from ehp import *
import urllib2
import urllib
from web import *
import re
from HTMLParser import HTMLParser
class Title(object):
""" This class is used to obtain url titles. """
def __init__(self):
self.opener = urllib2.build_opener()
self.opener.addheaders = [('User-agent', 'Mozilla/5.0')]
self.MAX_SIZE = 262144
def get_title(self, url):
page_title = ''
data = self.get_page(url)
#html = Html()
#struct = html.feed(data)
r = re.compile('
(.*?)', re.DOTALL)
page_title = HTMLParser().replace(r.findall(data))
########
#for indi in struct.sail():
# if indi.name == 'title':
# ########
# for indj in indi.sail():
# if indj.name == DATA:
# page_title = page_title + indj.data
# elif indj.name == CODE:
# page_title = page_title + code(indj.data)
# elif indj.name == AMP:
# page_title = page_title + amp(indj.data)
########
return page_title
def get_page(self, url):
url = self.opener.open(url, timeout=0.5)
data = url.read(self.MAX_SIZE)
return data