Read Pobjeda Online on your iPad or Kindle in no time. Click download to load the free ebook on your reader.
Check out all the available public recipes or write your own with these quick start guides. ReadBeam is built on calibre, so everything in the docs and the fora applies here as well.
News from Montenegro
Language: sr
Requires Subscription: No, it's available as free ebook
Schedule Every morning
ReadBeam
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
pobjeda.co.me
'''
import re
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class Pobjeda(BasicNewsRecipe):
title = 'Pobjeda Online'
__author__ = 'Darko Miletic'
description = 'News from Montenegro'
publisher = 'Pobjeda a.d.'
category = 'news, politics, Montenegro'
no_stylesheets = True
encoding = 'utf-8'
use_embedded_content = False
language = 'sr'
lang = 'sr-Latn-Me'
INDEX = u'http://www.pobjeda.co.me'
extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: serif1, serif}'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : lang
, 'pretty_print' : True
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
keep_only_tags = [dict(name='div', attrs={'class':'vijest'})]
remove_tags = [dict(name=['object','link'])]
feeds = [
(u'Politika' , u'http://www.pobjeda.co.me/rubrika.php?rubrika=1' )
,(u'Ekonomija' , u'http://www.pobjeda.co.me/rubrika.php?rubrika=2' )
,(u'Drustvo' , u'http://www.pobjeda.co.me/rubrika.php?rubrika=3' )
,(u'Crna Hronika' , u'http://www.pobjeda.co.me/rubrika.php?rubrika=4' )
,(u'Kultura' , u'http://www.pobjeda.co.me/rubrika.php?rubrika=5' )
,(u'Hronika Podgorice' , u'http://www.pobjeda.co.me/rubrika.php?rubrika=7' )
,(u'Feljton' , u'http://www.pobjeda.co.me/rubrika.php?rubrika=8' )
,(u'Crna Gora' , u'http://www.pobjeda.co.me/rubrika.php?rubrika=9' )
,(u'Svijet' , u'http://www.pobjeda.co.me/rubrika.php?rubrika=202')
,(u'Ekonomija i Biznis', u'http://www.pobjeda.co.me/dodatak.php?rubrika=11' )
,(u'Djeciji Svijet' , u'http://www.pobjeda.co.me/dodatak.php?rubrika=12' )
,(u'Kultura i Drustvo' , u'http://www.pobjeda.co.me/dodatak.php?rubrika=13' )
,(u'Agora' , u'http://www.pobjeda.co.me/dodatak.php?rubrika=133')
,(u'Ekologija' , u'http://www.pobjeda.co.me/dodatak.php?rubrika=252')
]
def preprocess_html(self, soup):
soup.html['xml:lang'] = self.lang
soup.html['lang'] = self.lang
mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=UTF-8")])
soup.head.insert(0,mlang)
soup.head.insert(1,mcharset)
return self.adeify_images(soup)
def get_cover_url(self):
cover_url = None
soup = self.index_to_soup(self.INDEX)
cover_item = soup.find('img',attrs={'alt':'Naslovna strana'})
if cover_item:
cover_url = self.INDEX + cover_item.parent['href']
return cover_url
def parse_index(self):
totalfeeds = []
lfeeds = self.get_feeds()
for feedobj in lfeeds:
feedtitle, feedurl = feedobj
self.report_progress(0, _('Fetching feed')+' %s...'%(feedtitle if feedtitle else feedurl))
articles = []
soup = self.index_to_soup(feedurl)
for item in soup.findAll('div', attrs={'class':'vijest'}):
description = self.tag_to_string(item.h2)
atag = item.h1.find('a')
if atag and atag.has_key('href'):
url = self.INDEX + '/' + atag['href']
title = self.tag_to_string(atag)
date = strftime(self.timefmt)
articles.append({
'title' :title
,'date' :date
,'url' :url
,'description':description
})
totalfeeds.append((feedtitle, articles))
return totalfeeds