python 爬虫汇总

import urllib, urllib2, re, requests, os, sys, cookielib
import gzip
import StringIO

#伪造headers 方式：

url = "http://am.22.cn"
headers = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
    'Accept-Encoding': 'gzip, deflate',
    'Accept-Language': 'zh-CN,zh;q=0.8',
    'Cache-Control': 'max-age=0',
    'Connection': 'keep-alive',
    'Cookie': 'ASP.NET_SessionId=v3s4qeaysqitplcsp2en142e; CNZZDATA906087=cnzz_eid%3D1527837511-1447985608-http%253A%252F%252Fwww.22.cn%252F%26ntime%3D1459259942',
    'Host': 'am.22.cn',
    'Referer':'http://am.22.cn/ykj/?t=0.21097470237873495&ddlSuf=0&keyword=wmLjx&chkorder=-1&chkday=-1&position=&position1=&position2=&MinPrice=0&MaxPrice=&selMinLen=1&selMaxLen=200&dealtype=2&keytype=0&issch=1&showtype=0',
    'Upgrade-Insecure-Requests': '1',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.116 UBrowser/5.6.11466.7 Safari/537.36'
}

request = urllib2.Request(url, headers=headers)
resp = urllib2.urlopen(request).read()
data = StringIO.StringIO(resp)
gzipper = gzip.GzipFile(fileobj=data)
html = gzipper.read()
print html




#cookies方式：
#cookies自动提交在opener里

    post_data = {"module": "enterzone", "login_name": "", "password": ""}

    ##cookies,访问一次获取cookies
    cj = cookielib.CookieJar()
    opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
    urllib2.install_opener(opener)
    url = "http://www.xxxx.com/login"
    request = urllib2.urlopen(url).read()


#编码post字典数据
    postdata = urllib.urlencode(post_data)

    resp = opener.open(url, postdata).read()



#验证码识别

上一篇: windows下python模块安装
下一篇: python 自写常用函数
文章来自: 本站原创
引用通告: 查看所有引用 | 我要引用此文章
Tags:
相关日志: