OpenClaw Agent
e0a2b323d9
- 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
112 lines
4.6 KiB
Python
112 lines
4.6 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
测试B站字幕提取 - 使用确定有字幕的视频
|
|
"""
|
|
import asyncio
|
|
import json
|
|
from playwright.async_api import async_playwright
|
|
|
|
async def test_with_cookie(bvid, cookie=None):
|
|
"""测试带 Cookie 的字幕提取"""
|
|
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()
|
|
|
|
# 如果有 cookie，添加到上下文
|
|
if cookie:
|
|
await context.add_cookies([cookie])
|
|
print("使用已登录 Cookie")
|
|
|
|
# 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()
|
|
|
|
print(f"Player API 响应码: {player_data.get('code')}")
|
|
|
|
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):
|
|
print(f" [{i+1}] 语言: {sub.get('lan_doc')}, ID: {sub.get('id')}")
|
|
print(f" URL: {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}"
|
|
print(f"\n正在获取字幕内容: {full_url}")
|
|
sub_response = await page.request.get(full_url)
|
|
print(f"字幕请求状态: {sub_response.status}")
|
|
|
|
if sub_response.ok:
|
|
sub_data = await sub_response.json()
|
|
body = sub_data.get('body', [])
|
|
print(f"\n字幕内容示例 (前5条):")
|
|
for i, item in enumerate(body[:5]):
|
|
from_time = item.get('from', 0)
|
|
to_time = item.get('to', 0)
|
|
content = item.get('content', '')
|
|
print(f" [{i+1}] [{from_time:.1f}s - {to_time:.1f}s] {content}")
|
|
print(f"\n✅ 字幕获取成功！共 {len(body)} 条字幕")
|
|
else:
|
|
print(f"❌ 获取字幕内容失败: {sub_response.status}")
|
|
print(f"响应头: {sub_response.headers}")
|
|
else:
|
|
print("❌ 该视频没有字幕")
|
|
print(f"Subtitle info: {json.dumps(subtitle_info, indent=2, ensure_ascii=False)}")
|
|
else:
|
|
print(f"❌ Player API 失败: {player_data.get('message')}")
|
|
print(f"完整响应: {json.dumps(player_data, indent=2, ensure_ascii=False)}")
|
|
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"""
|
|
|
|
# 罗翔的视频通常有官方字幕
|
|
test_videos = [
|
|
"BV1GJ411x7h7", # 罗翔 - 刑法
|
|
"BV1yx411s7Jq", # 可能的官方视频
|
|
"BV1zv4y1m7Qp", # B站官方视频
|
|
]
|
|
|
|
for bvid in test_videos:
|
|
print(f"\n{'='*60}")
|
|
print(f"测试视频: {bvid}")
|
|
print(f"{'='*60}")
|
|
try:
|
|
await test_with_cookie(bvid)
|
|
except Exception as e:
|
|
print(f"❌ 测试失败: {e}")
|
|
import traceback
|
|
traceback.print_exc()
|
|
await asyncio.sleep(2)
|
|
|
|
if __name__ == '__main__':
|
|
asyncio.run(main())
|