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
82 lines
3.4 KiB
Python
82 lines
3.4 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
|
||
|
||
VALID_PROTOCOLS = ("http", "https", "socks4", "socks5")
|
||
|
||
|
||
class YunDaiLiPlugin(BaseHTTPPlugin):
|
||
default_config = {"max_pages": 5}
|
||
name = "yundaili"
|
||
display_name = "云代理"
|
||
description = "从 GitHub 公开代理列表获取免费代理"
|
||
|
||
def __init__(self):
|
||
super().__init__()
|
||
# 主数据源：GitHub raw
|
||
self.urls = [
|
||
("http", "https://raw.githubusercontent.com/mmpx12/proxy-list/master/http.txt"),
|
||
("socks4", "https://raw.githubusercontent.com/mmpx12/proxy-list/master/socks4.txt"),
|
||
("socks5", "https://raw.githubusercontent.com/mmpx12/proxy-list/master/socks5.txt"),
|
||
]
|
||
# Fallback：jsdelivr CDN 加速
|
||
self.fallback_urls = [
|
||
("http", "https://cdn.jsdelivr.net/gh/mmpx12/proxy-list@master/http.txt"),
|
||
("socks4", "https://cdn.jsdelivr.net/gh/mmpx12/proxy-list@master/socks4.txt"),
|
||
("socks5", "https://cdn.jsdelivr.net/gh/mmpx12/proxy-list@master/socks5.txt"),
|
||
]
|
||
|
||
def _parse_htmls(self, htmls: List[str], url_mapping: List[tuple]) -> List[ProxyRaw]:
|
||
results: List[ProxyRaw] = []
|
||
for (protocol, _), html in zip(url_mapping, htmls):
|
||
if not html:
|
||
logger.warning(f"{self.display_name} {protocol.upper()} 返回空内容，可能网络受限或源已失效")
|
||
continue
|
||
|
||
count = 0
|
||
for line in html.splitlines():
|
||
line = line.strip()
|
||
if not line or ":" not in line:
|
||
continue
|
||
parts = line.split(":")
|
||
if len(parts) < 2:
|
||
continue
|
||
ip = parts[0].strip()
|
||
port_str = 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_str.isdigit() or not (1 <= int(port_str) <= 65535):
|
||
continue
|
||
final_protocol = protocol if protocol in VALID_PROTOCOLS else "http"
|
||
results.append(ProxyRaw(ip, int(port_str), final_protocol))
|
||
count += 1
|
||
|
||
if count:
|
||
logger.info(f"{self.display_name} {protocol.upper()} 解析完成，获取 {count} 个潜在代理")
|
||
return results
|
||
|
||
async def crawl(self) -> List[ProxyRaw]:
|
||
results: List[ProxyRaw] = []
|
||
|
||
# 顺序请求主源，避免某个 URL 卡住拖慢整体
|
||
for protocol, url in self.urls:
|
||
html = await self.fetch(url, timeout=12)
|
||
if html:
|
||
results.extend(self._parse_htmls([html], [(protocol, url)]))
|
||
|
||
# 主源为空时尝试 fallback（也顺序请求）
|
||
if not results:
|
||
logger.warning(f"{self.display_name} GitHub 主源全部返回空，尝试 jsdelivr fallback")
|
||
for protocol, url in self.fallback_urls:
|
||
html = await self.fetch(url, timeout=12)
|
||
if html:
|
||
results.extend(self._parse_htmls([html], [(protocol, url)]))
|
||
|
||
if results:
|
||
logger.info(f"{self.display_name} 总计解析完成，获取 {len(results)} 个潜在代理")
|
||
else:
|
||
logger.warning(f"{self.display_name} 未获取到任何代理")
|
||
return results
|