def dealContactPageIndex(self,url,i):
result=("","","","")
if not url:
return result
if not url.startswith("http"):
return result
print "Analyzing the web page to get the contact information: ",url
htmlfile=self.getpage(url)
if not htmlfile:
t=("","","","")
return t
#print htmlfile
#address re pattern ([\w\d\s]*,){3,8}([\w\d\s~.]*?.){1,5}
#(?:[\w\d\s]*,){3,10}(?:[\w\d\s]*\.)
#([\w\d\s]*,){3,10}([\w\d\s]*\.)
try:
addresses=re.findall(r"(?:[\w\d\s]*,){3,10}(?:[\w\d\s]*?\.)",htmlfile,re.DOTALL)
except:
addresses=""
try:
tels=re.findall(r"\d{2,7}\s+[\d\s]{2,10}\d+",htmlfile,re.DOTALL)
except:
tels=""
try:
emails=re.findall(r"\w+(?:[-+.]\w+)*@\w+(?:[-.]\w+)*\.\w+(?:[-.]\w+)*",htmlfile,re.DOTALL)
except:
emails=""
if addresses:
address=addresses[0].strip()
else:
address=""
if tels:
tel=tels[0].strip()
else:
tel=""
if emails:
email=emails[0].strip()
else:
email=""
try:
rawinformation=ExtMainText.main(htmlfile)
except:
rawinformation=""
self.addresses[i]=address
self.tels[i]=tel
self.emails[i]=email
self.rawInformations[i]=rawinformation
result=(address,tel,email,rawinformation)
return result
def dealContactPage(self,url):
result=("","","","")
if not url:
return result
if not url.startswith("http"):
return result
print "Analyzing the web page to get the contact information: ",url
htmlfile=self.getpage(url)
try:
addresses=re.findall(r"(?:[\w\d\s]*,){3,10}(?:[\w\d\s]*?\.)",htmlfile,re.DOTALL)
except:
addresses=""
try:
tels=re.findall(r"\d{2,7}\s+[\d\s]{2,10}\d+",htmlfile,re.DOTALL)
except:
tels=""
try:
emails=re.findall(r"\w+(?:[-+.]\w+)*@\w+(?:[-.]\w+)*\.\w+(?:[-.]\w+)*",htmlfile,re.DOTALL)
except:
emails=""
address=""
if addresses:
address=addresses[0].strip()
tel=""
if tels:
tel=tels[0].strip()
email=""
if emails:
tempemails=[]
for e in emails:
tempemails.append(e.strip())
email="\n".join(tempemails)
try:
rawinformation=ExtMainText.main(htmlfile)
except:
rawinformation=""
result=(address,tel,email,rawinformation)
return result