爬虫，识别古诗文网登录验证码，并登录

b站教学视频大多推荐使用第三方验证码识别平台，经过弹幕启发，初步了解了可以安装ddddocr软件包进行验证码识别

代码如下

import  requests
import ddddocr#导入ddddocr
from lxml import etree
import time
#ua伪装
header={
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36 Edg/124.0.0.0'

}
url ='https://so.gushiwen.cn/user/login.aspx?from=http://so.gushiwen.cn/user/collect.'
# response = requests.get(url=url,headers=header)#请求后验证码改变所以要用session
session=requests.session()
response =session.get(url)
content_code=response.content
# print(content)
tree =etree.HTML(content_code)
#xpath获取内容
viewstate=tree.xpath('/html/body/form[1]/div[1]/input/@value')
# print(viewstate)
viewstategen=tree.xpath('/html/body/form[1]/div[2]/input/@value')
# print(viewstategen)
#获取验证码，并进行本地下载
code_img='https://so.gushiwen.cn/'+tree.xpath('//*[@id="imgCode"]/@src')[0]
img_data=session.get(url=code_img,headers=header).content #二进制格式
with open('./code.jpg','wb') as fp:
    fp.write(img_data)
#读取验证码图片
with open('./code.jpg','rb') as  f:
    img_bytes=f.read()
#进行识别
ocr =ddddocr.DdddOcr()
res =ocr.classification(img_bytes)
print(res)

#登录操作
url2='https://so.gushiwen.cn/user/login.aspx?from=http%3a%2f%2fso.gushiwen.cn%2fuser%2fcollect.aspx'
data_post ={
'__VIEWSTATE':viewstate,
'__VIEWSTATEGENERATOR':viewstategen,
'fro' : 'http:// so.gushiwen.cn / user / collect.aspx',
'email': '',#你自己的账户密码
'pwd':'',
'code': res,
'denglu': '登录'
}

response_post=session.post(url=url2,headers=header,data=data_post)
content_post=response_post.text
with open('gushiwen.html','w',encoding='utf-8')as fp:
    fp.write(content_post)
print(content_post)