爬虫-6.2-验证码破解

验证码破解

1. 使用selenium
2. 使用打码平台 （推荐）
3. 使用机器学习破解

打码平台：超级鹰

超级鹰网址： https://www.chaojiying.com/

1. 注册并登录超级鹰账号
2. 查看价格体系
3. 下载官方文档和代码

chaojiying.py 文件

#!/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__':
    # 用户中心>>软件ID 生成一个替换 96001
    chaojiying = Chaojiying_Client('niejeff', 'abcdef123456', '898304')
    # 本地图片文件路径 来替换 a.jpg
    img = open('a.jpg', 'rb').read()
    # 1902 验证码类型
    print(chaojiying.PostPic(img, 1902))

示例：人人网登录破解

import random
import requests
from chaojiying import Chaojiying_Client

# 1， 保存登录成功后的cookie
# 2， 使用保存的cookie进行登录， 登录后获取个人信息
# url = "http://www.renren.com/548819077/profile"

headers = {
    'User-Agent': "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36"
}

# 登录
def login(code):
    # 人人网登录接口：
    url = "http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=202005945581"
    # 参数：
    data = {
        "email": "18566218080",
        "icode": code,
        "origURL": "http://www.renren.com/home",
        "domain": "renren.com",
        "key_id": "1",
        "captcha_type": "web_login",
        "password": "ba83d3541e9a8c60d769ef6a3a8f249cba83d3541e9a8c60d769ef6a3a8f249c",
        "rkey": "ba83d3541e9a8c60d769ef6a3a8f249c",
        "f": "",
    }

    response = session.post(url, data=data, headers=headers)
    result = response.content.decode()
    print(result)


# 获取验证码,并破解
def get_code():
    # 获取验证码接口
    url = "http://icode.renren.com/getcode.do?t=web_login&rnd=%s" % str(random.random())
    res = session.get(url, headers=headers)
    # 下载图片
    with open('code.jpg', 'wb') as fp:
        fp.write(res.content)
        fp.flush()

    # 破解验证码
    chaojiying = Chaojiying_Client(soft_id='898304')
    im = open('code.jpg', 'rb').read()
    result = chaojiying.PostPic(im, 2004)['pic_str']
    print(result)
    return result


# # 人人网个人中心
def get_profile():
    url = "http://www.renren.com/548819077/profile"
    response2 = session.get(url, headers=headers)
    print(response2.text)


if __name__ == '__main__':
    session = requests.session()

    # 获取验证码
    code = get_code()

    # 登录
    login(code)

    # 登录后再访问个人中心
    get_profile()