云打码 古诗文网
# 云打码 代码示例
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): #构造方法 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 ###################################################################### username = 'zhangc' #普通用户 password = 'zc1991' #密码 appid = 7568 #开发者页面软件ID appkey = 'bbb4575c2c541e5fa4fe932ce86774ef' #秘钥
filename = './PythonHTTP调用示例/getimage.jpg' #解码图片路径 # 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 = 1004 timeout = 40 #超时时间 if (username == 'username'): #检查 print('请设置好相关参数再测试') else: yundama = YDMHttp(username, password, appid, appkey) #初始化 uid = yundama.login(); #登陆云打码 print('uid: %s' % uid) #打印账户 balance = yundama.balance(); #查余额 print('balance: %s' % balance) #打印余额 cid, result = yundama.decode(filename, codetype, timeout);# 开始识别，图片路径，验证码类型ID，超时时间（秒），识别结果
print('cid: %s, result: %s' % (cid, result)) #打印结果
# 古诗文网 模拟登陆 处理cookie
import requests from lxml import etree from urllib import request def getCodeText(filename,codetype): result = None username = 'zhangc' password = 'zc1991' appid = 7568 appkey = 'bbb4575c2c541e5fa4fe932ce86774ef' filename = filename codetype = codetype timeout = 40 if (username == 'username'): print('请设置好相关参数再测试') else: yundama = YDMHttp(username, password, appid, appkey) uid = yundama.login(); balance = yundama.balance(); cid, result = yundama.decode(filename, codetype, timeout); return result url = 'https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx' session = requests.Session() # 创建session会话,处理cookie相关反爬机制 headers = { 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36' } page_text = session.get(url=url,headers=headers).text tree = etree.HTML(page_text) code_src = 'https://so.gushiwen.org'+tree.xpath('//*[@id="imgCode"]/@src')[0] #https://so.gushiwen.org #request.urlretrieve(url=code_src,filename='./gushi.jpg') #它有自己的cookie机制 code_img = session.get(url=code_src,headers=headers).content with open('./gushi.jpg','wb') as fp: fp.write(code_img) __VIEWSTATE = tree.xpath('//*[@id="__VIEWSTATE"]/@value')[0] #动态加载 __VIEWSTATEGENERATOR = tree.xpath('//*[@id="__VIEWSTATEGENERATOR"]/@value')[0] #动态加载 code_text = getCodeText('./gushi.jpg',1004) #这里调用识别 data = { "__VIEWSTATE": __VIEWSTATE, "__VIEWSTATEGENERATOR": __VIEWSTATEGENERATOR, "from": "http://so.gushiwen.org/user/collect.aspx", "email": "576951284@qq.com", "pwd": "zhangchen", "code": code_text, "denglu": "登录", } login_url = 'https://so.gushiwen.org/user/login.aspx?from=http%3a%2f%2fso.gushiwen.org%2fuser%2fcollect.aspx' page_login = session.post(url=login_url,headers=headers,data=data).text #暂时不处理cookie print(code_text) #打印解析出的验证码 with open('./gushi.html','w',encoding='utf-8') as f: f.write(page_login) print('结束')
