Files
ProxyPool/app/plugins/ip89.py
祀梦 635c524a7e refactor(backend): optimize database safety, validator performance, and scheduler concurrency
- Fix SQL injection risks in proxy_repo and task_repo
- Atomic acquire_pending with UPDATE ... RETURNING
- Reuse aiohttp ClientSession in ValidatorService
- Replace polling with asyncio.Event in SchedulerService
- Optimize ValidationQueue.drain with asyncio.Condition
- Concurrent plugin crawling with asyncio.gather
- Unify ProxyRaw model import path
- Fix test baseline and remove tracked __pycache__ files
2026-04-04 14:43:31 +08:00

41 lines
1.3 KiB
Python

import re
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
class Ip89Plugin(BaseHTTPPlugin):
default_config = {"max_pages": 5}
name = "ip89"
display_name = "89免费代理"
description = "从 89ip.cn 爬取免费代理"
def __init__(self):
super().__init__()
self.urls = [f"https://www.89ip.cn/index_{i}.html" for i in range(1, 6)]
async def crawl(self) -> List[ProxyRaw]:
results = []
for url in self.urls:
html = await self.fetch(url, timeout=15)
if not html:
continue
soup = BeautifulSoup(html, "lxml")
table = soup.find("table", class_="layui-table")
if not table:
continue
for row in table.find_all("tr"):
tds = row.find_all("td")
if len(tds) >= 2:
ip = tds[0].get_text(strip=True)
port = tds[1].get_text(strip=True)
if re.match(r"^\d+\.\d+\.\d+\.\d+$", ip) and port.isdigit():
results.append(ProxyRaw(ip, int(port), "http"))
if results:
logger.info(f"{self.display_name} 解析完成,获取 {len(results)} 个潜在代理")
return results