爬虫-89免费代理

import re
import requests
from bs4 import BeautifulSoup

headers ={
'Host': 'www.89ip.cn',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36',
}
payload ={
'num':100,  # 每次获取的数量
'address':'',
'kill_address':'',
'port':'',
'kill_port':'',
'isp':'',
}
res = requests.get('https://www.89ip.cn/tqdl.html',headers=headers,params=payload)
soup = BeautifulSoup(res.text,'lxml')
ip_list =[ ip.strip() for ip in re.split(r'<.+?>',str(soup.select_one('.fly-panel div'))) if re.search('\d{1,3}.\d{1,3}.\d{1,3}.\d{1,3}:\d{2,5}',ip) ]
print(*ip_list,sep='\n')
print('提取结果共',len(ip_list),'条')