I taught myself Python at my new job and really enjoy the language. I wrote a short class to do some basic data manipulation, and I'm pretty sure about that.
But the old habits from my structured / modular programming days are hard to break, and I know that there must be a better way to write this. So, I was wondering if anyone would like to take a look at the following and suggest some possible improvements or put me on a resource that could help me discover this.
Quick note: The randomItems root class was written by someone else, and I'm still hugging the itertools library. In addition, this is not the whole module - only the class I'm working on, and these are the prerequisites.
What do you think?
import itertools
import urllib2
import random
import string
class RandomItems(object):
"""This is the root class for the randomizer subclasses. These
are used to generate arbitrary content for each of the fields
in a csv file data row. The purpose is to automatically generate
content that can be used as functional testing fixture data.
"""
def __iter__(self):
while True:
yield self.next()
def slice(self, times):
return itertools.islice(self, times)
class RandomWords(RandomItems):
"""Obtain a list of random real words from the internet, place them
in an iterable list object, and provide a method for retrieving
a subset of length 1-n, of random words from the root list.
"""
def __init__(self):
urls = [
"http://dictionary-thesaurus.com/wordlists/Nouns%285,449%29.txt",
"http://dictionary-thesaurus.com/wordlists/Verbs%284,874%29.txt",
"http://dictionary-thesaurus.com/wordlists/Adjectives%2850%29.txt",
"http://dictionary-thesaurus.com/wordlists/Adjectives%28929%29.txt",
"http://dictionary-thesaurus.com/wordlists/DescriptiveActionWords%2835%29.txt",
"http://dictionary-thesaurus.com/wordlists/WordsThatDescribe%2886%29.txt",
"http://dictionary-thesaurus.com/wordlists/DescriptiveWords%2886%29.txt",
"http://dictionary-thesaurus.com/wordlists/WordsFunToUse%28100%29.txt",
"http://dictionary-thesaurus.com/wordlists/Materials%2847%29.txt",
"http://dictionary-thesaurus.com/wordlists/NewsSubjects%28197%29.txt",
"http://dictionary-thesaurus.com/wordlists/Skills%28341%29.txt",
"http://dictionary-thesaurus.com/wordlists/TechnicalManualWords%281495%29.txt",
"http://dictionary-thesaurus.com/wordlists/GRE_WordList%281264%29.txt"
]
self._words = []
for url in urls:
urlresp = urllib2.urlopen(urllib2.Request(url))
self._words.extend([word for word in urlresp.read().split("\r\n")])
self._words = list(set(self._words))
self._words.sort()
def next(self):
"""Return a single random word from the list
"""
return random.choice(self._words)
def get(self):
"""Return the entire list, if needed.
"""
return self._words
def wordcount(self):
"""Return the total number of words in the list
"""
return len(self._words)
def sublist(self,size=3):
"""Return a random segment of _size_ length. The default is 3 words.
"""
segment = []
for i in range(size):
segment.append(self.next())
return segment
def random_name(self):
"""Return a string-formatted list of 3 random words.
"""
words = self.sublist()
return "%s %s %s" % (words[0], words[1], words[2])
def main():
"""Just to see it work...
"""
wl = RandomWords()
print wl.wordcount()
print wl.next()
print wl.sublist()
print 'Three Word Name = %s' % wl.random_name()
if __name__ == "__main__":
main()