引入
- 相关的门户网站在进行登录的时候，如果用户连续登录的次数超过3次或者5次的时候，就会在登录页中动态生成验证码。通过验证码达到分流和反爬的效果
- 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- 云打码平台：(具体云代码平台接口代码见百度云,链接: https://pan.baidu.com/s/1utwt70743u2PJP4BErq3ZQ 提取码: kwtu 复制这段内容后打开百度网盘手机App，操作更方便哦)
具体实现代码如下:
1 import http.client, mimetypes, urllib, json, time, requests 2 3 4 class YDMHttp: 5 apiurl = 'http://api.yundama.com/api.php' 6 username = '' 7 password = '' 8 appid = '' 9 appkey = '' 10 11 def __init__(self, username, password, appid, appkey): 12 self.username = username 13 self.password = password 14 self.appid = str(appid) 15 self.appkey = appkey 16 17 def request(self, fields, files=[]): 18 response = self.post_url(self.apiurl, fields, files) 19 response = json.loads(response) 20 return response 21 22 def balance(self): 23 data = {'method': 'balance', 'username': self.username, 'password': self.password, 'appid': self.appid, 24 'appkey': self.appkey} 25 response = self.request(data) 26 if (response): 27 if (response['ret'] and response['ret'] < 0): 28 return response['ret'] 29 else: 30 return response['balance'] 31 else: 32 return -9001 33 34 def login(self): 35 data = {'method': 'login', 'username': self.username, 'password': self.password, 'appid': self.appid, 36 'appkey': self.appkey} 37 response = self.request(data) 38 if (response): 39 if (response['ret'] and response['ret'] < 0): 40 return response['ret'] 41 else: 42 return response['uid'] 43 else: 44 return -9001 45 46 def upload(self, filename, codetype, timeout): 47 data = {'method': 'upload', 'username': self.username, 'password': self.password, 'appid': self.appid, 48 'appkey': self.appkey, 'codetype': str(codetype), 'timeout': str(timeout)} 49 file = {'file': filename} 50 response = self.request(data, file) 51 if (response): 52 if (response['ret'] and response['ret'] < 0): 53 return response['ret'] 54 else: 55 return response['cid'] 56 else: 57 return -9001 58 59 def result(self, cid): 60 data = {'method': 'result', 'username': self.username, 'password': self.password, 'appid': self.appid, 61 'appkey': self.appkey, 'cid': str(cid)} 62 response = self.request(data) 63 return response and response['text'] or '' 64 65 def decode(self, filename, codetype, timeout): 66 cid = self.upload(filename, codetype, timeout) 67 if (cid > 0): 68 for i in range(0, timeout): 69 result = self.result(cid) 70 if (result != ''): 71 return cid, result 72 else: 73 time.sleep(1) 74 return -3003, '' 75 else: 76 return cid, '' 77 78 def report(self, cid): 79 data = {'method': 'report', 'username': self.username, 'password': self.password, 'appid': self.appid, 80 'appkey': self.appkey, 'cid': str(cid), 'flag': '0'} 81 response = self.request(data) 82 if (response): 83 return response['ret'] 84 else: 85 return -9001 86 87 def post_url(self, url, fields, files=[]): 88 for key in files: 89 files[key] = open(files[key], 'rb') 90 res = requests.post(url, files=files, data=fields) 91 return res.text
继续封装一个函数,调用这个类并执行其中的代码:
1 def parse_code_img(username, password, appid, appkey, filename, codetype): 2 # 用户名 3 username = username 4 # 密码 5 password = password 6 # 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！ 7 appid = appid 8 # 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！ 9 appkey = appkey 10 # 图片文件 11 filename = filename 12 # 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 13 codetype = codetype 14 # 超时时间，秒 15 timeout = 30 16 17 # 检查 18 if (username == ''): 19 print('请设置好相关参数再测试') 20 else: 21 # 初始化 22 yundama = YDMHttp(username, password, appid, appkey) 23 # 登陆云打码 24 uid = yundama.login() 25 print('uid: %s' % uid) 26 # 查询余额 27 balance = yundama.balance() 28 print('balance: %s' % balance) 29 # 开始识别，图片路径，验证码类型ID，超时时间（秒），识别结果 30 cid, result = yundama.decode(filename, codetype, timeout) 31 print('cid: %s, result: %s' % (cid, result)) 32 return result
之后哪里需要验证码处理将此两段代码复制到一个文件里,调用此文件,执行parse_code_img方法即可获取验证码的文本信息