爬虫day 04(通过登录去爬虫 解决django的csrf_token)

Posted 2020-10-14 窃语

#通过登录去爬虫
#首先要有用户名和密码
import urllib.request
import http.cookiejar
from lxml import etree
head = {
    ‘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‘
}
# 给opener加上cookie
def makeMyOpener(head):
    cj = http.cookiejar.CookieJar()
    opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj))
    header = []
    for key, value in head.items():
        elem = (key, value)
        header.append(elem)
    opener.addheaders = header
    return opener
# 爬自己的页面 
oper = makeMyOpener(head)
uop = oper.open(‘http://127.0.0.1:8000/index/loginHtml/‘, timeout = 1000)
data = uop.read()
html = data.decode()
# lxml提取 csrfmiddlewaretoken 

 selector = etree.HTML(html) links = selector.xpath(‘//form/input[@name="csrfmiddlewaretoken"]/@value‘) for link in links: csrfmiddlewaretoken = link print(link) url = ‘http://127.0.0.1:8000/index/login/‘ datas = {‘csrfmiddlewaretoken‘:csrfmiddlewaretoken,‘email‘:‘aa‘,‘pwd‘:‘aa‘}
# 必须要把字符串改为二进制流
data_encoded = urllib.parse.urlencode(datas).encode(encoding=‘utf-8‘)
response = oper.open(url,data_encoded)
content = response.read()
html = content.decode()
print(html)