Top Domains in Readability

top_readability_domains.py

#!/usr/bin/env python

import re, operator, argparse, oauth

from readability import ReaderClient
from beaker.cache import cache_regions, cache_region

parser = argparse.ArgumentParser(description="Look at Readability.com and determines the top domains you've read articles with")
parser.add_argument('file', nargs=1, help='Filename to export to.')

cache_regions.update({
    'short_term':{
        'expire': 3600,
        'type':'dbm',
        'data_dir': '/tmp',
    }
  })

@cache_region('short_term', 'sorted_domains')
def sorted_domains(number = -1):
  rdd = ReaderClient('consumer-key', 'secret-key', 'username', 'password')

  bookmarks = rdd.get_bookmarks(favorite=True)

  domains = {}
  for bookmark in bookmarks:
    domain = bookmark.article.domain
    www = re.search('www\.', domain)
    if www == None: 
      domain = bookmark.article.domain
    else:
      domain = bookmark.article.domain[www.end():]
    if not domain in domains:
      domains[domain] = 1
    else:
      domains[domain] += 1

  sorted_domains = sorted(domains.iteritems(), key=operator.itemgetter(1), reverse=True)
  if number == -1:
    pass
  else:
    sorted_domains = sorted_domains[:number]
  return sorted_domains

if __name__ == '__main__':
  arguments = parser.parse_args()
  for sorted_domain in sorted_domains(arguments.number):
    print "%s: %d" % (sorted_domain[0], sorted_domain[1])