import requests
from lxml import etree
import urllib.request
url = 'https://so.gushiwen.cn/user/login.aspx?from=http://so.gushiwen.cn/user/collect.aspx'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36 Edg/96.0.1054.62',
}
res = requests.get(url=url,headers=headers)
tree = etree.HTML(res.text)
# print(tree)
viewState = tree.xpath('//input[@id="__VIEWSTATE"]//@value')
# print(viewState[0])
viewStateGenerator = tree.xpath('//input[@id="__VIEWSTATEGENERATOR"]//@value')
# print(viewStateGenerator[0])
imgCode = tree.xpath('//img[@id="imgCode"]//@src')
# print(imgCode[0])
code_url = 'https://so.gushiwen.cn' + imgCode[0]
# print(code_url)
#urllib.request.urlretrieve(code_url,'code.jpg') 改成通过session获取，保证验证码和点击登录是在同一个请求
session = requests.session()
# 都使用session
rescode = session.get(code_url)
conCode = rescode.content
with open('code.jpg','wb')as fp:
fp.write(conCode)
codeInput = input('请输入你的验证码')
login_url = 'https://so.gushiwen.cn/user/login.aspx?from=http%3a%2f%2fso.gushiwen.cn%2fuser%2fcollect.aspx'
loginData = {
'__VIEWSTATE': viewState[0],
'__VIEWSTATEGENERATOR': viewStateGenerator[0],
'from': 'http://so.gushiwen.cn/user/collect.aspx',
'email': '[email protected]',
'pwd': 'sgj191026@#',
'code': codeInput,
'denglu': '登录',
}
loginRes = session.post(url=login_url,data=loginData,headers=headers)
loginContent = loginRes.text
file = open('loginSuccess.html', 'w',encoding='utf-8')
file.write(loginContent)
标签：code,登录,url,gushiwen,二维码,session,print,aspx,古诗词 From： https://www.cnblogs.com/sgj191024/p/17740967.html