json
from playwright.async_api import async_playwright

async def test_wbi_subtitle(bvid):
    """测试 WBI API 字幕"""
    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()

        print(f"正在测试视频: {url}")
        print("=" * 80)

        # 首先获取 aid 和 cid
        print("\n1. 获取视频基本信息...")
        try:
            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', {})
                print(f"   标题: {video_data.get('title')}")
                aid = video_data.get('aid')
                cid = video_data.get('cid')
                print(f"   aid: {aid}")
                print(f"   cid: {cid}")
            else:
                print(f"   ❌ 失败: {data.get('message')}")
                await browser.close()
                return
        except Exception as e:
            print(f"   ❌ 异常: {e}")
            await browser.close()
            return

        # 使用 WBI API 获取播放器信息（包含字幕）
        print("\n2. 使用 WBI API 获取播放器信息...")
        try:
            wbi_url = "https://api.bilibili.com/x/player/wbi/v2"
            wbi_response = await page.request.get(wbi_url, params={'aid': aid, 'cid': cid})

            print(f"   状态码: {wbi_response.status}")
            if wbi_response.ok:
                wbi_data = await wbi_response.json()
                print(f"   响应码: {wbi_data.get('code')}")

                if wbi_data.get('code') == 0:
                    player_data = wbi_data.get('data', {})
                    print(f"\n   数据结构:")
                    print(f"   {json.dumps(list(player_data.keys()), indent=4, ensure_ascii=False)}")

                    # 检查字幕
                    subtitle_info = player_data.get('subtitle', {})
                    print(f"\n   字幕信息:")
                    print(f"   {json.dumps(subtitle_info, indent=4, ensure_ascii=False)}")

                    subtitles_list = subtitle_info.get('subtitles', [])
                    if subtitles_list:
                        print(f"\n   ✅ 找到 {len(subtitles_list)} 个字幕!")
                        for i, sub in enumerate(subtitles_list):
                            print(f"      [{i+1}] {sub.get('lan_doc')} (lan={sub.get('id')}, type={sub.get('id_type')})")
                            print(f"          URL: {sub.get('subtitle_url')}")

                            # 获取字幕内容
                            subtitle_url = sub.get('subtitle_url', '')
                            if subtitle_url:
                                full_url = f"https:{subtitle_url}"
                                print(f"\n          正在获取字幕内容...")
                                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"          ✅ 获取成功，共 {len(body)} 条字幕")
                                    print(f"          前3条字幕:")
                                    for j, item in enumerate(body[:3]):
                                        from_time = item.get('from', 0)
                                        to_time = item.get('to', 0)
                                        content = item.get('content', '')
                                        print(f"             [{j+1}] [{from_time:.1f}s - {to_time:.1f}s] {content}")
                                else:
                                    print(f"          ❌ 获取失败: {sub_response.status}")
                    else:
                        print(f"\n   ❌ 没有找到字幕")
                        print(f"   allow_submit: {subtitle_info.get('allow_submit')}")
                else:
                    print(f"   ❌ API 错误: {wbi_data.get('message')}")
            else:
                print(f"   ❌ HTTP 错误: {wbi_response.status}")
        except Exception as e:
            print(f"   ❌ 异常: {e}")
            import traceback
            traceback.print_exc()

        # 尝试不使用 wbi，使用旧版本 API
        print("\n3. 尝试旧版 API (v2)...")
        try:
            old_url = "https://api.bilibili.com/x/player/v2"
            old_response = await page.request.get(old_url, params={'bvid': bvid, 'cid': cid})
            print(f"   状态码: {old_response.status}")
            if old_response.ok:
                old_data = await old_response.json()
                subtitle_info = old_data.get('data', {}).get('subtitle', {})
                subtitles_list = subtitle_info.get('subtitles', [])
                print(f"   字幕数量: {len(subtitles_list)}")
                if subtitles_list:
                    print(f"   ✅ 旧版 API 找到字幕!")
                    for sub in subtitles_list:
                        print(f"      {sub.get('lan_doc')}")
        except Exception as e:
            print(f"   ❌ 异常: {e}")

        await browser.close()

if __name__ == '__main__':
    bvid = "BV1KtFzzqEUG"
    asyncio.run(test_wbi_subtitle(bvid))