Files
ProxyPool/app/plugins/speedx.py
祀梦 635c524a7e refactor(backend): optimize database safety, validator performance, and scheduler concurrency
- Fix SQL injection risks in proxy_repo and task_repo
- Atomic acquire_pending with UPDATE ... RETURNING
- Reuse aiohttp ClientSession in ValidatorService
- Replace polling with asyncio.Event in SchedulerService
- Optimize ValidationQueue.drain with asyncio.Condition
- Concurrent plugin crawling with asyncio.gather
- Unify ProxyRaw model import path
- Fix test baseline and remove tracked __pycache__ files
2026-04-04 14:43:31 +08:00

53 lines
1.8 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",
]
async def crawl(self) -> List[ProxyRaw]:
results = []
for url in self.urls:
html = await self.fetch(url, timeout=30)
if not html:
continue
# 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.split("\n"):
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))
if results:
logger.info(f"{self.display_name} 解析完成,获取 {len(results)} 个潜在代理")
return results