#!/usr/bin/python

# import urllib2 to download web pages 

import urllib2
import sys 

httpResponse = urllib2.urlopen(sys.argv[1])
htmlPage = httpResponse.read()

#print htmlPage

# lets feed the htmlpage to a parser
# we can use DOM or Stream parser
# will use DOM in this example 

from BeautifulSoup import BeautifulSoup

htmlDom = BeautifulSoup(htmlPage)

# dump page title 

print htmlDom.title.string

# dump all links in page 

#allLinks = htmlDom.findAll('a', {'href': True})
#for link in allLinks:
#	print link['href']

# print all the comments in the html page 

from BeautifulSoup import Comment 

allComments = htmlDom.findAll(text = lambda text:isinstance(text, Comment))

for eachComment in allComments :
	print eachComment

# dump all the text, individual tags ...