模拟登陆：验证码处理
模拟登陆：
实现流程：对登陆页面进行请求，从请求到的页面源码中解析下载验证码图片
使用打码平台对验证码进行识别
基于登陆按钮发起一个post请求（处理参数）
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。
- 使用云打码平台识别验证码
- 云打码平台处理验证码的实现流程：
- 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： - 1.在官网中进行注册（普通用户和开发者用户） - 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
相关代码展示：
import requests from lxml import etree from urllib import request headers={"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36"} 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 ###################################################################### session = requests.Session() data_url="https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx" data_msg=session.get(url=data_url,headers=headers).text tree = etree.HTML(data_msg) VIEWSTATE=tree.xpath('//*[@id="__VIEWSTATE"]/@value')[0] VIEWSTATEGENERATOR=tree.xpath('//*[@id="__VIEWSTATEGENERATOR"]/@value')[0] image_url="https://so.gushiwen.org"+tree.xpath('//*[@id="imgCode"]/@src')[0] image_msg=session.get(url=image_url,headers=headers).content with open("./code.jpg","wb") as f: f.write(image_msg) def get_code_data(filepath,type): result=None # 用户名 (普通用户的用户名） username = '******' # 密码 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 = **** # 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 = '*********************' # 图片文件 filename = filepath # 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 = 40 # 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 code=get_code_data("./code.jpg",1004) login_url="https://so.gushiwen.org/user/login.aspx?from=http%3a%2f%2fso.gushiwen.org%2fuser%2fcollect.aspx" data={ "__VIEWSTATE": VIEWSTATE, "__VIEWSTATEGENERATOR": VIEWSTATEGENERATOR, "from": "http://so.gushiwen.org/user/collect.aspx", "email": "675922036@qq.com", "pwd": "songping218", "code": code, "denglu": "登录", } page_msg=session.post(url=login_url,data=data,headers=headers).text msg = session.get(url="https://so.gushiwen.org/user/collect.aspx",headers=headers).text print(msg)
