3-爬虫-模拟登录图片验证码处理

Posted 2020-12-14 wgwg

模拟登录

• 验证码的识别
  • 线上的打码平台
    • 超级鹰
      • url：https://www.chaojiying.com/about.html
      • 使用流程：
        • 注册：注册一个用户中心的账号
        • 登录：用户中心的身份
          • 创建一个软件ID： 899370
          • 下载示例代码
    • 云打码
• 动态变化的请求参数
  • 动态变化请求参数的处理
    • 一般会隐藏在前台页面中
    • 是由相关的js函数动态生成

超级鹰的示例代码

#!/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()


if __name__ == ‘__main__‘:
    chaojiying = Chaojiying_Client(‘超级鹰用户名‘, ‘超级鹰用户名的密码‘, ‘96001‘)    #用户中心>>软件ID 生成一个替换 96001
    im = open(‘a.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()

超级鹰示例代码

识别古诗文网中的验证码图片

import requests
from lxml import etree
headers = {
    ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36‘
}



def transdform_code_img(img_path,img_type):
    chaojiying = Chaojiying_Client(‘超级鹰账号‘, ‘密码‘, ‘软件ID‘)    #用户中心>>软件ID 生成一个替换 96001
    im = open(img_path, ‘rb‘).read()                                                    #本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
    return chaojiying.PostPic(im, img_type)[‘pic_str‘]


main_url = ‘https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx‘
page_text = requests.get(url=main_url,headers=headers).text
#解析验证码图片地址
tree = etree.HTML(page_text)
img_src = ‘https://so.gushiwen.org‘+tree.xpath(‘//*[@id="imgCode"]/@src‘)[0]
img_data = requests.get(url=img_src,headers=headers).content
with open(‘./code.jpg‘,‘wb‘) as fp:
    fp.write(img_data)


transdform_code_img(‘./code.jpg‘,1004)

实现模拟登录

sess = requests.Session()

main_url = ‘https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx‘
page_text = sess.get(url=main_url,headers=headers).text
#解析验证码图片地址
tree = etree.HTML(page_text)
img_src = ‘https://so.gushiwen.org‘+tree.xpath(‘//*[@id="imgCode"]/@src‘)[0]
img_data = sess.get(url=img_src,headers=headers).content
with open(‘./code.jpg‘,‘wb‘) as fp:
    fp.write(img_data)

__VIEWSTATE = tree.xpath(‘//*[@id="__VIEWSTATE"]/@value‘)[0]
__VIEWSTATEGENERATOR = tree.xpath(‘//*[@id="__VIEWSTATEGENERATOR"]‘)[0]    
code_text = transdform_code_img(‘./code.jpg‘,1004)
print(code_text)

login_url = ‘https://so.gushiwen.org/user/login.aspx?from=http%3a%2f%2fso.gushiwen.org%2fuser%2fcollect.aspx‘
data = {
    ‘__VIEWSTATE‘: __VIEWSTATE,
    ‘__VIEWSTATEGENERATOR‘: __VIEWSTATEGENERATOR,
    ‘from‘: ‘http://so.gushiwen.org/user/collect.aspx‘,
    ‘email‘: ‘账号‘,
    ‘pwd‘: ‘密码‘,
    ‘code‘: code_text,
    ‘denglu‘: ‘登录‘,
}
login_page_text = sess.post(url=login_url,headers=headers,data=data).text
with open(‘./login.html‘,‘w‘,encoding=‘utf-8‘) as fp:
    fp.write(login_page_text)