爬虫模拟古诗文网登录（识别验证码、模拟登录）2023/1/12可用

爬虫模拟古诗文网登录（识别验证码、模拟登录）2023/1/12可用

全部代码如下，注释交代了具体步骤

import requests
from lxml import etree
import ddddocr# 1、获取验证码
session = requests.Session()
login_url = ".aspx?from=.aspx"
headers = {'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36 Edg/108.0.1462.76"
}
login_page_text = (url=login_url, headers=headers).text
tree = etree.HTML(login_page_text)
code_img_src = "" + tree.xpath('//*[@id="imgCode"]/@src')[0]
# 2、将验证码图片保存到本地
img_data = (url=code_img_src, headers=headers).content
with open('./codeImg.jpg', 'wb') as fp:fp.write(img_data)
# 3、利用ddddocr库进行识别验证码
ocr = ddddocr.DdddOcr()
with open('./codeImg.jpg', 'rb') as fp:img_bytes = fp.read()
res = ocr.classification(img_bytes)
print("---------------------------------------------------")
print('识别出的验证码为：' + res)
# 4、进行模拟登录
viewstate = tree.xpath('//*[@id="__VIEWSTATE"]/@value')[0] # 这个参数是动态的，全局搜索在源码中找到
data = {'__VIEWSTATE': viewstate,'__VIEWSTATEGENERATOR': ' C93BE1AE','from': '.aspx','email': '************',  # 你的古诗文网账号'pwd': '*********',  # 你的古诗文网密码'code': res,'denglu': '登录',
}
response = session.post(url=login_url, data=data, headers=headers)
print("状态码：", response.status_code)
# 5、保存成功登录后的个人信息界面的源码
response_text = 
with open('./古诗文网模拟登录.html', 'w', encoding='utf-8') as fp:fp.write(response_text)

我的运行结果：