验证码处理

方式

1.手动处理

2.云打码平台自动识别验证码

    实现流程：
    -1.对携带验证码的页面数据进行抓取
    -2.可以将验证码图片进行解析，验证码图片下载到本地
    -3.将验证码图片交给第三方进行识别，返回验证码图片上的值
        -云打码平台
        1.进行注册 注册普通用户和开发者用户
        2.登录开发者用户
            1.进行示例代码下载（开发文档》》调用示例及最新的DLL》》pythonhttp示例下载）
            2.创建一个软件（我的软件》》新的软件）
        3.使用示例代码中的源文件代码文件进行修改

代码实现

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

# 调用打码平台，识别验证码
def getCode(codeImg):
    # 用户名
    username    = ‘bobo328410948‘

    # 密码
    password    = ‘bobo328410948‘                            

    # 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       = 6003                                     

    # 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      = ‘1f4b564483ae5c907a1d34f8e2f2776c‘    

    # 图片文件
    filename    = codeImg   # 路径                       

    # 验证码类型，# 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
    codetype    = 3000

    # 超时时间，秒
    timeout     = 20                                   

    # 检查
    if (username == ‘username‘):
        print(‘请设置好相关参数再测试‘)
    else:
        # 初始化
        yundama = YDMHttp(username, 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 result

import requests
from lxml import etree
import json,time,re
#1.对携带验证码的页面数据进行抓取
url = ‘https://accounts.douban.com/login?source=movie‘
# 自定义请求头信息
headers={
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36‘

}
# 将代理IP封装到字典
proxies={
    ‘http‘:‘59.44.43.198:80‘   # 更换代理IP可能会不出现验证码
}
page_text = requests.get(url=url,proxies=proxies).text
#2.可以将验证码图片进行解析，验证码图片下载到本地
tree = etree.HTML(page_text)
codeImg_url = tree.xpath(‘//*[@id="captcha_image"]/@src‘)[0]
#获取验证码图片对应的二进制数据
code_img = requests.get(url=codeImg_url,headers=headers).content
# 获取动态的captcha-id
captcha_id = re.findall(‘<img id="captcha_image".*?id=(.*?)&.*?>‘,page_text,re.S)[0]
with open(‘./code.png‘,‘wb‘)as fp:
    fp.write(code_img)
codeText = getCode(‘./code.png‘)
print(codeText)

# 进行登录操作
post = ‘https://accounts.douban.com/login‘
data={
   ‘source‘:‘movie‘,
    ‘redir‘:‘https://movie.douban.com/‘,
    ‘form_email‘:‘15027900535‘,
    ‘form_password‘:‘[email protected]‘,
    ‘captcha-solution‘:codeText,
    ‘captcha-id‘:captcha_id,
    ‘login‘:‘登录‘
}

print(captcha_id)

login_text = requests.post(url=post,data=data,headers=headers,proxies=proxies).text
with open(‘./log.html‘,‘w‘,encoding=‘utf-8‘)as fp:
    fp.write(login_text)
print(‘ok‘)

原文地址：https://www.cnblogs.com/yuliangkaiyue/p/10022941.html