import sys
import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

from core.crawler import BasePlugin
from core.log import logger
from bs4 import BeautifulSoup
import re
import asyncio

class Ip89Plugin(BasePlugin):
    def __init__(self):
        super().__init__()
        self.name = "89免费代理"
        # 抓取前 5 页
        self.urls = [
            f"https://www.89ip.cn/index_{i}.html" for i in range(1, 6)
        ]

    async def parse(self, html):
        """
        解析 89ip 页面
        """
        if not html:
            return
            
        soup = BeautifulSoup(html, 'lxml')
        table = soup.find('table', class_='layui-table')
        if not table:
            return

        rows = table.find_all('tr')
        count = 0
        for row in rows:
            tds = row.find_all('td')
            if len(tds) >= 2:
                ip = tds[0].get_text(strip=True)
                port = tds[1].get_text(strip=True)
                # 89ip 通常不直接写协议，默认尝试 http
                protocol = 'http'
                
                if re.match(r'^\d+\.\d+\.\d+\.\d+$', ip) and port.isdigit():
                    yield ip, int(port), protocol
                    count += 1
        
        if count > 0:
            logger.info(f"{self.name} 解析完成，获得 {count} 个潜在代理")


if __name__ == "__main__":
    async def test_plugin():
        plugin = Ip89Plugin()
        print(f"========== 测试 {plugin.name} ==========")
        print(f"目标URL数量: {len(plugin.urls)}")
        print(f"开始抓取...\n")
        
        proxies = await plugin.run()
        
        print(f"\n========== 抓取结果 ==========")
        print(f"总计获取 {len(proxies)} 个代理:")
        print("-" * 60)
        
        for idx, (ip, port, protocol) in enumerate(proxies, 1):
            print(f"{idx:3d}. {ip:15s} : {str(port):5s}  |  {protocol}")
        
        print("-" * 60)
        print(f"完成！共 {len(proxies)} 个代理~")
    
    asyncio.run(test_plugin())