buzz_stats.py

#!/opt/local/bin/python2.6

import feedparser
import httplib2
import re
import sys

BASE_FEED_URL = 'http://buzz.googleapis.com/feeds/%s/public/posted'

HTTP = httplib2.Http("/tmp/httplib2-cache")

def parse_feed(feed_url):
  response, content = HTTP.request(feed_url, "GET")
  assert response.status == 200
  return feedparser.parse(content)

def main(argv):
  if len(argv) != 2:
    print 'Usage: buzz_feed.py username'
    return 1
  feed = parse_feed(BASE_FEED_URL % argv[1])
  total_posts = len(feed.entries)
  total_words = 0
  total_chars = 0
  total_replies = 0
  total_reply_words = 0
  total_reply_chars = 0
  total_newlines = 0
  reply_authors = set()
  for entry in feed.entries:
    total_words += len(re.split('\W+', entry.content[0].value))
    total_chars += len(entry.content[0].value)
    total_replies += int(entry.total)
    total_newlines += entry.content[0].value.count('\n')
    for link in entry.links:
      if link.rel == 'replies':
        reply_feed = parse_feed(link.href)
        for reply in reply_feed.entries:
          total_reply_words += len(re.split('\W+', reply.content[0].value))
          total_reply_chars += len(reply.content[0].value)
          reply_authors.add(reply.author)
  print 'Number of posts: %d' % total_posts
  print 'Total words in %d posts: %d' % (total_posts, total_words)
  print 'Total characters: %d' % total_chars
  print 'Total newlines: %d' % total_newlines
  print 'Average words per post: %d' % (total_words / total_posts)
  print 'Average chars per post: %d' % (total_chars / total_posts)
  print 'Total replies: %d' % total_replies
  print 'Average number of replies: %d' % (total_replies / total_posts)
  print 'Average number of words per reply: %d' % (total_reply_words / total_replies)
  print 'Average number of characters per reply: %d' % (total_reply_chars / total_replies)
  print 'Number of unique authors replying: %d' % len(reply_authors)

if __name__ == '__main__':
  main(sys.argv)