parse_delicious_xml.py

#!/usr/bin/env python
# encoding: utf-8
"""
parse_delicious_xml.py

First download your bookmarks and restrict to specific tags if desired:

$ curl --user 'username':'password' -o delicious.xml 'https://api.del.icio.us/v1/posts/all'

Extract and count most common domains:

$ python parse_delicious_xml.py | sort | uniq -c | sort -nr > ranked_delicious_domains.txt

Created by Peter Skomoroch on 2010-08-15.
Copyright (c) 2010 Data Wrangling LLC. All rights reserved.
"""

import sys
import os
from BeautifulSoup import BeautifulStoneSoup
xml = open('delicious.xml', 'rU').read()
soup = BeautifulStoneSoup(xml)

posts = soup.findAll('post')

for i, post in enumerate(posts):
  print post['href'].split('/')[2]