Python爬虫-requests的cookie登录

requests cookie登录古诗文网（未完成）

import requests
from bs4 import BeautifulSoup
from chaojiying import main
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/99.0.4844.51 Safari/537.36',
'cookie': 'login=flase; wsEmail=761175224%40qq.com; gsw2017user=2540638%7cC5DF54F25A68AD338F7A18407732DF23; login=flase; wxopenid=defoaltid; gswZhanghao=761175224%40qq.com; gswEmail=761175224%40qq.com; Hm_lvt_9007fab6814e892d3020a64454da5a55=1646752892,1646793777; Hm_lpvt_9007fab6814e892d3020a64454da5a55=1646793777; ASP.NET_SessionId=q12om5f0euy3v0z0f01eeabx',
'referer': 'https://so.gushiwen.cn/user/login.aspx?from=http://so.gushiwen.cn/user/collect.aspx',
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'zh-TW,zh;q=0.9,en-US;q=0.8,en;q=0.7,zh-CN;q=0.6',
'cache-control': 'max-age=0',
'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="99", "Google Chrome";v="99"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': 'Windows',
'sec-fetch-dest': 'document',
'sec-fetch-mode': 'navigate',
'sec-fetch-site': 'same-origin',
'sec-fetch-user': '?1',
'upgrade-insecure-requests': '1',
}

response=requests.get(url=url,headers=headers)

content=response.text

soup=BeautifulSoup(content,'lxml')

# __VIEWSTATE: 3RNZfUcIoj4/qh3a2bOP8DhcyqMJ9vW9GjbCrmcXJyHCMaRipEv6Tz7+YU/kC/n9iAiwyoJBnaYunv3QfRng8PESVoy15kRQcDXVZRTnP9RyB+9xJ/tOXBjX1RY=

# __VIEWSTATEGENERATOR: C93BE1AE

# from: http://so.gushiwen.cn/user/collect.aspx

# email: 761175224@qq.com

# pwd: 321123123

# code: qwe

# denglu: 登录

viewstate=soup.select('#__VIEWSTATE')[0].attrs.get('value')

viewstategenerator=soup.select('#__VIEWSTATEGENERATOR')[0].attrs.get('value')

code=soup.select('#imgCode')[0].attrs.get('src')
code_url = 'https://so.gushiwen.cn' + code

import urllib.request
urllib.request.urlretrieve(url=code_url,filename='code.jpg')


code_name=main()

post_url='https://so.gushiwen.cn/user/login.aspx?from=http%3a%2f%2fso.gushiwen.cn%2fuser%2fcollect.aspx'

post_data={
'__VIEWSTATE': viewstate,
'__VIEWSTATEGENERATOR': viewstategenerator,
'from': 'http://so.gushiwen.cn/user/collect.aspx',
'email': '761175224@qq.com',
'pwd': 'd761175224',
'code': code_name,
'denglu': '登录',
}
response_post=session.post(url=post_url,headers=headers,data=post_data)
content_post=response_post.text

with open('gushiwen.html','w',encoding= ' utf-8')as fp:
fp.write(content_post)

这里有个注意事项，在上面验证码请求的url和下面点击登录的url是分开的，相当于请求了两次，所以会出现验证码错误的情况，这里用到requests里面有一个方法 session（） ，通过session的返回值，就能使请求变成一个对象。
所以要用：

session=requests.session()

response_code=session.get(code_url)

content_code=response_code.content

with open('yanzhengma.jpg','wb')as fp:
    fp.write(content_code)

代替：

import urllib.request
urllib.request.urlretrieve(url=code_url,filename='code.jpg')

完整代码：

import requests
from bs4 import BeautifulSoup
from chaojiying import main
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/99.0.4844.51 Safari/537.36',
    'cookie': 'login=flase; wsEmail=761175224%40qq.com; gsw2017user=2540638%7cC5DF54F25A68AD338F7A18407732DF23; login=flase; wxopenid=defoaltid; gswZhanghao=761175224%40qq.com; gswEmail=761175224%40qq.com; Hm_lvt_9007fab6814e892d3020a64454da5a55=1646752892,1646793777; Hm_lpvt_9007fab6814e892d3020a64454da5a55=1646793777; ASP.NET_SessionId=q12om5f0euy3v0z0f01eeabx',
    'referer': 'https://so.gushiwen.cn/user/login.aspx?from=http://so.gushiwen.cn/user/collect.aspx',
    'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
    'accept-encoding': 'gzip, deflate, br',
    'accept-language': 'zh-TW,zh;q=0.9,en-US;q=0.8,en;q=0.7,zh-CN;q=0.6',
    'cache-control': 'max-age=0',
    'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="99", "Google Chrome";v="99"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': 'Windows',
    'sec-fetch-dest': 'document',
    'sec-fetch-mode': 'navigate',
    'sec-fetch-site': 'same-origin',
    'sec-fetch-user': '?1',
    'upgrade-insecure-requests': '1',
}

response=requests.get(url=url,headers=headers)

content=response.text

soup=BeautifulSoup(content,'lxml')

# __VIEWSTATE: 3RNZfUcIoj4/qh3a2bOP8DhcyqMJ9vW9GjbCrmcXJyHCMaRipEv6Tz7+YU/kC/n9iAiwyoJBnaYunv3QfRng8PESVoy15kRQcDXVZRTnP9RyB+9xJ/tOXBjX1RY=
# __VIEWSTATEGENERATOR: C93BE1AE
# from: http://so.gushiwen.cn/user/collect.aspx
# email: 761175224@qq.com
# pwd: 321123123
# code: qwe
# denglu: 登录

viewstate=soup.select('#__VIEWSTATE')[0].attrs.get('value')

viewstategenerator=soup.select('#__VIEWSTATEGENERATOR')[0].attrs.get('value')

code=soup.select('#imgCode')[0].attrs.get('src')
code_url = 'https://so.gushiwen.cn' + code

session=requests.session()

response_code=session.get(code_url)

content_code=response_code.content

with open('yanzhengma.jpg','wb')as fp:
    fp.write(content_code)

code_name=main()

post_url='https://so.gushiwen.cn/user/login.aspx?from=http%3a%2f%2fso.gushiwen.cn%2fuser%2fcollect.aspx'

post_data={
    '__VIEWSTATE': viewstate,
    '__VIEWSTATEGENERATOR': viewstategenerator,
    'from': 'http://so.gushiwen.cn/user/collect.aspx',
    'email': '761175224@qq.com',
    'pwd': 'd761175224',
    'code': code_name,
    'denglu': '登录',
}
response_post=session.post(url=post_url,headers=headers,data=post_data)
content_post=response_post.text

with open('gushiwen.html','w',encoding= ' utf-8')as fp:
    fp.write(content_post)

验证码我直接引入了超级鹰打码平台的接口，但是要先把验证码图片保存到本地才能识别，不知道有没有直接识别的方法。

ps：运行出来并没有进入到登陆后界面，开始以为是需要cookie的原因，但是加了cookie也不行，后来又加了所有的请求头信息也不行。可能是cookie没找对，也可能还有别的反爬手段。总之这个爬取就是半成品，等哪天顿悟了再回来。