How To Extract Html Link Using Python And HTMLParser Module - | python web scraping | python example - part 3

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52

#!/usr/bin/python
# ---------------- READ ME ---------------------------------------------
# This Script is Created Only For Practise And Educational Purpose Only
# This Script Is Created For https://www.bitforestinfo.com
# This Script is Written By
__author__='''

######################################################
                By                            
######################################################

    Suraj Singh
     
     
    surajsinghbisht054@gmail.com
    https://www.bitforestinfo.com/

     
######################################################
'''
# Import Module
import urllib2
import sys
from HTMLParser import HTMLParser


# For More Info https://docs.python.org/2/library/htmlparser.html
class link_extractor(HTMLParser):
    def handle_starttag(self,tag, attrs):
        for attr in attrs:
            if 'href' in attr[0]:
                print attr[1]



if len(sys.argv)==1:
 print "[*] Please Provide Domain Name:\n Usages: python link_hp.py www.examplesite.com\n"
 sys.exit(0)

# Retrieve Html Data From Url
def get_html(url):
 try:
   page = urllib2.urlopen(url).read()
 except Exception as e:
  print "[Error Found] ",e
  page=None
 return page

html_data=get_html(sys.argv[1])

parser=link_extractor() # Creating Handler
parser.feed(html_data) # Feeding Data