rss_reader.py

# -*- coding: utf-8
from xml.dom import minidom
from urllib import urlopen
from os import getcwd
import codecs
 
class HackingRssReader:
 
    def __init__(self, feed_url = 'http://hacking.pl/rss.xml' ):
        self.feed_url = feed_url# nie ma powodu tego ukrywać
 
    def _get_raw(self):
        response = urlopen(self.feed_url)
        return response.read()

    def _parse_raw(self, source):
        rss = minidom.parseString(source)
        all_news = []
 
        for node in rss.childNodes[0].getElementsByTagName('item'):
            news = []
            for field in ['title', 'description', 'pubDate']:
                news.append(node.getElementsByTagName(field)[0].childNodes[0].toxml())

            all_news.append(news) 
        return all_news

    def get_news(self):
        return self._parse_raw(self._get_raw())

    def save_news_txt(self, news, path, encoding='utf-8'):
        with codecs.open(path, 'wb', encoding) as out:
            out.write(u'#Tytuł\n#Treść\n#Data\n*****\n')
            for item in news:
                out.write(u'\n'.join(item))
            out.write('\n#####\n')

    def print_news(self, news):
        for n, item in enumerate(news):
            print "%d. # %s # %s" %(n, item[0], item[2])
            print item[1]
            print

rss = HackingRssReader()
news = rss.get_news()
rss.print_news(news)