def dlPaper(self) :
for msg in self.msg :
filename=''
From=msg[0]
url=msg[1]
uf=self.urlFrom(url)
if uf==1 or uf==2 :
nature='http://www.nature.com'
req=urllib2.Request(url)
res=self.openner.open(req).read()
parser=BeautifulSoup(res)
pdf=parser.findAll(attrs={'class':re.compile(r'download')})
for item in pdf :
s=re.search(r'href="(.*.pdf)"',str(item))
if s :
pdf=nature+s.group(1)
filename=pdf.rstrip('pdf').split('/')[-1]+str(time.strftime("%Y.%m.%d.%H.%M.%S",time.localtime()))+'.pdf'
urllib.urlretrieve(pdf,filename)
msg.append(filename)
msg.append(1)
break
else :
msg.append(filename)
msg.append(0)
def FromCell(self, msg):
url = msg['Subject']
pub = ''
req = urllib2.Request(url)
res = self.openner.open(req).read()
parser = BeautifulSoup(res)
pr = parser.findAll(attrs={'name': re.compile(r'citation_pdf_url')})
for item in pr:
s = re.search(r'content="(.*?.pdf)"', str(item))
if s:
pdf = pub + s.group(1)
print(pdf)
req = urllib2.Request(pdf)
res = self.openner.open(req).read()
parser = BeautifulSoup(res)
pa = parser.findAll('p')
for it in pa:
s = re.search(r'href="(.*?)"', str(it))
if s:
s = s.group(1).split('amp;')
pdf = ''.join(s)
print(pdf)
def FromScience(self, msg):
url = msg['Subject']
pub = 'http://www.sciencemag.org'
req = urllib2.Request(url)
res = self.openner.open(req).read()
parser = BeautifulSoup(res)
pr = parser.findAll('a')
for item in pr:
s = re.search(r'href="(.*?.pdf)"', str(item))
if s:
pdf = pub + s.group(1)
filename = pdf.rstrip('pdf').split('/')[-1] + str(
time.strftime("%Y.%m.%d.%H.%M.%S",
time.localtime())) + '.pdf'
urllib.urlretrieve(pdf, filename)
msg['FileName'] = filename
msg['Flag'] = 1