kb-skills/kb-zhihu-metadata/zhihu_metadata.py

#!/usr/bin/env python3
"""
知乎元数据获取工具

支持以下内容类型：
- zvideo: 知乎视频 (https://www.zhihu.com/zvideo/xxx)
- zhuanlan: 知乎专栏文章 (https://zhuanlan.zhihu.com/p/xxx)
- answer: 知乎回答 (https://www.zhihu.com/question/xxx/answer/yyy)
- question: 知乎问题 (https://www.zhihu.com/question/xxx)
"""

import argparse
import json
import sys
import os
from typing import Dict, Optional, Any

# 添加当前目录到 Python 路径
current_dir = os.path.dirname(os.path.abspath(__file__))
if current_dir not in sys.path:
    sys.path.insert(0, current_dir)

from zhihu_extractor import ZhihuPlaywrightExtractor


def extract_zvideo(video_id: str, headless: bool = True) -> Dict[str, Any]:
    """
    获取知乎视频元数据

    Args:
        video_id: 视频 ID (数字字符串)
        headless: 是否使用无头浏览器

    Returns:
        视频元数据字典
    """
    url = f"https://www.zhihu.com/zvideo/{video_id}"
    return _extract_metadata(url, "zvideo", headless)


def extract_zhuanlan(article_id: str, headless: bool = True) -> Dict[str, Any]:
    """
    获取知乎专栏文章元数据

    Args:
        article_id: 文章 ID (数字字符串)
        headless: 是否使用无头浏览器

    Returns:
        文章元数据字典
    """
    url = f"https://zhuanlan.zhihu.com/p/{article_id}"
    return _extract_metadata(url, "zhuanlan", headless)


def extract_answer(answer_id: str, headless: bool = True) -> Dict[str, Any]:
    """
    获取知乎回答元数据

    Args:
        answer_id: 回答 ID (数字字符串)
        headless: 是否使用无头浏览器

    Returns:
        回答元数据字典
    """
    # 回答需要构建包含问题ID的URL，但answer_id本身足以识别
    # 使用一个占位符问题ID，因为提取器会从URL中提取answer_id
    url = f"https://www.zhihu.com/question/0/answer/{answer_id}"
    return _extract_metadata(url, "answer", headless)


def extract_question(question_id: str, headless: bool = True) -> Dict[str, Any]:
    """
    获取知乎问题元数据

    Args:
        question_id: 问题 ID (数字字符串)
        headless: 是否使用无头浏览器

    Returns:
        问题元数据字典
    """
    url = f"https://www.zhihu.com/question/{question_id}"
    return _extract_metadata(url, "question", headless)


def _extract_metadata(url: str, content_type: str, headless: bool) -> Dict[str, Any]:
    """
    内部函数：提取元数据

    Args:
        url: 知乎 URL
        content_type: 内容类型 (zvideo/zhuanlan)
        headless: 是否使用无头浏览器

    Returns:
        元数据字典
    """
    extractor = ZhihuPlaywrightExtractor(headless=headless)
    result = extractor.extract(url)

    if result:
        # 标准化输出格式
        metadata = {
            "type": content_type,
            "id": result.get("content_id", ""),
            "url": result.get("url", url),
            "title": result.get("title", ""),
            "author": result.get("author", ""),
            "publish_time": result.get("publish_time", ""),
            "vote_up": result.get("vote_up", 0),
            "content_markdown": result.get("content_markdown", ""),
            "raw_html": result.get("content", ""),
        }
        return metadata
    else:
        return {
            "type": content_type,
            "error": "Failed to extract content",
            "url": url
        }


def main():
    """命令行入口"""
    parser = argparse.ArgumentParser(
        description="知乎元数据获取工具",
        formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog="""
支持的类型:
  zvideo   - 知乎视频 (https://www.zhihu.com/zvideo/123456)
  zhuanlan - 知乎专栏文章 (https://zhuanlan.zhihu.com/p/123456)
  answer   - 知乎回答 (https://www.zhihu.com/question/xxx/answer/yyy)
  question - 知乎问题 (https://www.zhihu.com/question/xxx)

示例:
  python zhihu_metadata.py --id "123456" --type zvideo
  python zhihu_metadata.py --id "123456" --type zhuanlan
  python zhihu_metadata.py --id "123456" --type answer
  python zhihu_metadata.py --id "123456" --type question
        """
    )

    parser.add_argument(
        "--id", "-i",
        required=True,
        help="知乎内容 ID (视频ID/文章ID/回答ID/问题ID)"
    )

    parser.add_argument(
        "--type", "-t",
        required=True,
        choices=["zvideo", "zhuanlan", "answer", "question"],
        help="内容类型: zvideo=视频, zhuanlan=专栏文章, answer=回答, question=问题"
    )

    parser.add_argument(
        "--output", "-o",
        default=None,
        help="输出文件路径 (默认: stdout)"
    )

    parser.add_argument(
        "--headless",
        action="store_true",
        default=True,
        help="使用无头浏览器模式 (默认: True)"
    )

    args = parser.parse_args()

    # 提取元数据
    if args.type == "zvideo":
        result = extract_zvideo(args.id, headless=args.headless)
    elif args.type == "zhuanlan":
        result = extract_zhuanlan(args.id, headless=args.headless)
    elif args.type == "answer":
        result = extract_answer(args.id, headless=args.headless)
    elif args.type == "question":
        result = extract_question(args.id, headless=args.headless)
    else:
        print(f"不支持的类型: {args.type}")
        sys.exit(1)

    # 输出结果
    json_output = json.dumps(result, ensure_ascii=False, indent=2)

    if args.output:
        with open(args.output, 'w', encoding='utf-8') as f:
            f.write(json_output)
        print(f"结果已保存到: {args.output}")
    else:
        print(json_output)


if __name__ == "__main__":
    main()