2010 1.09

From XPUB & Lens-Based wiki

Display the titles of an RSS feed

#!/usr/bin/env python

from optparse import OptionParser
parser = OptionParser()
parser.add_option("-u", "--url", dest="url", default="http://feeds.bbci.co.uk/news/rss.xml", help="the url to read from")
parser.add_option("-n", "--numlines", type="int", dest="num", default=1000, help="how many lines to display")
(options, args) = parser.parse_args()

import feedparser
feed = feedparser.parse(options.url)
for e in feed.entries[:options.num]:
    print e.title.encode("utf-8")

Words

Turns a text in an alphabetical list of unique words. Attempts to strip punctuation and lowercases everything.

#!/usr/bin/env python

import sys, string

words = {}
for line in sys.stdin:
    for word in line.split():
        word = word.lower().strip(string.punctuation)
        words[word] = words.get(word, 0) + 1

for word in sorted(words.keys()):
    print word,
print


Word counts

Grab words (as above) and display one per line followed by the number of times the word appears.

#!/usr/bin/env python

import sys, string

words = {}
for line in sys.stdin:
    for word in line.split():
        word = word.lower().strip(string.punctuation)
        words[word] = words.get(word, 0) + 1

for (word, count) in sorted(words.items()):
    print word, count