split_string.py

# The built-in <string>.split() procedure works
# okay, but fails to find all the words on a page
# because it only uses whitespace to split the
# string. To do better, we should also use punctuation
# marks to split the page into words.

# The procedure, split_string, that takes two
# inputs: the string to split and a string containing
# all of the characters considered separators. The
# procedure returns a list of strings that break
# the source string up by the characters in the
# splitlist.

import re
def split_string(source,splitlist):
    if ' ' in splitlist:
        k = []
        k.extend(splitlist)
        for i in k:
            source = source.replace( i ,' ' )
        return source.split()
    else:
        y = re.split(splitlist, source)
        if '' in y:
            y.remove('')
        return y


out = split_string("http://this.domain.com/here/there/everywhere.html",'/')
print out
#>>>['http:', 'this.domain.com', 'here', 'there', 'everywhere.html']

out = split_string("This is a test-of the,,string separation-code!"," ,!-")
print out
#>>> ['This', 'is', 'a', 'test', 'of', 'the', 'string', 'separation', 'code']

out = split_string("After  the flood   ...  all the colors came out.", " .")
print out
#>>> ['After', 'the', 'flood', 'all', 'the', 'colors', 'came', 'out']

out = split_string("First Name,Last Name,Street Address,City,State,Zip Code",",")
print out
#>>>['First Name', 'Last Name', 'Street Address', 'City', 'State', 'Zip Code']