starmen1265
193d2b375d
- kb-zhihu-metadata: 新增 zhihu_article_crawler.py 支持爬取知乎专栏文章 - kb-zhihu-content: 添加 article-from-media 类型支持从 MediaCrawler 数据读取 - 更新 SKILL.md 文档说明新功能
87 lines
2.4 KiB
Markdown
87 lines
2.4 KiB
Markdown
# KB Zhihu Content Skill
|
|
|
|
**kb-zhihu-content** - Download Zhihu videos and extract content.
|
|
|
|
## Features
|
|
|
|
- Video download using **yt-dlp**
|
|
- Subtitle extraction (returns no subtitle, triggers Whisper)
|
|
- **Read article content from MediaCrawler data** (NEW!)
|
|
- Supports `ZHIHU_COOKIE` environment variable
|
|
|
|
## Environment Variables
|
|
|
|
| Variable | Required | Description |
|
|
|----------|----------|-------------|
|
|
| `ZHIHU_COOKIE` | No | 知乎登录 Cookie (for member-only videos) |
|
|
|
|
## Commands
|
|
|
|
```bash
|
|
# Download video
|
|
python zhihu_content.py --id "12345678" --type video --output "/path/to/downloads/"
|
|
|
|
# Extract subtitle (returns no subtitle, triggers Whisper)
|
|
python zhihu_content.py --id "12345678" --type subtitle --output "/path/to/subtitles/"
|
|
|
|
# 从 MediaCrawler 读取文章内容 (⚡ NEW!)
|
|
python zhihu_content.py --type article-from-media --input "~/work/MediaCrawler/data/zhihu/json/detail_contents_2026-02-27.json" --output "~/work/knowledge-base/data/zhihu/"
|
|
```
|
|
|
|
## MediaCrawler 数据读取
|
|
|
|
**新功能**：从 MediaCrawler 爬取的数据中提取知乎文章内容
|
|
|
|
### 使用方法
|
|
|
|
```bash
|
|
# 从 MediaCrawler JSON 文件读取文章内容
|
|
python zhihu_content.py --type article-from-media \
|
|
--input "~/work/MediaCrawler/data/zhihu/json/detail_contents_2026-02-27.json" \
|
|
--output "~/work/knowledge-base/data/zhihu/"
|
|
|
|
# 查找最新的爬取数据
|
|
python zhihu_content.py --type article-from-media \
|
|
--output "~/work/knowledge-base/data/zhihu/"
|
|
```
|
|
|
|
### 参数说明
|
|
|
|
| 参数 | 说明 |
|
|
|------|------|
|
|
| `--type article-from-media` | 从 MediaCrawler 数据读取 |
|
|
| `--input` | MediaCrawler 输出文件路径（可选，不指定则自动查找最新） |
|
|
| `--output` | 输出目录 |
|
|
|
|
### 输出格式
|
|
|
|
```json
|
|
{
|
|
"success": true,
|
|
"type": "article",
|
|
"filename": "zhihu_article_如何高效的爬取微信公众号.md",
|
|
"filepath": "/home/xxx/work/knowledge-base/data/zhihu/zhihu_article_如何高效的爬取微信公众号.md",
|
|
"message": "文章内容已导出"
|
|
}
|
|
```
|
|
|
|
## 原有功能
|
|
|
|
### Video Download
|
|
|
|
Video download uses **yt-dlp**:
|
|
1. Parses `ZHIHU_COOKIE` environment variable (optional)
|
|
2. Creates temporary Netscape-format cookie file
|
|
3. Runs `yt-dlp -f best -o <output> <url>`
|
|
4. Cleans up temporary file
|
|
|
|
**Note**: 知乎视频通常没有官方字幕，将自动触发 Whisper 语音识别
|
|
|
|
## Installation
|
|
|
|
```bash
|
|
# Already included in kb-skills repo
|
|
# Ensure yt-dlp is installed
|
|
pip install yt-dlp aiohttp
|
|
```
|