#!/usr/bin/env python3
"""
Weibo Scraper - 微博热点内容爬取工具
"""

import json
import time
import requests
from datetime import datetime
from typing import Optional, List, Dict, Any
import argparse
import os
import sys

class WeiboScraper:
    """微博热点内容爬取器"""

    def __init__(self, config: Optional[Dict[str, Any]] = None):
        self.config = config or {}
        self.base_url = "https://weibo.com/ajax/side/hotSearch"
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
            "Accept": "application/json, text/plain, */*",
            "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
            "Referer": "https://weibo.com"
        }
        self.session = requests.Session()
        self.session.headers.update(self.headers)

    def get_hot_search(self, limit: int = 50) -> List[Dict[str, Any]]:
        """获取微博热搜榜"""
        try:
            response = self.session.get(self.base_url, timeout=10)
            if response.status_code == 200:
                data = response.json()
                if data.get("ok") == 1:
                    return data.get("data", {}).get("realtime", [])[:limit]
            return []
        except Exception as e:
            print(f"Error fetching hot search: {e}", file=sys.stderr)
            return []

    def format_item(self, item: Dict[str, Any], category: str = "综合") -> Dict[str, Any]:
        """格式化单条热搜数据"""
        return {
            "source": {
                "platform": "weibo",
                "category": category,
                "hot_id": str(item.get("word_scheme", "")),
                "url": f"https://s.weibo.com/weibo?q={item.get('word', '')}"
            },
            "engagement": {
                "likes": item.get("num", 0),
                "comments": 0,
                "shares": 0,
                "read_count": item.get("raw_hot", 0)
            },
            "content": {
                "title": item.get("word", ""),
                "text": item.get("note", ""),
                "media_urls": [],
                "category_tags": [category]
            },
            "author": {
                "username": "",
                "followers": 0,
                "verified": False
            },
            "timestamp": datetime.now().isoformat(),
            "metrics": {
                "hot_rank": item.get("rank", 0),
                "hot_score": item.get("raw_hot", 0),
                "trend": "up" if item.get("label_name") else "stable"
            }
        }

    def scrape(self, category: str = "综合", limit: int = 50) -> Dict[str, Any]:
        """执行爬取"""
        items = self.get_hot_search(limit)
        results = []

        for item in items:
            if item.get("flag", 0) in [1, 2]:  # 有效数据
                # 根据关键词判断分类
                category = self._detect_category(item.get("word", ""))
                results.append(self.format_item(item, category))

        return {
            "success": True,
            "timestamp": datetime.now().isoformat(),
            "count": len(results),
            "data": results
        }

    def _detect_category(self, keyword: str) -> str:
        """根据关键词检测分类"""
        keyword = keyword.lower()

        categories = {
            "娱乐": ["明星", "演员", "歌手", "电影", "电视剧", "综艺", "演唱会", "恋情", "结婚", "离婚", "分手"],
            "社会": ["事件", "新闻", "事故", "疫情", "政策", "法律", "民生"],
            "科技": ["手机", "电脑", "AI", "互联网", "数码", "科技", "发布会"],
            "搞笑": ["搞笑", "段子", "视频", "搞笑", "沙雕", "幽默"],
            "体育": ["足球", "篮球", "NBA", "世界杯", "奥运", "比赛", "冠军"],
            "财经": ["股票", "基金", "经济", "财经", "房价", "油价"]
        }

        for cat, keywords in categories.items():
            if any(kw in keyword for kw in keywords):
                return cat
        return "综合"

def save_results(data: Dict[str, Any], output_path: str):
    """保存结果到文件"""
    os.makedirs(os.path.dirname(output_path), exist_ok=True)
    with open(output_path, 'w', encoding='utf-8') as f:
        json.dump(data, f, ensure_ascii=False, indent=2)

def main():
    parser = argparse.ArgumentParser(description="微博热点内容爬取工具")
    parser.add_argument("--category", type=str, default="综合", help="分类筛选")
    parser.add_argument("--limit", type=int, default=50, help="爬取数量限制")
    parser.add_argument("--output", type=str, default="workspace/weibo_output.json", help="输出文件路径")
    parser.add_argument("--cron", action="store_true", help="定时模式(仅输出不打印)")
    args = parser.parse_args()

    scraper = WeiboScraper()
    result = scraper.scrape(category=args.category, limit=args.limit)

    if args.cron:
        output_path = args.output
    else:
        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
        output_path = f"workspace/weibo_{timestamp}.json"

    save_results(result, output_path)

    if not args.cron:
        print(json.dumps(result, ensure_ascii=False, indent=2))
    else:
        print(f"Saved to {output_path}")

if __name__ == "__main__":
    main()