fix: 修复爬虫网络层、验证队列卡死及 API 500 错误

- 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
This commit is contained in:
祀梦
2026-04-04 19:27:36 +08:00
parent 635c524a7e
commit f09a8e16c4
19 changed files with 505 additions and 161 deletions

View File

@@ -13,27 +13,34 @@ class Fate0Plugin(BaseHTTPPlugin):
def __init__(self):
super().__init__()
self.urls = ["https://raw.githubusercontent.com/fate0/proxylist/master/proxy.list"]
self.urls = [
"https://raw.githubusercontent.com/fate0/proxylist/master/proxy.list",
"https://cdn.jsdelivr.net/gh/fate0/proxylist@master/proxy.list",
]
async def crawl(self) -> List[ProxyRaw]:
results = []
# 顺序 fetch带 fallback
for url in self.urls:
html = await self.fetch(url, timeout=30)
if not html:
if html:
break
if not html:
logger.warning(f"{self.display_name} 所有源均不可用")
return results
for line in html.split("\n"):
line = line.strip()
if not line:
continue
try:
data = json.loads(line)
ip = data.get("host")
port = data.get("port")
protocol = data.get("type", "http")
if ip and port:
results.append(ProxyRaw(ip, int(port), protocol))
except Exception:
continue
for line in html.split("\n"):
line = line.strip()
if not line:
continue
try:
data = json.loads(line)
ip = data.get("host")
port = data.get("port")
protocol = data.get("type", "http")
if ip and port:
results.append(ProxyRaw(ip, int(port), protocol))
except Exception:
continue
if results:
logger.info(f"{self.display_name} 解析完成,获取 {len(results)} 个潜在代理")
return results