class Query(object):
def __init__(self):
self.request = Singleton.GetInstance()
self.parser = Parser
self.Re = Re()
def query(self):
CreditUrl = 'https://ipcrs.pbccrc.org.cn/simpleReport.do?method=viewReport'
CreditHeader = {
'Referer':
'https://ipcrs.pbccrc.org.cn/reportAction.do?method=queryReport',
'User-Agent':
'Mozilla/5.0(Windows NT 6.1;WOW64;rv:52.0)Gecko/20100101Firefox/52.0'
}
CreditData = {
'counttime': '',
'reportformat': '21',
'tradeCode': 'xubjjc'
}
CreditReponse = self.request.post(CreditUrl,
headers=CreditHeader,
data=CreditData,
verify=False)
#这个报告要存一份到原始数据库
CreditReponse = CreditReponse.content.decode('gbk')
#调用解析器解析并放入数据库
CodeError = self.Re.reFind(CreditReponse, r'(查询码输入错误，请重新输入)')
if CodeError:
print('查询码输入错误')
exit()
self.parser.parser(self, CreditReponse)
print(type(CreditReponse))
print('')
class Apply(object):
def __init__(self):
self.request = Singleton.GetInstance()
self.Re = Re()
def apply(self):
try:
#获取第一个申请页面
firsturl = 'https://ipcrs.pbccrc.org.cn/reportAction.do?method=applicationReport'
firstheader = {
'Referer': 'https://ipcrs.pbccrc.org.cn/menu.do',
'User-Agent': 'Mozilla/5.0(Windows NT 6.1;WOW64;rv:52.0)Gecko/20100101Firefox/52.0'
}
firstresponse = self.request.get(firsturl, headers=firstheader, verify=False).content.decode('gbk')
#获取第一个页面的token
tokenfirst = self.Re.reFind(firstresponse, r'TOKEN" value="(.*?)"')
askdata = {
'org.apache.struts.taglib.html.TOKEN': tokenfirst,
'method':'checkishasreport',
'authtype': '2',
'ApplicationOption': '25',
'ApplicationOption': '24',
'ApplicationOption': '21'
}
askurl = 'https://ipcrs.pbccrc.org.cn/reportAction.do?method=checkishasreport'
askheaders = {
'Referer':'https://ipcrs.pbccrc.org.cn/reportAction.do?method=applicationReport',
'User-Agent': 'Mozilla/5.0(Windows NT 6.1;WOW64;rv:52.0)Gecko/20100101Firefox/52.0'
}
#获取答题页面
askresponse = self.request.post(askurl, headers=askheaders, data=askdata, verify=False).content.decode('gbk')
soup = BeautifulSoup(askresponse,'lxml')
lis = soup.find_all('li')
asklist = []
for li in lis:
# Problem = BeautifulSoup.find(li,'p').text
# asklist.append(Problem)
Answers = BeautifulSoup.find_all(li,'span')
for Answer in Answers:
asklist.append(Answer.text)
#写入到数据库
print (asklist)
#等待客户输入答案
param = self.Re.reFindAll(askresponse, r'value="(.*?)">')
if len(param) == 0:
print('获取失败')
submitdata = {
'org.apache.struts.taglib.html.TOKEN': param[0],
'method':'',
'authtype': '2',
'ApplicationOption': '25',
'ApplicationOption': '24',
'ApplicationOption': '21',
'kbaList[0].derivativecode': param[1],
'kbaList[0].businesstype':param[2],
'kbaList[0].questionno':param[3],
'kbaList[0].kbanum': param[4],
'kbaList[0].question': param[5],
'kbaList[0].options1': param[6],
'kbaList[0].options2': param[7],
'kbaList[0].options3': param[8],
'kbaList[0].options4': param[9],
'kbaList[0].options5': param[10],
'kbaList[0].answerresult':'1', #
'kbaList[0].options': '1',
'kbaList[1].derivativecode': param[11],
'kbaList[1].businesstype':param[12],
'kbaList[1].questionno': param[13],
'kbaList[1].kbanum': param[14],
'kbaList[1].question': param[15],
'kbaList[1].options1':param[16],
'kbaList[1].options2': param[17],
'kbaList[1].options3': param[18],
'kbaList[1].options4': param[19],
'kbaList[1].options5': param[20],
'kbaList[1].answerresult': '1',
'kbaList[1].options': '1',
'kbaList[2].derivativecode': param[21],
'kbaList[2].businesstype': param[22],
'kbaList[2].questionno': param[23],
'kbaList[2].kbanum': param[24],
'kbaList[2].question': param[25],
'kbaList[2].options1': param[26],
'kbaList[2].options2': param[27],
'kbaList[2].options3': param[28],
'kbaList[2].options4': param[29],
'kbaList[2].options5': param[30],
'kbaList[2].answerresult': '1',
'kbaList[2].options': '1',
'kbaList[3].derivativecode': param[31],
'kbaList[3].businesstype': param[32],
'kbaList[3].questionno': param[33],
'kbaList[3].kbanum': param[34],
'kbaList[3].question': param[35],
'kbaList[3].options1': param[36],
'kbaList[3].options2': param[37],
'kbaList[3].options3': param[38],
'kbaList[3].options4': param[39],
'kbaList[3].options5': param[40],
'kbaList[3].answerresult': '1',
'kbaList[3].options': '1',
'kbaList[4].derivativecode': param[41],
'kbaList[4].businesstype': param[42],
'kbaList[4].questionno': param[43],
'kbaList[4].kbanum': param[44],
'kbaList[4].question': param[45],
'kbaList[4].options1': param[46],
'kbaList[4].options2': param[47],
'kbaList[4].options3': param[48],
'kbaList[4].options4': param[49],
'kbaList[4].options5': param[50],
'kbaList[4].answerresult': '1',
'kbaList[4].options': '1',
}
submitheader = {
'Referer': 'https://ipcrs.pbccrc.org.cn/reportAction.do?method=checkishasreport',
'User-Agent': 'Mozilla/5.0(Windows NT 6.1;WOW64;rv:52.0)Gecko/20100101Firefox/52.0'
}
submitUrl = 'https://ipcrs.pbccrc.org.cn/reportAction.do?method=submitKBA'
submitresponse = self.request.post(submitUrl, headers=submitheader, data=submitdata, verify=False)
submitresponse = submitresponse.content.decode('gbk')
compileResult = self.Re.reFind(submitresponse,r'(您于.*?申请正在受理，请耐心等待。)')
Result = self.Re.reFind(submitresponse, r'(您的查询.*?获取结果)')
if compileResult:
print(compileResult)
if Result:
print(Result)
except Exception as e:
print(e)
class Login(object):
def __init__(self):
self.request = Singleton.GetInstance()
self.getcpatcha = getCaptcha()
self.Re = Re()
def login(self, username, password):
firstHeader = {
'User-Agent':
'Mozilla / 5.0(Windows NT 6.1;WOW64;rv:52.0) Gecko / 20100101 Firefox / 52.0',
'Referer': 'https://ipcrs.pbccrc.org.cn/index1.do'
}
#获取第一个页面的token
firstUrl = 'https://ipcrs.pbccrc.org.cn/login.do?method=initLogin'
firstresponse = self.request.get(firstUrl,
headers=firstHeader,
verify=False).content.decode('gbk')
tokenfirst = self.Re.reFind(firstresponse, r'TOKEN" value="(.*?)"')
#验证码下载预测
captcha = self.getcpatcha.predict()
#获取登陆页面
loginpostdata = {
'org.apache.struts.taglib.html.TOKEN': tokenfirst,
'method': 'login',
'data': time.time() * 1000,
'loginname': username,
'password': password,
'_@IMGRC@_': captcha,
}
loginHeader = {
'User-Agent':
'Mozilla/5.0(Windows NT 6.1;WOW64;rv:52.0)Gecko/20100101Firefox/52.0',
'Referer': 'https://ipcrs.pbccrc.org.cn/page/login/loginreg.jsp'
}
try:
response = self.request.post(
'https://ipcrs.pbccrc.org.cn/login.do',
headers=loginHeader,
data=loginpostdata,
verify=False)
if response.status_code == 200:
response = response.content.decode('gbk')
compileerror = self.Re.reFind(response, r'(因登录名与密码.*?分钟。)')
compilePassword = self.Re.reFind(response, r'(登录名或密码错误)')
if compileerror:
#错误登陆5次
#把状态码和错误原因存入数据库然后退出
print(compileerror)
exit()
elif compilePassword:
# 密码错误
print(compilePassword)
exit()
#验证码输入错误
compileCaptchaError = self.Re.reFind(response, r'(验证码输入错误)')
while compileCaptchaError:
captcha = self.getcpatcha.predict()
loginpostdata = {
'org.apache.struts.taglib.html.TOKEN': tokenfirst,
'method': 'login',
'data': time.time() * 1000,
'loginname': username,
'password': password,
'_@IMGRC@_': captcha,
}
response = self.request.post(
'https://ipcrs.pbccrc.org.cn/login.do',
headers=loginHeader,
data=loginpostdata,
verify=False)
response = response.content.decode('gbk')
compileCaptchaError = self.Re.reFind(
response, r'(验证码输入错误)')
print('登陆成功')
else:
#存入数据库失败原因
exit()
except Exception as e:
print(e)
def parser(self, html):
Credit = {}
selector = etree.HTML(html)
#基本信息
basicInfo = {}
infos = selector.xpath(r'//tr[2]/td/table[1]//td/strong/text()')
for info in infos:
temp = info.split('：')
basicInfo[temp[0]] = temp[1]
infos = selector.xpath(r'//tr[2]/td/table[2]//td/strong/text()')
for info in infos:
temp = info.split('：')
if len(temp) == 1:
basicInfo['婚否'] = temp[0]
else:
basicInfo[temp[0]] = temp[1]
Credit['基本信息'] = basicInfo
#信贷记录
xindai = {}
xindai = {}
infos = selector.xpath(r'//tr[2]/td/table[3]//td/strong/text()')
xindai['注释'] = infos[1].replace('\xa0','')
infos = selector.xpath(r'//tr[2]/td/table[4]//td/text()')
listinfo = ['信息概要']
for info in infos:
info = removeSymbol.removesymbol(self, info)
if info != '':
listinfo.append(info)
#sinfos = str(infos).replace('\\n','').replace('\\r','').replace('\\t','').replace('\\`\\`','')
xindai['信息概要'] = listinfo
infos = selector.xpath(r'//tr[2]/td/table[4]//tr[1]/td[2]//span/text()')
infofull = ''
for info in infos:
info = removeSymbol.removesymbol(self, info)
if info != '':
infofull += info
xindai['逾期记录'] = infofull
Credit['信贷记录'] = xindai
#信用卡
CreditCard = {}
infos = selector.xpath(r'//div/div/table//tr[2]/td/ol[1]//text()')
infolist = []
#去除一些空的项
for info in infos:
info = removeSymbol.removesymbol(self, info)
if info != '':
infolist.append(info)
key = infolist[0]
infolist = infolist[1:]
jsonlist = []
for info in infolist:
info = removeSymbol.removesymbol(self, info)
if info != '':
json = {}
json['发卡时间'] = Re.reFind(self, info, r'(\d+年\d+月\d+日)')
json['发卡行'] = Re.reFind(self, info, r'日(.*?)截')
json['截止时间'] = Re.reFind(self, info, r'截至(.*?)，信用')
print(Re.reFind(self, info, r'信用额度(.*?)，'))
json['信用额度'] = Re.reFind(self, info, r'信用额度(.*?)，')
json['已使用额度'] = Re.reFind(self, info, r'0，(.*?)。')
jsonlist.append(json)
CreditCard = {key:jsonlist}
Credit['信用卡'] = CreditCard
print(Credit)
#公共记录
recordlist = []
infos = selector.xpath(r'//tr[2]/td/table[5]//text()')
for info in infos:
info = removeSymbol.removesymbol(self, info)
if info != '':
recordlist.append(info)
recordlist = recordlist[1:]
Credit['公共记录'] = recordlist
#查询记录
qrecordlist = []
infos = selector.xpath(r'//tr[2]/td/table[7]//text()')
for info in infos:
info = removeSymbol.removesymbol(self, info)
if info != '':
qrecordlist.append(info)
Credit['查询记录'] = qrecordlist
print (Credit)
class Register(object):
def __init__(self):
self.request = Singleton.GetInstance()
self.Re = Re()
self.getcpatcha = getCaptcha()
self.namecheck = nameCheck()
def register(self):
firstUrl = 'https://ipcrs.pbccrc.org.cn/login.do?method=initLogin'
firstHeader = {
'User-Agent':
'Mozilla / 5.0(Windows NT 6.1;WOW64;rv:52.0) Gecko / 20100101 Firefox / 52.0',
'Referer': 'https://ipcrs.pbccrc.org.cn/index1.do'
}
firstResponse = self.request.get(firstUrl,
headers=firstHeader,
verify=False)
if firstResponse.status_code == 200:
firstResponse = firstResponse.content.decode('gbk')
tokenfirst = self.Re.reFind(firstResponse, r'TOKEN" value="(.*?)"')
print('第一个页面请求成功')
#获取第二个页面
secondUrl = 'https://ipcrs.pbccrc.org.cn/userReg.do'
secondHeader = {
'User-Agent':
'Mozilla / 5.0(Windows NT 6.1;WOW64;rv:52.0) Gecko / 20100101 Firefox / 52.0',
'Referer': 'https://ipcrs.pbccrc.org.cn/page/login/loginreg.jsp'
}
secondData = {
'org.apache.struts.taglib.html.TOKEN': tokenfirst,
'method': 'initReg'
}
secondResponse = self.request.post(secondUrl,
headers=secondHeader,
data=secondData,
verify=False)
if secondResponse.status_code == 200:
secondResponse = secondResponse.content.decode('gbk')
tokensecond = self.Re.reFind(secondResponse,
r'TOKEN" value="(.*?)"')
print('第二个页面请求成功')
#获取第三个页面
thirdUrl = 'https://ipcrs.pbccrc.org.cn/userReg.do'
captcha = self.getcpatcha.predict()
thirdHeader = {
'Referer': 'https://ipcrs.pbccrc.org.cn/userReg.do',
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36',
#'Accept': 'text/html, application xhtml+xml, application/xml;q=0.9,image/webp,*/*;q=0.8',
#'Accept-Encoding': 'gzip, deflate, br',
# 'Accept-Language': 'zh-CN,zh;q = 0.8',
# 'Cache-Control': 'max-age=0',
#'Connection': 'keep-alive',
# 'Content-Length': '203',
#'Host': 'ipcrs.pbccrc.org.cn',
'Content-Type': 'application/x-www-form-urlencoded;charset=UTF-8',
# 'Origin': 'https://ipcrs.pbccrc.org.cn',
#'Upgrade-Insecure-Requests': '1'
}
thirdData = {
'org.apache.struts.taglib.html.TOKEN': tokensecond,
'method': 'checkIdentity',
'userInfoVO.name': '王大丽',
'userInfoVO.certType': '0',
'userInfoVO.certNo': '532129198806123369',
'_@IMGRC@_': captcha,
'1': 'on'
}
# thirdData = urllib.parse.urlencode(thirdData)
thirdResponse = self.request.post(thirdUrl,
headers=thirdHeader,
data=thirdData,
verify=False)
thirdResponse = thirdResponse.content.decode('gbk')
compileCaptchaError = self.Re.reFind(thirdResponse, r'(验证码输入错误)')
while compileCaptchaError:
captcha = self.getcpatcha.predict()
thirdData = {
'org.apache.struts.taglib.html.TOKEN': tokensecond,
'method': 'checkIdentity',
'userInfoVO.name': '杨帆',
'userInfoVO.certType': '0',
'userInfoVO.certNo': '510184198907130057',
'_@IMGRC@_': captcha,
'1': 'on'
}
thirdresponse = self.request.post(thirdUrl,
headers=thirdHeader,
data=(thirdData),
verify=False)
thirdresponse = thirdresponse.content.decode('gbk')
compileCaptchaError = self.Re.reFind(thirdresponse, r'(验证码输入错误)')
print('')
result = self.namecheck.namecheck('yy80188815')
dmtUrl = 'https://ipcrs.pbccrc.org.cn/userReg.do'
dtmHeader = {
'User-Agent':
'Mozilla / 5.0(Windows NT 6.1;WOW64;rv:52.0) Gecko / 20100101 Firefox / 52.0',
'Referer': 'ipcrs.pbccrc.org.cn/userReg.do'
}
dtmData = {'method': 'getAcvitaveCode', 'mobileTel': '18980920233'}
dtmResponse = self.request.post(secondUrl,
headers=dtmHeader,
data=dtmData,
verify=False)