Simple script to show diff between two HTML pages in understandable format

htmldiff.py

#!/usr/bin/env python
""" Simple script to show diff between two HTML pages in understandable format """
import urllib2, tidy, sys, subprocess

tidy_kwargs = dict(
    output_xml=1,
    indent=1,
    indent_attributes=1,
    wrap=80,
    char_encoding='raw',
    tidy_mark=0,
    force_output=1,
    quote_marks=1,
    word_2000=1,
    indent_spaces=0,
    wrap_attributes=1,
)

def read_website(website, output_filename):
    url = 'http://%s' % website
    content = urllib2.urlopen(url).read()
    clean_content = str(tidy.parseString(content, **tidy_kwargs))
    f = open(output_filename, 'w')
    f.write(clean_content)
    f.close()

def print_diff(file1, file2):
    subprocess.call(
        [
         'bash', '-c',
         'diff -u %s %s | colordiff | less -R' % (file1, file2)
        ])

read_website(website, '/tmp/before.xhtml')
# Do smth...
read_website(website, '/tmp/after.xhtml')
print_diff('/tmp/before.xhtml', '/tmp/after.xhtml')