f09a8e16c4
- 修复 BaseHTTPPlugin 连接池、并发控制、异常日志、超时策略 - 修复/增强 8 个爬虫插件的稳定性和 fallback 机制 - 清理 validation_tasks 表 4 万+ pending 任务，避免队列卡死 - 修复 app/api/main.py 缺失全局 app 实例导致的 500 错误 - 提升前端 Axios 超时到 120 秒，避免请求断开 - 修复插件统计持久化和调度器生命周期问题
68 lines
2.6 KiB
Python
68 lines
2.6 KiB
Python
import re
|
|
from typing import List
|
|
from app.core.plugin_system import ProxyRaw
|
|
from app.plugins.base import BaseHTTPPlugin
|
|
from app.core.log import logger
|
|
|
|
|
|
class SpeedXPlugin(BaseHTTPPlugin):
|
|
default_config = {"max_pages": 5}
|
|
name = "speedx"
|
|
display_name = "SpeedX代理库"
|
|
description = "从 SpeedX GitHub 仓库获取 SOCKS 代理列表"
|
|
|
|
def __init__(self):
|
|
super().__init__()
|
|
self.urls = [
|
|
"https://raw.githubusercontent.com/TheSpeedX/SOCKS-List/master/http.txt",
|
|
"https://raw.githubusercontent.com/TheSpeedX/SOCKS-List/master/socks4.txt",
|
|
"https://raw.githubusercontent.com/TheSpeedX/SOCKS-List/master/socks5.txt",
|
|
]
|
|
self.fallback_urls = [
|
|
"https://cdn.jsdelivr.net/gh/TheSpeedX/SOCKS-List@master/http.txt",
|
|
"https://cdn.jsdelivr.net/gh/TheSpeedX/SOCKS-List@master/socks4.txt",
|
|
"https://cdn.jsdelivr.net/gh/TheSpeedX/SOCKS-List@master/socks5.txt",
|
|
]
|
|
|
|
def _parse_htmls(self, htmls: List[str], urls: List[str]) -> List[ProxyRaw]:
|
|
results = []
|
|
for idx, html in enumerate(htmls):
|
|
if not html:
|
|
continue
|
|
url = urls[idx]
|
|
|
|
# 根据 URL 判断协议
|
|
protocol = "http"
|
|
if "socks5" in url:
|
|
protocol = "socks5"
|
|
elif "socks4" in url:
|
|
protocol = "socks4"
|
|
|
|
for line in html.splitlines():
|
|
line = line.strip()
|
|
if not line or ":" not in line:
|
|
continue
|
|
parts = line.split(":")
|
|
if len(parts) >= 2:
|
|
ip = parts[0].strip()
|
|
port = parts[1].strip()
|
|
if not re.match(r"^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$", ip):
|
|
continue
|
|
if not port.isdigit() or not (1 <= int(port) <= 65535):
|
|
continue
|
|
results.append(ProxyRaw(ip, int(port), protocol))
|
|
return results
|
|
|
|
async def crawl(self) -> List[ProxyRaw]:
|
|
htmls = await self.fetch_all(self.urls, timeout=15)
|
|
results = self._parse_htmls(htmls, self.urls)
|
|
|
|
if not results:
|
|
logger.warning(f"{self.display_name} GitHub 源全部返回空，尝试 jsdelivr fallback")
|
|
htmls = await self.fetch_all(self.fallback_urls, timeout=15)
|
|
results = self._parse_htmls(htmls, self.fallback_urls)
|
|
|
|
if results:
|
|
logger.info(f"{self.display_name} 解析完成，获取 {len(results)} 个潜在代理")
|
|
return results
|