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
71 lines
2.7 KiB
Python
71 lines
2.7 KiB
Python
import re
|
||
import asyncio
|
||
import random
|
||
from typing import List
|
||
from bs4 import BeautifulSoup
|
||
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 KuaiDaiLiPlugin(BaseHTTPPlugin):
|
||
default_config = {"max_pages": 5}
|
||
name = "kuaidaili"
|
||
display_name = "快代理"
|
||
description = "从快代理网站爬取免费代理"
|
||
|
||
def __init__(self):
|
||
super().__init__()
|
||
# 减少页数，降低被反爬概率，确保至少能拿到数据
|
||
self.urls = [
|
||
"https://www.kuaidaili.com/free/inha/1/",
|
||
"https://www.kuaidaili.com/free/intr/1/",
|
||
]
|
||
|
||
def get_headers(self) -> dict:
|
||
headers = super().get_headers()
|
||
headers["Referer"] = "https://www.kuaidaili.com/free/inha/"
|
||
headers["Accept"] = "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"
|
||
headers["Accept-Encoding"] = "gzip, deflate, br"
|
||
headers["Accept-Language"] = "zh-CN,zh;q=0.9,en;q=0.8"
|
||
headers["Sec-Fetch-Dest"] = "document"
|
||
headers["Sec-Fetch-Mode"] = "navigate"
|
||
headers["Sec-Fetch-Site"] = "same-origin"
|
||
headers["Upgrade-Insecure-Requests"] = "1"
|
||
return headers
|
||
|
||
async def crawl(self) -> List[ProxyRaw]:
|
||
results = []
|
||
# 先访问首页预热会话，获取 cookie，降低被反爬概率
|
||
await self.fetch("https://www.kuaidaili.com/", timeout=10)
|
||
await asyncio.sleep(random.uniform(2, 4))
|
||
|
||
# 顺序请求免费代理页面
|
||
for url in self.urls:
|
||
html = await self.fetch(url, timeout=10)
|
||
if not html:
|
||
continue
|
||
soup = BeautifulSoup(html, "lxml")
|
||
table = soup.find("table")
|
||
if not table:
|
||
logger.warning(f"{self.display_name} 未能找到表格，可能是触发了反爬: {url}")
|
||
continue
|
||
|
||
for row in table.find_all("tr"):
|
||
tds = row.find_all("td")
|
||
if len(tds) >= 5:
|
||
ip = tds[0].get_text(strip=True)
|
||
port = tds[1].get_text(strip=True)
|
||
protocol = tds[4].get_text(strip=True).lower() if len(tds) > 4 else "http"
|
||
if protocol not in VALID_PROTOCOLS:
|
||
protocol = "http"
|
||
if re.match(r"^\d+\.\d+\.\d+\.\d+$", ip) and port.isdigit():
|
||
results.append(ProxyRaw(ip, int(port), protocol))
|
||
await asyncio.sleep(random.uniform(5, 8))
|
||
|
||
if results:
|
||
logger.info(f"{self.display_name} 解析完成，获取 {len(results)} 个潜在代理")
|
||
return results
|