xpath抓取代理ip

最新推荐文章于 2023-11-28 11:50:13 发布

转载最新推荐文章于 2023-11-28 11:50:13 发布 · 580 阅读

文章标签：

#xpath抓取代理I

python 爬虫专栏收录该内容

17 篇文章

订阅专栏


#coding:utf-8
import urllib
import urllib2
import requests
from bs4 import BeautifulSoup
from lxml import etree
_headers={'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding':'gzip, deflate, sdch',
'Accept-Language':'zh-CN,zh;q=0.8',
'Cache-Control':'max-age=0',
'Connection':'keep-alive',
'Host':'www.xicidaili.com',
'If-None-Match':'W/"b077743016dc54409ebe6b86ba7a869b"',
'Upgrade-Insecure-Requests':'1',
'User-Agent':'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.75 Safari/537.36',
}
_cookies=None
try:
    #_cookies=requests.get('http://www.xicidaili.com/nn/1',headers=_headers).cookies
    response=requests.get('http://www.xicidaili.com/nn',headers=_headers)
    text=response.text
    html=etree.HTML(text)
    result=html.xpath('(//tr[@class="odd"]|//tr[@class=""])/td[2]')
    result1 = html.xpath('(//tr[@class="odd"]|//tr[@class=""])/td[3]')
    result2 = html.xpath('(//tr[@class="odd"]|//tr[@class=""])/td[6]')
    print result
    for i ,j ,k in zip(result,result1,result2):
        print i.text,j.text,k.text

except urllib2.URLError,e:
    print e.reason