Work4 - Programming - Q4

import re;

# IDs for the different context_type values
HTML_TEXT = 1
HTML_ATTRIBUTE = 2
JS_STRING = 3

# Cleans up a string for output
def sanitize(input, context_type):
    
  output = ""
    
  if context_type == HTML_TEXT:
    output = re.sub(r"<[^>]*>", "", input)

elif context_type == HTML_ATTRIBUTE:
    return re.sub(r"(<[^>]*>)|\"|'", "", input)

elif context_type == JS_STRING:
    output = re.sub(r"'", "\\'", input)
    output = re.sub(r"\"", "\\\"", output)
    output = re.sub(r"<[^>]*>", "", output)
    
  else:
    # No regex corresponding for context_type
    raise Exception("Wrong argument for context type.");

return output

# Testing a little bit
html = u'<ul class="class"><li/>Lorem\'ipsum dolor "sit amet, consectetuer adipiscing elit.</li><li class="class">Aliquam tincidunt mauris eu risus.</li><li>Vestibulum auctor dapibus neque.</li></ul>'

print sanitize(html, HTML_TEXT)
print sanitize(html, HTML_ATTRIBUTE)
print sanitize(html, JS_STRING)
print sanitize(html, "")

Browser Version Not Supported

Due to Python Fiddle's reliance on advanced JavaScript techniques, older browsers might have problems running it correctly. Please download the latest version of your favourite browser.
Chrome 10+ Firefox 4+ Safari 5+
IE 10+

Let me try anyway!

Python Fiddle

Python Cloud IDE