doganeskinat.py

#!/usr/bin/env python
import sys, datetime
import requests
from StringIO import StringIO
from lxml.html import parse
import PyRSS2Gen

PAGE = 'http://www.dailysabah.com/columns/dogan-eskinat/archive'

# XPath queries
TITLE = '/html/body/div[1]/section/div/div[1]/div/ul[1]/li[%d]/a/span[1]/text()'
LINK = '/html/body/div[1]/section/div/div[1]/div/ul[1]/li[%d]/a/@href'
DATE = '/html/body/div[1]/section/div/div[1]/div/ul[1]/li[%d]/a/span[2]/text()'
DESCRIPTION = '/html/body/div[1]/section/div/div[1]/div/ul[1]/li[%d]/a/text()'


def get_page():
	response = requests.get(PAGE)
	return StringIO(response.content)


def explore(content):
	root = parse(content).getroot()
	articles = []
	for index in range(1, 11):
		articles.append({
				'title' : root.xpath(TITLE % index)[0],
				'link' : 'http://www.dailysabah.com/' + root.xpath(LINK % index)[0],
				'date' : root.xpath(DATE % index)[0],
				'description' : root.xpath(DESCRIPTION % index)[2],
			})
	print articles
	return articles


def make_rss(articles):
	
	rss_items = []
	for article in articles:
		rss_items.append(
			PyRSS2Gen.RSSItem(
				title  = article['title'], 
				link = article['link'], 
				description = article['description'], 
				guid = PyRSS2Gen.Guid(article['link']), 
				pubDate = article['date']
			)
		)

	rss = PyRSS2Gen.RSS2(
		title = 'Dogan Eskinat',
		link = PAGE,
		description = 'Latest articles written by Dogan Eskinat on Daily Sabah',
		lastBuildDate = datetime.datetime.now(),
		items = rss_items
		)

	return rss.to_xml()


def main():
	content = get_page()
	articles = explore(content)
	print make_rss(articles)
	f1=open(str(sys.argv[1]), 'w+')
	f1.write(make_rss(articles))


if __name__ == '__main__':
	main()