爬取代理实例
from lxml import etree
import requests
from fake_useragent import UserAgent
headers={
'User-Agent':UserAgent().chrome
}
url='https://www.xicidaili.com/nn/'
response=requests.get(url,headers=headers)
e=etree.HTML(response.text)
trs=e.xpath('//table[@id="ip_list"]/tr')
for num in range(2,len(trs)):
ip=trs[num].xpath('td[2]/text()')
port=trs[num].xpath('td[3]/text()')
type=trs[num].xpath('td[6]/text()')
print(type[0] + '://' + ip[0] + ':' + port[0])