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
import asyncio

class ProxyListDownloadPlugin(BasePlugin):
    def __init__(self):
        super().__init__()
        self.name = "ProxyListDownload"
        self.urls = [
            "https://www.proxy-list.download/api/v1/get?type=http",
            "https://www.proxy-list.download/api/v1/get?type=https"
        ]

    async def parse(self, html):
        if not html:
            return
            
        lines = html.split('\r\n')
        if len(lines) <= 1:
            lines = html.split('\n')
            
        count = 0
        for line in lines:
            line = line.strip()
            if not line:
                continue
            
            if ':' in line:
                parts = line.split(':')
                if len(parts) >= 2:
                    ip = parts[0]
                    port = parts[1]
                    protocol = 'http' if 'type=http' in self.current_url else 'https'
                    yield ip, int(port), protocol
                    count += 1
        
        if count > 0:
            logger.info(f"{self.name} 解析完成，从 {self.current_url} 获得 {count} 个潜在代理")


if __name__ == "__main__":
    async def test_plugin():
        plugin = ProxyListDownloadPlugin()
        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())