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
96 lines
4.1 KiB
Python
96 lines
4.1 KiB
Python
from typing import List
|
||
from app.core.plugin_system import ProxyRaw
|
||
from app.plugins.base import BaseHTTPPlugin
|
||
from app.core.log import logger
|
||
|
||
|
||
class ProxyListDownloadPlugin(BaseHTTPPlugin):
|
||
default_config = {"max_pages": 5}
|
||
name = "proxylist_download"
|
||
display_name = "ProxyListDownload"
|
||
description = "从 GitHub 公开代理列表获取代理"
|
||
|
||
def __init__(self):
|
||
super().__init__()
|
||
# 首选 GitHub raw + fallback 备用源（jsdelivr CDN 或 ProxyScrape API）
|
||
self.sources = [
|
||
{
|
||
"primary": "https://raw.githubusercontent.com/komutan234/Proxy-List-Free/main/proxies/http.txt",
|
||
"fallbacks": [
|
||
"https://cdn.jsdelivr.net/gh/komutan234/Proxy-List-Free@main/proxies/http.txt",
|
||
"https://api.proxyscrape.com/v2/?request=get&protocol=http&timeout=10000&country=all&ssl=all&anonymity=all",
|
||
],
|
||
"protocol": "http",
|
||
},
|
||
{
|
||
"primary": "https://raw.githubusercontent.com/komutan234/Proxy-List-Free/main/proxies/socks4.txt",
|
||
"fallbacks": [
|
||
"https://cdn.jsdelivr.net/gh/komutan234/Proxy-List-Free@main/proxies/socks4.txt",
|
||
"https://api.proxyscrape.com/v2/?request=get&protocol=socks4&timeout=10000&country=all",
|
||
],
|
||
"protocol": "socks4",
|
||
},
|
||
{
|
||
"primary": "https://raw.githubusercontent.com/komutan234/Proxy-List-Free/main/proxies/socks5.txt",
|
||
"fallbacks": [
|
||
"https://cdn.jsdelivr.net/gh/komutan234/Proxy-List-Free@main/proxies/socks5.txt",
|
||
"https://api.proxyscrape.com/v2/?request=get&protocol=socks5&timeout=10000&country=all",
|
||
],
|
||
"protocol": "socks5",
|
||
},
|
||
]
|
||
|
||
def _detect_protocol(self, url: str) -> str:
|
||
"""根据 URL 判断协议（注意不要用 https:// 来判断）"""
|
||
if "socks4" in url:
|
||
return "socks4"
|
||
elif "socks5" in url:
|
||
return "socks5"
|
||
elif "/http.txt" in url or "protocol=http" in url:
|
||
return "http"
|
||
return "http"
|
||
|
||
def _parse_lines(self, html: str, protocol: str) -> List[ProxyRaw]:
|
||
"""解析代理文本，统一处理 \r\n、\n 两种换行以及可能存在的空行"""
|
||
results = []
|
||
# 统一替换为 \n 后再分割
|
||
text = html.replace("\r\n", "\n").replace("\r", "\n")
|
||
for line in text.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 ip and port.isdigit():
|
||
results.append(ProxyRaw(ip, int(port), protocol))
|
||
return results
|
||
|
||
async def crawl(self) -> List[ProxyRaw]:
|
||
results = []
|
||
# 并发请求所有 primary URL
|
||
primary_urls = [s["primary"] for s in self.sources]
|
||
primary_htmls = await self.fetch_all(primary_urls, timeout=15)
|
||
|
||
for idx, html in enumerate(primary_htmls):
|
||
source = self.sources[idx]
|
||
protocol = source.get("protocol") or self._detect_protocol(source["primary"])
|
||
|
||
if html and html.strip():
|
||
results.extend(self._parse_lines(html, protocol))
|
||
continue
|
||
|
||
# primary 返回空或仅空白字符，依次尝试 fallback
|
||
logger.warning(f"{self.display_name} 主源返回空，尝试 fallback: {source['primary']}")
|
||
for fallback_url in source["fallbacks"]:
|
||
fallback_html = await self.fetch(fallback_url, timeout=15)
|
||
if fallback_html and fallback_html.strip():
|
||
fb_protocol = source.get("protocol") or self._detect_protocol(fallback_url)
|
||
results.extend(self._parse_lines(fallback_html, fb_protocol))
|
||
break
|
||
|
||
if results:
|
||
logger.info(f"{self.display_name} 解析完成，获得 {len(results)} 个潜在代理")
|
||
return results
|