4ef7931941
修复问题： - 添加缺失的 httpx 依赖到 requirements.txt - 修复前端批量删除参数格式与后端不匹配（数组->对象数组） - 移除 app/api/main.py 中重复创建 app 的冗余代码 - 修复 Plugins.vue v-model 直接修改 store 状态的 Vue 警告 - 修复 README 端口/启动命令文档与实际配置不一致 - 修正 pytest.ini 过时配置 (asyncio_default_fixture_loop_scope) - 修复 WebUI index.html 语言设置为 zh-CN - 修复 .gitignore 错误忽略 tests/ 目录 后端优化： - 修复调度器默认间隔从 5 秒改为 30 分钟，避免无节制验证 - 修复 validate_all_now 在调度器停止时无法执行的 bug - 设置保存后热更新运行中调度器的验证间隔 - 将 update_score 优化为原子单事务 SQL，消除并发竞态 - 导出功能改为真正的流式分批读取（iter_batches），降低大导出内存占用 - ProxyResponse Schema 补齐 response_time_ms 字段 - 日志级别改为从配置动态读取，不再硬编码 INFO - 清理 validator_service 中的冗余 try/finally 代码 插件健壮性： - 修复 ip3366/ip89/kuaidaili/proxylist_download/speedx/yundaili/proxyscrape 的端口范围检查和 IPv6 地址解析问题（改用 rsplit + 1-65535 校验） - 修复 PluginService.list_plugins 并发竞争条件 - 修复 run_all_plugins 去重逻辑与数据库 UNIQUE 约束保持一致 - 修复 proxyscrape 异常时错误跳过 fallback 的 bug 测试： - 新增 7 个插件解析单元测试 - 新增 update_score 自动删除和 iter_batches 流式读取测试 - 全部 74 个测试通过
70 lines
2.6 KiB
Python
70 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
|
|
ip, _, port = line.rpartition(":")
|
|
ip = ip.strip()
|
|
port = port.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
|
|
try:
|
|
results.append(ProxyRaw(ip, int(port), protocol))
|
|
except ValueError:
|
|
continue
|
|
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
|