驗證碼破解


一些網站會在正常的賬號密碼認證之外加一些驗證碼,以此來明確地區分人/機行為,從一定程度上達到反爬的效果.

一,圖片驗證碼

對於普通圖片驗證碼,tesserocr庫就可以識別:

tesserocr庫詳見: https://blog.csdn.net/qq_39208536/article/details/80755400

我們還可以使用第三方的接口識別

如雲打碼平台:  http://www.yundama.com/index.html

注冊賬號之后更具其提供的API接口使用!

下載的原文件:

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

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

# 用戶名
username    = 'username'

# 密碼
password    = 'password'                            

# 軟件ID,開發者分成必要參數。登錄開發者后台【我的軟件】獲得!
appid       = 1                                     

# 軟件密鑰,開發者分成必要參數。登錄開發者后台【我的軟件】獲得!
appkey      = '22cc5376925e9387a23cf797cb9ba745'    

# 圖片文件
filename    = 'getimage.jpg'                        

# 驗證碼類型,# 例:1004表示4位字母數字,不同類型收費不同。請准確填寫,否則影響識別率。在此查詢所有類型 http://www.yundama.com/price.html
codetype    = 1004

# 超時時間,秒
timeout     = 60                                    

# 檢查
if (username == 'username'):
    print('請設置好相關參數再測試')
else:
    # 初始化
    yundama = YDMHttp(username, password, appid, appkey)

    # 登陸雲打碼
    uid = yundama.login();
    print('uid: %s' % uid)

    # 查詢余額
    balance = yundama.balance();
    print('balance: %s' % balance)

    # 開始識別,圖片路徑,驗證碼類型ID,超時時間(秒),識別結果
    cid, result = yundama.decode(filename, codetype, timeout);
    print('cid: %s, result: %s' % (cid, result))

######################################################################
python3示例

ex: 人人網在連續輸錯5次密碼之后,就會添加驗證碼登陸,使用爬蟲登陸人人網,獲取個人主頁

示例類:

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.進行登陸操作,服務器就會對當前用戶 創建一個cookie對象(存儲當前的用戶狀態信息,以及身份標識)
# 2. 進行個人主頁的請求(攜帶步驟1中創建的cookie), 獲取當前用戶個人主頁的頁面數據


def get_code(img_path):
    # 用戶名
    username = 'EksYiQiang'
    # 密碼
    password = 'xyq19990113'                            

    # 軟件ID,開發者分成必要參數。登錄開發者后台【我的軟件】獲得!
    appid = 6041                                     

    # 軟件密鑰,開發者分成必要參數。登錄開發者后台【我的軟件】獲得!
    appkey = 'c9f0265f96d9e97118aeb8eff629da64'    

    # 圖片文件
    filename = img_path                        

    # 驗證碼類型,# 例:1004表示4位字母數字,不同類型收費不同。請准確填寫,否則影響識別率。在此查詢所有類型 http://www.yundama.com/price.html
    codetype = 2004

    # 超時時間,秒
    timeout = 60                                    

    # 檢查
    if (username == 'username'):
        print('請設置好相關參數再測試')
    else:
        # 初始化
        yundama = YDMHttp(username, password, appid, appkey)

        # 登陸雲打碼
        uid = yundama.login();
        print('uid: %s' % uid)

        # 查詢余額
        balance = yundama.balance();
        print('balance: %s' % balance)

        # 開始識別,圖片路徑,驗證碼類型ID,超時時間(秒),識別結果
        cid, result = yundama.decode(filename, codetype, timeout);
        print('cid: %s, result: %s' % (cid, result))
    return result

# 登陸,先獲取登陸頁面的圖片驗證碼
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)

 #登錄請求的url(通過抓包工具獲取)
login_url = "http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=2018922149650"
session = requests.session()  # #創建一個session對象,該對象會自動將請求中的cookie進行存儲和攜帶
data = {
    "rkey":"d818910ba02fe92c2e1835721e2ca2e2",
    "password":"1239e82545fec64c0f6358e13e5ee2a5b281c1af4098e0251dcd8c13455f5056",
    "origURL":"http://www.renren.com/home",
    "key_id": "1",
    "icode":code_content,  # 把驗證碼發過來
    "f":"",
    "email": "18829037944",
    "domain": "renren.com",
    "captcha_type": "web_login",
}
session.post(url=login_url, data=data, headers=headers) #  使用session發送請求,目的是為了將session保存該次請求中的cookie

get_url = "http://www.renren.com/968520666/profile"
#  再次使用session進行請求的發送,該次請求中已經攜帶了cookie
response = session.get(url=get_url, headers=headers)
#設置響應內容的編碼格式
response.encoding = 'utf-8'
page_text = response.text

#將響應內容寫入文件
with open('./renren77777.html','w', encoding="utf-8") as fp:
    fp.write(page_text)
    print("over")

二,滑動驗證碼

https://www.cnblogs.com/linhaifeng/articles/7802150.html

 


免責聲明!

本站轉載的文章為個人學習借鑒使用,本站對版權不負任何法律責任。如果侵犯了您的隱私權益,請聯系本站郵箱yoyou2525@163.com刪除。



 
粵ICP備18138465號   © 2018-2025 CODEPRJ.COM