Created
June 1, 2012 04:57
-
-
Save Codercise/2848914 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Question 4: Remove Tags | |
# When we add our words to the index, we don't really want to include | |
# html tags such as <body>, <head>, <table>, <a href="..."> and so on. | |
# Write a procedure, remove_tags, that takes as input a string and returns | |
# a list of words, in order, with the tags removed. Tags are defined to be | |
# strings surrounded by < >. Words are separated by whitespace or tags. | |
# You may assume the input does not include any unclosed tags, that is, | |
# there will be no '<' without a following '>'. | |
def remove_tags(html): | |
start_tag = '>' | |
end_tag = '</' | |
find_stag = html.find(start_tag) | |
find_etag = html.find(end_tag) | |
if start_tag == -1: | |
return None | |
find_stag = html.find(start_tag) | |
find_etag = html.find(end_tag) | |
content = html[find_stag + 1:find_etag] | |
derp = [] | |
splitted=(content.split()) | |
return splitted | |
def remove_tags(html): | |
return html.strip('<></') | |
print remove_tags('''<h1>Title</h1><p>This is a | |
<a href="http://www.udacity.com">link</a>.<p>''') | |
#>>> ['Title','This','is','a','link','.'] | |
print remove_tags('''<table cellpadding='3'> | |
<tr><td>Hello</td><td>World!</td></tr> | |
</table>''') | |
#>>> ['Hello','World!'] | |
print remove_tags("<hello><goodbye>") | |
#>>> [] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment