def visitLoginpage(self):
'''Visit the login page'''
url = 'https://ipcrs.pbccrc.org.cn/login.do?method=initLogin'
self.__headers['Referer'] = 'https://ipcrs.pbccrc.org.cn/index1.do'
options = {
'method': 'get',
'url': url,
'form': None,
'params': None,
'cookies': self.__cookies,
'headers': self.__headers
}
response = basicRequest(options)
if response:
path_dict = dict(
date='//input[@name="date"]/@value',
code_url='//img[@id="imgrc"]/@src',
token=
'//input[@name="org.apache.struts.taglib.html.TOKEN"]/@value')
result = xpathText(response.text, path_dict)
if result['date'] and result['code_url'] and result['token']:
code = self.getCode(self.__host + result['code_url'])
form_item = dict(token=result['token'],
date=result['date'],
code=code)
return self.loginSys(form_item)
else:
return dict(result=40001, error='xpath not found')
else:
return dict(result=4000, func='visitLoginpage')
def inputIdCode(self):
'''Give the id_code to Sys'''
form = {
'method': 'checkTradeCode',
'code': 'e5pkaa',
'reportformat': '21'
}
form['code'] = self.__section['id_code']
url = 'https://ipcrs.pbccrc.org.cn/reportAction.do'
self.__headers[
'Referer'] = 'https://ipcrs.pbccrc.org.cn/reportAction.do?method=queryReport'
options = {
'method': 'post',
'url': url,
'form': form,
'params': None,
'cookies': self.__cookies,
'headers': self.__headers
}
response = basicRequest(options)
if response:
if (response.text).strip() == str(0):
return self.acquireReport()
else:
return dict(resul=4444, error='id_code_error')
else:
return dict(result=4000, func='inputIdCode')
def getProxies():
""" http://www.youdaili.net/
:return:
"""
options = {'method': 'get', 'url': 'http://www.youdaili.net/'}
response = basicRequest(options)
if not response:
return False
path = '//div[@class="m_box2"][1]/ul/li[1]/a/@href'
href = etree.HTML(response.content).xpath(path)
if not href:
return False
options = {'method': 'get', 'url': href[0]}
response = basicRequest(options)
path = '//div[@class="cont_font"]/p/span/text()'
result = [
i.lstrip('\r\n') for i in etree.HTML(response.content).xpath(path)
]
proxies = [re.search('(.*)\@', i).group(1) for i in result[:-1]]
return proxies
def loginSys(self, form_item):
'''Login the system'''
form = {
'org.apache.struts.taglib.html.TOKEN':
'1ec8589094a44e23e603c901536bbc59',
'method': 'login',
'date': '1467878083784',
'loginname': 'luocx1988',
'password': '******',
'_@IMGRC@_': 'gr3qga'
}
form['date'] = form_item['date']
form['_@IMGRC@_'] = form_item['code']
form['password'] = self.__section['password']
form['loginname'] = self.__section['user_name']
form['org.apache.struts.taglib.html.TOKEN'] = form_item['token']
url = 'https://ipcrs.pbccrc.org.cn/login.do'
self.__headers[
'Referer'] = 'https://ipcrs.pbccrc.org.cn/page/login/loginreg.jsp'
options = {
'method': 'post',
'url': url,
'form': form,
'params': None,
'cookies': self.__cookies,
'headers': self.__headers
}
response = basicRequest(options)
if response:
error = self.loginError(response.text)
if error['error'] == None:
return self.welcomePage()
elif error['error'] == 'code': # code error
if self.__threshold > 0:
self.__threshold -= 1
form_item['code'] = self.updateCode()
return self.loginSys(form_item)
else:
return dict(result=4440, error='image recognition failed')
elif error['error'] == 'user_name': # use_name or pw error
return dict(result=4400, error='user_name or pw error')
else:
return dict(result=4000, func='loginByJS')
def getCode(self, url, save_path='./code'):
'''Download code image and then invoke the recogImage function '''
options = {
'method': 'get',
'url': url,
'form': None,
'stream': True,
'cookies': self.__cookies,
'headers': self.__headers
}
response = basicRequest(options)
if response:
image = saveImage(response)
return self.recogImage(image)
else:
return dict(result=4000, func='getNoteCode')
def visitSys(self):
'''Visit the home page'''
url = 'https://ipcrs.pbccrc.org.cn/'
options = {
'method': 'get',
'url': url,
'form': None,
'params': None,
'cookies': None,
'headers': self.__headers
}
response = basicRequest(options)
if response:
self.__cookies = dict_from_cookiejar(response.cookies)
return self.visitLoginpage()
else:
return dict(result=4000, func='visitSys')
def welcomePage(self):
'''Visit the welcome page afer login sucessfully'''
url = 'https://ipcrs.pbccrc.org.cn/welcome.do'
self.__headers['Referer'] = 'https://ipcrs.pbccrc.org.cn/login.do'
options = {
'method': 'get',
'url': url,
'form': None,
'params': None,
'cookies': self.__cookies,
'headers': self.__headers
}
response = basicRequest(options)
if response:
return self.inputIdCode()
else:
return dict(result=4000, func='welcomePage')
def logoutSys(self):
'''Logout the system'''
form = {'method': 'loginOut'}
url = 'https://ipcrs.pbccrc.org.cn/login.do?' + str(random.random())
self.__headers['Referer'] = 'https://ipcrs.pbccrc.org.cn/top2.do'
options = {
'method': 'post',
'url': url,
'form': form,
'params': None,
'cookies': self.__cookies,
'headers': self.__headers
}
response = basicRequest(options)
if response:
return dict(result=2000)
else:
return dict(result=4000, func='logoutSys')
def updateCode(self, save_path='./code'):
'''Verify fail and download new picture'''
url = 'https://ipcrs.pbccrc.org.cn/imgrc.do?a=' + str(
random.randint(1467967606991, 1767967607647))
options = {
'method': 'get',
'url': url,
'form': None,
'stream': True,
'cookies': self.__cookies,
'headers': self.__headers
}
response = basicRequest(options)
if response:
image = saveImage(response)
return self.recogImage(image)
else:
return dict(result=4000, func='updateCode')
def acquireReport(self):
'''Claw person credit information'''
form = {'tradeCode': 'e5pkaa', 'reportformat': '21'}
form['tradeCode'] = self.__section['id_code']
url = 'https://ipcrs.pbccrc.org.cn/simpleReport.do?method=viewReport'
self.__headers[
'Referer'] = 'https://ipcrs.pbccrc.org.cn/reportAction.do?method=queryReport'
options = {
'method': 'post',
'url': url,
'form': form,
'params': None,
'cookies': self.__cookies,
'headers': self.__headers
}
response = basicRequest(options)
if response:
report_result = clawCreditReport(etree.HTML(response.text))
print report_result
self.logoutSys()
else:
return dict(result=4000, func='acquireReport')