def __init__(self):

conf = ConfigParser()

conf.read('conf.ini')

self.url = 'http://www.mace.manchester.ac.uk'

self.login_data = dict(conf.items('account'))

self.headers = dict(conf.items('header'))

self.ses = requests.session()

def getPage(self):

try:

res = self.ses.get(url = self.url+'/people/staff/academic-staff/', headers = self.headers)

return res.text.decode('utf-8')

except requests.exceptions.RequestException:

print 'open '+self.url+' error'

def getGeneInfo(self,html):

doc = pq(html)

staff = []

for data in doc('tr'):

person = []

for i in range(len(pq(data).find('td'))):

person.append(pq(data).find('td').eq(i).text())

person.append(pq(data).find('td').eq(0).find('a').attr('href'))

person.append(pq(data).find('td').eq(4).find('a').attr('href'))

if(len(person)!=0 and person[0]):

staff.append(person)

return staff

def mkDir(self,path):

path = path.strip()

isPathexits = os.path.exists(path)

if (not isPathexits):

os.makedirs(path)

return True

else:

print 'path'+'dir exists'

return False

def getPersonBio(self,url,name):

try:

res = self.ses.get(self.url+url+'&pg=1', headers = self.headers)

# with open('personresearch.html','w') as f:

# f.write(res.text)

info = []

doc = pq(res.text)

for item in doc('div.researchstaffprofile-section').eq(1).find('p'):

info.append(pq(item).text())

return info

except requests.exceptions.RequestException:

print 'open '+name+' detail page error'

def getPersonResearch(self,url,name):

try:

res = self.ses.get(self.url+url+'&pg=2', headers = self.headers)

# with open('personresearch.html','w') as f:

# f.write(res.text)

info = []

doc = pq(res.text)

for item in doc('div.researchstaffprofile-section').eq(0).find('li'):

info.append(pq(item).text())

return info

except requests.exceptions.RequestException:

print 'open research '+name+' page error'

def getPersonPub(self,url,name):

try:

res = self.ses.get(self.url + url + '&pg=4', headers=self.headers)

# with open('personresearch.html','w') as f:

# f.write(res.text)

doc = pq(res.text)

info = []

for item in doc('div.researchstaffprofile-section').eq(0).find('li'):

info.append(pq(item).text())

return info

except requests.exceptions.RequestException: