Extract href tag values (hyperlinks) from a webpage.

find-hyperlinks.1.sh

#!/usr/bin/python
from HTMLParser import HTMLParser
class MyHTMLParser(HTMLParser):
    def handle_starttag(self, tag, attrs):
        if tag == "a":
           for name, value in attrs:
              if name == "href":
                   print name, "=", value
parser = MyHTMLParser()
parser.feed(your_html_string)

find-hyperlinks.py

#!/usr/bin/python
from HTMLParser import HTMLParser
class MyHTMLParser(HTMLParser):
    def handle_starttag(self, tag, attrs):
        if tag == "a":
           for name, value in attrs:
              if name == "href":
                   print name, "=", value
parser = MyHTMLParser()
parser.feed(your_html_string)

find-hyperlinks1.py

#!/usr/bin/python
from BeautifulSoup import BeautifulSoup
import urllib2
import re

html_page = urllib2.urlopen("http://example.com/example.html")
soup = BeautifulSoup(html_page)
for link in soup.findAll('a'):
    print link.get('href')

find-hyperlinks2.py

#!/usr/bin/python
#-*- coding: utf-8 -*-
# usage ./find_hyperlinks.py "https://example.com/example.txt"
import os
import sys
import wget
from BeautifulSoup import BeautifulSoup
sys.setdefaultencoding('UTF8')
url = sys.argv[1]
filename = os.path.basename(url)
soup = BeautifulSoup(filename)
for tag in soup.findAll('a', href=True):
  print(str(tag['href']))