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
This commit is contained in:
OpenClaw Agent
@@ -0,0 +1,228 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
下载视频片段用于 OCR 提取硬字幕
|
||||
策略：每隔 N 秒截取一帧，而不是下载整个视频
|
||||
"""
|
||||
import asyncio
|
||||
import json
|
||||
import os
|
||||
import cv2
|
||||
import numpy as np
|
||||
from playwright.async_api import async_playwright
|
||||
from urllib.request import Request, urlopen
|
||||
|
||||
async def extract_frames_for_ocr(bvid, output_dir="/tmp/bilibili_frames", interval_seconds=10, max_frames=200):
|
||||
"""
|
||||
提取视频帧用于 OCR
|
||||
|
||||
Args:
|
||||
bvid: B站视频 BV 号
|
||||
output_dir: 输出目录
|
||||
interval_seconds: 截帧间隔（秒）
|
||||
max_frames: 最大截取帧数
|
||||
|
||||
Returns:
|
||||
str: 输出目录路径
|
||||
"""
|
||||
url = f"https://www.bilibili.com/video/{bvid}"
|
||||
|
||||
# 创建输出目录
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
|
||||
print(f"正在提取视频帧: {url}")
|
||||
print(f"间隔: {interval_seconds}秒，最大帧数: {max_frames}")
|
||||
print("=" * 80)
|
||||
|
||||
async with async_playwright() as playwright:
|
||||
browser = await playwright.chromium.launch(headless=True)
|
||||
context = await browser.new_context()
|
||||
page = await context.new_page()
|
||||
|
||||
# 获取视频信息
|
||||
print("\n1. 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:
|
||||
print(f" ❌ 失败: {data.get('message')}")
|
||||
await browser.close()
|
||||
return None
|
||||
|
||||
video_data = data.get('data', {})
|
||||
title = video_data.get('title')
|
||||
aid = video_data.get('aid')
|
||||
cid = video_data.get('cid')
|
||||
duration = video_data.get('duration')
|
||||
print(f" 标题: {title}")
|
||||
print(f" 时长: {duration}秒")
|
||||
except Exception as e:
|
||||
print(f" ❌ 异常: {e}")
|
||||
await browser.close()
|
||||
return None
|
||||
|
||||
# 获取视频流 URL
|
||||
print("\n2. 获取视频流 URL...")
|
||||
try:
|
||||
playurl_api = "https://api.bilibili.com/x/player/playurl"
|
||||
params = {
|
||||
'bvid': bvid,
|
||||
'cid': cid,
|
||||
'qn': 80, # 1080P
|
||||
'otype': 'json',
|
||||
'fnver': 0,
|
||||
'fnval': 0, # FLV 格式
|
||||
}
|
||||
|
||||
playurl_response = await page.request.get(playurl_api, params=params)
|
||||
|
||||
if not playurl_response.ok or playurl_response.status != 200:
|
||||
print(f" ❌ HTTP 错误: {playurl_response.status}")
|
||||
await browser.close()
|
||||
return None
|
||||
|
||||
playurl_data = await playurl_response.json()
|
||||
|
||||
if playurl_data.get('code') != 0:
|
||||
print(f" ❌ API 错误: {playurl_data.get('message')}")
|
||||
await browser.close()
|
||||
return None
|
||||
|
||||
play_data = playurl_data.get('data', {})
|
||||
durl = play_data.get('durl', [])
|
||||
|
||||
if not durl:
|
||||
print(f" ❌ 没有找到视频流")
|
||||
await browser.close()
|
||||
return None
|
||||
|
||||
# 获取第一个分段的 URL
|
||||
first_segment_url = durl[0].get('url')
|
||||
print(f" ✅ 获取到视频流 URL")
|
||||
|
||||
except Exception as e:
|
||||
print(f" ❌ 异常: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
await browser.close()
|
||||
return None
|
||||
|
||||
# 使用 OpenCV 直接从 URL 读取视频并提取帧
|
||||
print(f"\n3. 提取视频帧...")
|
||||
|
||||
try:
|
||||
# 添加请求头
|
||||
headers = {
|
||||
'Referer': 'https://www.bilibili.com/',
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
|
||||
}
|
||||
|
||||
# 使用 urllib 下载视频到临时文件（只下载前 50MB）
|
||||
print(f" 正在下载视频（前 50MB）...")
|
||||
|
||||
req = Request(first_segment_url, headers=headers)
|
||||
|
||||
# 下载视频数据（限制 50MB）
|
||||
chunk_size = 8192
|
||||
max_bytes = 50 * 1024 * 1024 # 50MB
|
||||
video_data = bytearray()
|
||||
|
||||
with urlopen(req, timeout=60) as response:
|
||||
while True:
|
||||
chunk = response.read(chunk_size)
|
||||
if not chunk or len(video_data) >= max_bytes:
|
||||
break
|
||||
video_data.extend(chunk)
|
||||
|
||||
print(f" 已下载 {len(video_data) / 1024 / 1024:.2f}MB")
|
||||
|
||||
# 保存为临时文件
|
||||
temp_video_path = os.path.join(output_dir, "temp_video.flv")
|
||||
with open(temp_video_path, 'wb') as f:
|
||||
f.write(bytes(video_data))
|
||||
|
||||
# 使用 OpenCV 打开视频
|
||||
cap = cv2.VideoCapture(temp_video_path)
|
||||
|
||||
if not cap.isOpened():
|
||||
print(f" ❌ 无法打开视频文件")
|
||||
await browser.close()
|
||||
return None
|
||||
|
||||
# 获取视频帧率
|
||||
fps = cap.get(cv2.CAP_PROP_FPS)
|
||||
total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
|
||||
print(f" 帧率: {fps:.2f} fps")
|
||||
print(f" 总帧数: {total_frames}")
|
||||
|
||||
# 计算需要提取的帧
|
||||
interval_frames = int(fps * interval_seconds)
|
||||
frame_count = 0
|
||||
extracted_count = 0
|
||||
|
||||
print(f"\n 开始提取帧...")
|
||||
|
||||
while True:
|
||||
# 跳到目标帧
|
||||
cap.set(cv2.CAP_PROP_POS_FRAMES, frame_count)
|
||||
|
||||
# 读取帧
|
||||
ret, frame = cap.read()
|
||||
|
||||
if not ret:
|
||||
break
|
||||
|
||||
# 保存帧
|
||||
frame_path = os.path.join(output_dir, f"frame_{extracted_count:04d}_{frame_count}.jpg")
|
||||
cv2.imwrite(frame_path, frame)
|
||||
extracted_count += 1
|
||||
|
||||
print(f" 提取第 {extracted_count} 帧 (时间: {frame_count / fps:.1f}s)")
|
||||
|
||||
# 检查是否达到最大帧数
|
||||
if extracted_count >= max_frames:
|
||||
print(f" 已达到最大帧数限制")
|
||||
break
|
||||
|
||||
# 跳到下一帧
|
||||
frame_count += interval_frames
|
||||
|
||||
cap.release()
|
||||
|
||||
# 删除临时视频文件
|
||||
os.remove(temp_video_path)
|
||||
|
||||
print(f"\n4. 完成！")
|
||||
print(f" 成功提取 {extracted_count} 帧图像")
|
||||
print(f" 输出目录: {output_dir}")
|
||||
|
||||
await browser.close()
|
||||
return output_dir
|
||||
|
||||
except Exception as e:
|
||||
print(f" ❌ 提取帧失败: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
await browser.close()
|
||||
return None
|
||||
|
||||
if __name__ == '__main__':
|
||||
import sys
|
||||
|
||||
bvid = "BV1KtFzzqEUG"
|
||||
|
||||
result = asyncio.run(extract_frames_for_ocr(
|
||||
bvid,
|
||||
interval_seconds=10, # 每 10 秒提取一帧
|
||||
max_frames=100 # 最多提取 100 帧
|
||||
))
|
||||
|
||||
if result:
|
||||
print(f"\n✅ 提取完成！")
|
||||
print(f"输出目录: {result}")
|
||||
print(f"\n下一步：使用 OCR 工具识别字幕")
|
||||
else:
|
||||
print(f"\n❌ 提取失败")
|
||||
sys.exit(1)
|
||||
Reference in New Issue
Block a user