python crawler extract javascript masked links window.open

window_dot_open_crawler.py

#author : osman ehmad

import urllib2

page = urllib2.urlopen('http://www.javascript-coder.com/files/window-popup/javascript-window-open-example1.html')

source = page.read()

# SCRIPT or script will depend upon pages you want crawled
# or both can easily be incorporated

# we first find where javascript is located, if there are multiple responses that can also be catered for

js_start = source.find('<SCRIPT')

js_end = source.find('</SCRIPT')

javascript = source[js_start:js_end]

#^ find all javascript on the page

print "\n\n\n ---printing javascript---\n\n\n"

print javascript

# finds window.open function

function_start = javascript.find('window.open(')

function_end = javascript.find(');')

arguments = javascript[function_start:function_end]

# splits the function up in its argument

broken = arguments.split(',')

print "\n\n\n ---printing the required function after parsing---\n\n\n"

print broken

#^ because first argument in js window.open is link, we print it

link = broken[0].split('(')

#^ this will parse broken[0] to extract required link string

print "\n\n\n ---printing masked javascript link--\n\n\n"

print link