古诗文网简介

古诗文网登录界面
模拟登录两大难点
- __VIEWSTATE、__VIEWSTATEGENERATOR两个动态参数
- 验证码

python登录

1、解析登录界面，获取__VIEWSTATE、__VIEWSTATEGENERATOR参数
2、获取登陆界面验证码图片，输入验证码
3、模拟登录
**要使用requests.session方法，访问同一个界面。防止在进行验证码下载时页面刷新，post请求网页更改**

import requests
from bs4 import BeautifulSoup
import urllib

# 登录界面的url
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/117.0.0.0 Safari/537.36'}

# 获取网页源码
response = requests.get(url=url, headers=headers)
content = response.text

# 解析页面源码
soup = BeautifulSoup(content, 'lxml')
# 获取__VIEWSTATE
viewsate = soup.select('#__VIEWSTATE')[0].attrs.get('value')
# 获取__VIEWSTATEGENERATOR
viewsate_generator = soup.select('#__VIEWSTATEGENERATOR')[0].attrs.get('value')
# 获取验证码
Verification_src = soup.select('#imgCode')[0].attrs.get('src')
Verification_url = 'https://so.gushiwen.cn' + Verification_src

# 保存图片到本地，查看图片，在输入框输入验证码
# 不能使用urllib.request.urlretrieve，会刷新界面，
# urllib.request.urlretrieve(url=Verification_url, filename='./practice_088_古诗文网/Verification.jpg')
session = requests.session()
response = session.get(Verification_url)
with open('./practice_088_古诗文网/Verification.jpg', 'wb') as fp:
    fp.write(response.content)

# 输入验证码 
code_name = input("请输入验证码：")


# 登录网站
url_post = "https://so.gushiwen.cn/user/login.aspx?from=http%3a%2f%2fso.gushiwen.cn%2fuser%2fcollect.aspx"
data_post = {'__VIEWSTATE': viewsate,
            '__VIEWSTATEGENERATOR': viewsate_generator,
            'from': 'http://so.gushiwen.cn/user/collect.aspx',
            'email': '12345678@qq.com',
            'pwd': '12345678',
            'code': code_name,
            'denglu': '登录'}

# requests.session
response_post = session.post(url=url_post, data=data_post, headers=headers)
content_post = response_post.text

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