验证码

验证码

某些网站访问需要验证码，并且在访问过于频繁的时候也会出现验证码。这时候验证码识别就出现了。

验证码识别

1. 人工识别
2. 打码平台 ，付费（人工+机器学习）
3. 机器学习

下面以云打码平台的使用为例

云打码平台的使用

1. 对携带验证码的页面数据进行抓取
2. 可以将页面数据中验证码进行解析，验证码图片下载到本地
3. 可以将验证码图片提交给三方平台进行识别，返回验证码图片上的数据值
   1. 云打码平台：http://www.yundama.com/demo.html
      1. 在官网中进行注册（普通用户和开发者用户）
         1. 使用普通账户充值
      2. 登录开发者用户：
         1. 实例代码的下载（开发文档-》调用实例及最新的DLL-》PythonHTTP实例下载）
         2. 创建一个软件：我的软件-》添加新的软件
         3. 使用示例代码中的源码文件中的代码进行修改，让其识别验证码图片中的数据值

人人网登录示例

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

import http.client, mimetypes, urllib, json, time, requests
from lxml import etree


class YDMHttp:
    apiurl = 'http://api.yundama.com/api.php'
    username = ''
    password = ''
    appid = ''
    appkey = ''

    def __init__(self, username, password, appid, appkey):
        self.username = username
        self.password = password
        self.appid = str(appid)
        self.appkey = appkey

    def request(self, fields, files=[]):
        response = self.post_url(self.apiurl, fields, files)
        response = json.loads(response)
        return response

    def balance(self):
        data = {'method': 'balance', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey}
        response = self.request(data)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['balance']
        else:
            return -9001

    def login(self):
        data = {'method': 'login', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey}
        response = self.request(data)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['uid']
        else:
            return -9001

    def upload(self, filename, codetype, timeout):
        data = {'method': 'upload', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey, 'codetype': str(codetype), 'timeout': str(timeout)}
        file = {'file': filename}
        response = self.request(data, file)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['cid']
        else:
            return -9001

    def result(self, cid):
        data = {'method': 'result', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey, 'cid': str(cid)}
        response = self.request(data)
        return response and response['text'] or ''

    def decode(self, filename, codetype, timeout):
        cid = self.upload(filename, codetype, timeout)
        if (cid > 0):
            for i in range(0, timeout):
                result = self.result(cid)
                if (result != ''):
                    return cid, result
                else:
                    time.sleep(1)
            return -3003, ''
        else:
            return cid, ''

    def report(self, cid):
        data = {'method': 'report', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey, 'cid': str(cid), 'flag': '0'}
        response = self.request(data)
        if (response):
            return response['ret']
        else:
            return -9001

    def post_url(self, url, fields, files=[]):
        for key in files:
            files[key] = open(files[key], 'rb')
        res = requests.post(url, files=files, data=fields)
        return res.text


def get_code(filename, codetype):
    """

    :param filename: 文件路径
    :param codetype: 打码类型,例：1004表示4位字母数字，不同类型收费不同。请准确填写，否则影响识别率。
    在此查询所有类型 http://www.yundama.com/price.html
    :return:
    """
    # 用户名
    USERNAEM = 'xxx'
    # 密码
    PASSWORD = 'xxx'
    # 软件ＩＤ，开发者分成必要参数。登录开发者后台【我的软件】获得！
    appid = 8411
    # 软件密钥，开发者分成必要参数。登录开发者后台【我的软件】获得！
    appkey = '584a13ed22a2a14a391296c409493ed4'
    # 超时时间，秒
    timeout = 60

    # 检查
    if (USERNAEM == 'username'):
        print('请设置好相关参数再测试')
    else:
        # 初始化
        yundama = YDMHttp(USERNAEM, PASSWORD, appid, appkey)

        # 登陆云打码
        uid = yundama.login()
        print('uid: %s' % uid)

        # 查询余额
        balance = yundama.balance()
        print('balance: %s' % balance)

        # 开始识别，图片路径，验证码类型ID，超时时间（秒），识别结果
        cid, result = yundama.decode(filename, codetype, timeout)
        print('cid: %s, result: %s' % (cid, result))
        return cid, result


FILENAME = 'tmp.jpg'
# get_code(filename, 1000)
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36',
}
code_XP = '//*[@id="verifyPic_login"]/@src'

start_url = 'http://www.renren.com/SysHome.do'

session = requests.Session()
res1 = session.get(start_url, headers=headers)
tree = etree.HTML(res1.text)
icode_url = tree.xpath(code_XP)

if icode_url:
    icode_url = icode_url[0]
    with open(FILENAME, 'wb') as f:
        f.write(session.get(icode_url, headers=headers).content)
    code = get_code(FILENAME, 1000)[1]
else:
    code = ''
url2 = 'http://login.renren.com/ajax/getEncryptKey'
res2 = session.get(url2, headers=headers)
# print(res2.json())
rkey = res2.json().get('rkey')

url3 = 'http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=201964034544 '
data = {
    "email": "username",
    "icode": code,
    "origURL": "http://www.renren.com/home",
    "domain": "renren.com",
    "key_id": "1",
    "captcha_type": "web_login",
    "password": "password",  # 通过抓包获取加密后的密码
    "rkey": rkey,
    "f": "",
}

res3 = session.post(url3, headers=headers, data=data)
detail_url = 'http://www.renren.com/289676607/profile'  # 个人页面
page_text = session.get(url=detail_url, headers=headers).text
with open('./renren.html', 'w', encoding='utf-8') as fp:
    fp.write(page_text)