A small utility to take in as input an HTML file and output formatted information. I used this to un-garble test failures messages.

html_unescape.py

""" 
Unescape HTML junk into something readable 
Usage: python html_unescape.py < input_file 
"""

import fileinput
import HTMLParser

replacements = [
    ('\\:', ':')
]

def main():
    parser = HTMLParser.HTMLParser()
    for html_text in fileinput.input():
        plain_text = parser.unescape(html_text)
        for old_text, new_text in replacements:
            plain_text = plain_text.replace(old_text, new_text)
        print plain_text
if __name__ == '__main__':
    main()