验证码破解

一些网站会在正常的账号密码认证之外加一些验证码，以此来明确地区分人/机行为，从一定程度上达到反爬的效果.

一,图片验证码

对于普通图片验证码,tesserocr库就可以识别:

tesserocr库详见: https://blog.csdn.net/qq_39208536/article/details/80755400

我们还可以使用第三方的接口识别

如云打码平台: http://www.yundama.com/index.html

注册账号之后更具其提供的API接口使用!

下载的原文件:

import http.client, mimetypes, urllib, json, time, requests

######################################################################

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

######################################################################

# 用户名
username    = 'username'

# 密码
password    = 'password'                            

# 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       = 1                                     

# 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      = '22cc5376925e9387a23cf797cb9ba745'    

# 图片文件
filename    = 'getimage.jpg'                        

# 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    = 1004

# 超时时间，秒
timeout     = 60                                    

# 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))

######################################################################

python3示例

ex: 人人网在连续输错5次密码之后,就会添加验证码登陆,使用爬虫登陆人人网,获取个人主页

示例类:

import http.client, mimetypes, urllib, json, time, requests

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

python3示例

import requests
from lxml import etree

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.67 Safari/537.36"
}
# 1.进行登陆操作，服务器就会对当前用户 创建一个cookie对象(存储当前的用户状态信息，以及身份标识)
# 2. 进行个人主页的请求（携带步骤1中创建的cookie）， 获取当前用户个人主页的页面数据


def get_code(img_path):
    # 用户名
    username = 'EksYiQiang'
    # 密码
    password = 'xyq19990113'                            

    # 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 = 6041                                     

    # 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 = 'c9f0265f96d9e97118aeb8eff629da64'    

    # 图片文件
    filename = img_path                        

    # 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 = 2004

    # 超时时间，秒
    timeout = 60                                    

    # 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

# 登陆,先获取登陆页面的图片验证码
url = "http://www.renren.com/"
page_text = requests.get(url=url, headers=headers).text
tree = etree.HTML(page_text)
codeImg_url = tree.xpath('//*[@id="verifyPic_login"]/@src')[0]
print(codeImg_url)
img_content = requests.get(url=codeImg_url, headers=headers).content
with open("code_img.jpg", "wb") as f:
    f.write(img_content)
    
code_content = get_code("code_img.jpg")
print(code_content)

 #登录请求的url（通过抓包工具获取）
login_url = "http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=2018922149650"
session = requests.session()  # #创建一个session对象，该对象会自动将请求中的cookie进行存储和携带
data = {
    "rkey":"d818910ba02fe92c2e1835721e2ca2e2",
    "password":"1239e82545fec64c0f6358e13e5ee2a5b281c1af4098e0251dcd8c13455f5056",
    "origURL":"http://www.renren.com/home",
    "key_id": "1",
    "icode":code_content,  # 把验证码发过来
    "f":"",
    "email": "18829037944",
    "domain": "renren.com",
    "captcha_type": "web_login",
}
session.post(url=login_url, data=data, headers=headers) #  使用session发送请求，目的是为了将session保存该次请求中的cookie

get_url = "http://www.renren.com/968520666/profile"
#  再次使用session进行请求的发送，该次请求中已经携带了cookie
response = session.get(url=get_url, headers=headers)
#设置响应内容的编码格式
response.encoding = 'utf-8'
page_text = response.text

#将响应内容写入文件
with open('./renren77777.html','w', encoding="utf-8") as fp:
    fp.write(page_text)
    print("over")

二,滑动验证码

https://www.cnblogs.com/ctztake/p/8313605.html

一,图片验证码

二,滑动验证码

猜你喜欢