Difference between revisions of "2010 1.09"

From Media Design: Networked & Lens-Based wiki
Jump to navigation Jump to search
Line 14: Line 14:
 
     print e.title.encode("utf-8")
 
     print e.title.encode("utf-8")
 
</source>
 
</source>
 +
 +
== Words ==
 +
 +
Turns a text in an alphabetical list of unique words. Attempts to strip punctuation and lowercases everything.
 +
 +
<source lang="python">
 +
#!/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
 +
</source>
 +
  
 
== Word counts ==
 
== Word counts ==

Revision as of 23:24, 6 December 2010

Read a feed with a URL from the command line

#!/usr/bin/env python
import sys, feedparser

try:
    url = sys.argv[1]
except IndexError:
    url = "http://feeds.bbci.co.uk/news/rss.xml"

feed = feedparser.parse(url)
for e in feed.entries:
    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

#!/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