简单Python3爬虫程序（3）进阶：登录、解压缩、cookies

import gzip
import re
import http.cookiejar
import urllib.request
import urllib.parse

def getXSRF(data):
    cer = re.compile('name=\"_xsrf\" value=\"(.*)\"', flags = 0)
    strlist = cer.findall(data)
    return strlist[0]

def getOpener(head):
    # deal with the Cookies
    cj = http.cookiejar.CookieJar()
    pro = urllib.request.HTTPCookieProcessor(cj)
    opener = urllib.request.build_opener(pro)
    header = []
    for key, value in head.items():
        elem = (key, value)
        header.append(elem)
    opener.addheaders = header
    return opener
header = {
    'Connection': 'Keep-Alive',
    'Accept': 'text/html, application/xhtml+xml, */*',
    'Accept-Language': 'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko',
    'Accept-Encoding': 'gzip, deflate',
    'Host': 'www.zhihu.com',
    'DNT': '1'
}

url = 'http://www.zhihu.com/'
opener = getOpener(header)
op = opener.open(url)
data = op.read()
data = ungzip(data)     # 解压
_xsrf = getXSRF(data.decode())

url += 'login/email'
id = '账号'
password = '密码'
postDict = {
        '_xsrf':_xsrf,
        'email': id,
        'password': password,
        'rememberme': 'y'
}
postData = urllib.parse.urlencode(postDict).encode()
op = opener.open(url,data=postData)
data = op.read()
data = ungzip(data)
saveFile(data)
print(data.decode())

其中的

saveFile

和解压函数

ungzip

请看：简单Python3爬虫程序（5）

（wtf，sb了一下，把自己的用户名密码都发上来了，还好我的文章没人看，这个时候反而庆幸了。。。）