The Hindu Quick Scraper

thehindu.py

#!/usr/bin/python
# Abhinay Omkar

from urllib2 import urlopen
import simplejson as json
from lxml import etree
root = etree.fromstring(urlopen("http://www.thehindu.com/?service=rss").read())
items = root[0].findall('item')

output = []

for item in items:
  item_dict = {}
	item_dict["title"] = item.find('title').text
	item_dict["description"] = item.find('description').text
	item_dict["link"] = item.find('link').text
	item_dict["pubDate"] = item.find('pubDate').text

	output.append(item_dict)

print json.dumps(output, indent=4, separators=(',', ': '))