openclaw-skills/test_subtitle2.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
测试B站字幕提取问题 - 改进版
"""
import asyncio
import json
import re
from playwright.async_api import async_playwright
from bs4 import BeautifulSoup

async def test_subtitle_api(bvid):
    """测试字幕API"""
    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("正在访问页面...")
        await page.goto(url, wait_until='networkidle', timeout=60000)
        await asyncio.sleep(3)

        # 方法1: 检查 __INITIAL_STATE__ 是否存在
        print("\n=== 测试方法1: 检查 __INITIAL_STATE__ 结构 ===")
        try:
            initial_state = await page.evaluate('() => window.__INITIAL_STATE__')
            if initial_state:
                print(f"__INITIAL_STATE__ keys: {list(initial_state.keys())}")
                video_data = initial_state.get('videoData', {})
                print(f"videoData keys: {list(video_data.keys())}")
                print(f"aid: {video_data.get('aid')}")
                print(f"cid: {video_data.get('cid')}")
            else:
                print("__INITIAL_STATE__ 不存在")
        except Exception as e:
            print(f"方法1失败: {e}")

        # 方法2: 从 HTML 中提取
        print("\n=== 测试方法2: 从 HTML script 标签提取 ===")
        try:
            content = await page.content()
            soup = BeautifulSoup(content, 'lxml')
            script_tags = soup.find_all('script')

            for script in script_tags:
                if script.string and '__INITIAL_STATE__' in script.string:
                    match = re.search(r'window\.__INITIAL_STATE__\s*=\s*({.+?});', script.string)
                    if match:
                        data = json.loads(match.group(1))
                        video_data = data.get('videoData', {})
                        print(f"aid: {video_data.get('aid')}")
                        print(f"cid: {video_data.get('cid')}")
                        print(f"subtitle: {video_data.get('subtitle')}")

                        # 如果找到了 cid，尝试获取字幕
                        cid = video_data.get('cid')
                        if cid:
                            await test_subtitle_api_with_cid(page, bvid, cid)
                            break
        except Exception as e:
            print(f"方法2失败: {e}")

        # 方法3: 使用 API 获取视频信息
        print("\n=== 测试方法3: 使用 API 获取视频信息 ===")
        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"aid: {video_data.get('aid')}")
                print(f"cid: {video_data.get('cid')}")
                print(f"title: {video_data.get('title')}")

                cid = video_data.get('cid')
                if cid:
                    await test_subtitle_api_with_cid(page, bvid, cid)
        except Exception as e:
            print(f"方法3失败: {e}")

        await browser.close()

async def test_subtitle_api_with_cid(page, bvid, cid):
    """使用 cid 测试字幕 API"""
    print(f"\n=== 使用 cid={cid} 获取字幕 ===")

    try:
        api_url = "https://api.bilibili.com/x/player/v2"
        response = await page.request.get(api_url, params={'bvid': bvid, 'cid': cid})
        data = await response.json()

        print(f"Response code: {data.get('code')}")

        if data.get('code') == 0:
            player_data = data.get('data', {})
            subtitle_info = player_data.get('subtitle', {})
            print(f"Subtitle info:")
            print(f"  allow_submit: {subtitle_info.get('allow_submit')}")
            print(f"  subtitles count: {len(subtitle_info.get('subtitles', []))}")

            subtitles_list = subtitle_info.get('subtitles', [])
            if subtitles_list:
                print(f"\nFound {len(subtitles_list)} subtitles:")
                for i, sub in enumerate(subtitles_list[:3]):
                    print(f"  [{i+1}] {sub.get('id')} - {sub.get('lan_doc')}")

                # 获取第一个字幕内容
                subtitle_url = subtitles_list[0].get('subtitle_url', '')
                print(f"\nFetching subtitle from: {subtitle_url}")
                full_url = f"https:{subtitle_url}"
                response = await page.request.get(full_url)
                if response.ok:
                    sub_data = await response.json()
                    print(f"First 3 subtitle items:")
                    for i, item in enumerate(sub_data.get('body', [])[:3]):
                        print(f"  [{i+1}] [{item.get('from')} - {item.get('to')}] {item.get('content')}")
                else:
                    print(f"Failed to fetch subtitle: {response.status}")
            else:
                print("No subtitles found")
        else:
            print(f"API error: {data.get('message')}")
    except Exception as e:
        print(f"Failed: {e}")

if __name__ == '__main__':
    # 测试一个有字幕的视频
    bvid = "BV1MnFNz5EDL"
    asyncio.run(test_subtitle_api(bvid))