python模拟（验证码）登录

模拟（验证码）登录流程：

1.验证码的识别，获取验证码图片的文字数据
2.对post请求进行发送（处理请求参数）
3.对响应数据进行持久化存储
示例网站：https://www.nowapi.com/?app=account.login
云打码平台：http://www.chaojiying.com

code.py

#!/usr/bin/env python
# coding:utf-8

import requests
from hashlib import md5

class Chaojiying_Client(object):

    def __init__(self, username, password, soft_id):
        self.username = username
        password = password.encode('utf8')
        self.password = md5(password).hexdigest()
        self.soft_id = soft_id
        self.base_params = {
            'user': self.username,
            'pass2': self.password,
            'softid': self.soft_id,
        }
        self.headers = {
            'Connection': 'Keep-Alive',
            'User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',
        }

    def PostPic(self, im, codetype):
        """
        im: 图片字节
        codetype: 题目类型 参考 http://www.chaojiying.com/price.html
        """
        params = {
            'codetype': codetype,
        }
        params.update(self.base_params)
        files = {'userfile': ('ccc.jpg', im)}
        r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files,
                          headers=self.headers)
        return r.json()

    def ReportError(self, im_id):
        """
        im_id:报错题目的图片ID
        """
        params = {
            'id': im_id,
        }
        params.update(self.base_params)
        r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)
        return r.json()

test.py

# 编码流程：
# 1.验证码的识别，获取验证码图片的文字数据
# 2.对post请求进行发送（处理请求参数）
# 3.对响应数据进行持久化存储
import requests
from lxml import etree

import requests
from hashlib import md5
from code import Chaojiying_Client


# 1、对验证码图片进行捕获和识别
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'
    }
url = 'https://www.nowapi.com/?app=account.login'
page_text = requests.get(url=url,headers=headers).text
tree = etree.HTML(page_text)
code_img_src = tree.xpath('//*[@id="authCodeImg"]/@src')[0]
code_img_data = requests.get(url=code_img_src,headers=headers).content
with open('./code.jpg','wb') as fp:
    fp.write(code_img_data)

# 2、使用云打码平台提供代码进行验证码识别
if __name__ == '__main__':
    chaojiying = Chaojiying_Client('账号', '密码', '927610')  # 用户中心>>软件ID 生成一个替换 96001
    im = open('code.jpg', 'rb').read()  # 本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
    print(chaojiying.PostPic(im, 1902))  # 1902 验证码类型  官方网站>>价格体系 3.4+版 print 后要加()
    result = chaojiying.PostPic(im, 1902)
# 3、post请求的发送（模拟登录）
login_url = 'https://www.nowapi.com/index.php?ajax=1'
data = {
        'usernm':' 账号',
        'passwd': '密码',
        'authcode': result,
        'tourl':'',
        'app':'accountr.aja_login'
}
response = requests.post(url=login_url,headers=headers,data=data)
# 验证请求是否成功（200）成功
print(response.status_code)
login_page_text = response.text
with open('www.nowapi.com','w',encoding='utf-8')as fp:
    fp.write(login_page_text)