Read Danas 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.
Dnevne novine sa vestima iz sveta, politike, ekonomije, kulture, sporta, Beograda, Novog Sada i cele Srbije.
Language: sr
Requires Subscription: No, it's available as free ebook
Schedule Every morning
ReadBeam
__license__ = 'GPL v3'
__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
'''
danas.rs
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Danas(BasicNewsRecipe):
title = 'Danas'
__author__ = 'Darko Miletic'
description = 'Dnevne novine sa vestima iz sveta, politike, ekonomije, kulture, sporta, Beograda, Novog Sada i cele Srbije.'
publisher = 'Danas d.o.o.'
category = 'news, politics, Serbia'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = False
use_embedded_content = False
encoding = 'utf-8'
masthead_url = 'http://www.danas.rs/images/basic/danas.gif'
language = 'sr'
remove_javascript = True
publication_type = 'newspaper'
remove_empty_feeds = True
extra_css = """ @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}
@font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
.article,.articledescription,body,.lokacija,.feed{font-family: Tahoma,Arial,Helvetica,sans1,sans-serif}
.nadNaslov,h1,.preamble{font-family: Georgia,"Times New Roman",Times,serif1,serif}
.antrfileText{border-left: 2px solid #999999;
margin-left: 0.8em;
padding-left: 1.2em;
margin-bottom: 0;
margin-top: 0}
h2,.datum,.lokacija,.autor{font-size: small}
.autor{text-transform: uppercase}
.antrfileNaslov{border-left: 2px solid #999999;
margin-left: 0.8em;
padding-left: 1.2em;
font-weight:bold;
margin-bottom: 0;
margin-top: 0}
img{margin-bottom: 0.8em}
.naslovTemeDana{font-size: small}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
preprocess_regexps = [
(re.compile(u'\u0110'), lambda match: u'\u00D0')
,(re.compile(u'\u2018'), lambda match: '‘') # left single quotation mark
,(re.compile(u'\u2019'), lambda match: '’') # right single quotation mark
,(re.compile(u'\u201a'), lambda match: '‘') # single low-9 quotation mark
,(re.compile(u'\u201b'), lambda match: '’') # single high-reversed-9 quotation mark
,(re.compile(u'\u201c'), lambda match: '“') # left double quotation mark
,(re.compile(u'\u201d'), lambda match: '”') # right double quotation mark
,(re.compile(u'\u201e'), lambda match: '“') # double low-9 quotation mark
,(re.compile(u'\u201f'), lambda match: '”') # double high-reversed-9 quotation mark
,(re.compile(u'\u00f4'), lambda match: '“') # latin small letter o with circumflex
,(re.compile(u'\u00f6'), lambda match: '”') # latin small letter o with dieaeresis
,(re.compile(u'\u00e1'), lambda match: ' ' ) # latin small letter a with acute
,(re.compile(u'\u00e4'), lambda match: ' ' ) # latin small letter a with dieaeresis
]
keep_only_tags = [dict(name='div', attrs={'id':'left'})]
remove_tags = [
dict(name='div', attrs={'class':['width_1_4','metaClanka','baner','listaVesti','article_nav']})
,dict(name='div', attrs={'id':'comments'})
,dict(name=['object','link','iframe','meta'])
]
remove_attributes = ['w:st','st']
feeds = [
(u'Politika' , u'http://www.danas.rs/rss/rss.asp?column_id=27')
,(u'Hronika' , u'http://www.danas.rs/rss/rss.asp?column_id=2' )
,(u'Drustvo' , u'http://www.danas.rs/rss/rss.asp?column_id=24')
,(u'Dijalog' , u'http://www.danas.rs/rss/rss.asp?column_id=1' )
,(u'Ekonomija' , u'http://www.danas.rs/rss/rss.asp?column_id=6' )
,(u'Svet' , u'http://www.danas.rs/rss/rss.asp?column_id=25')
,(u'Srbija' , u'http://www.danas.rs/rss/rss.asp?column_id=28')
,(u'Kultura' , u'http://www.danas.rs/rss/rss.asp?column_id=5' )
,(u'Sport' , u'http://www.danas.rs/rss/rss.asp?column_id=13')
,(u'Scena' , u'http://www.danas.rs/rss/rss.asp?column_id=42')
,(u'Feljton' , u'http://www.danas.rs/rss/rss.asp?column_id=19')
,(u'Periskop' , u'http://www.danas.rs/rss/rss.asp?column_id=4' )
,(u'Famozno' , u'http://www.danas.rs/rss/rss.asp?column_id=47')
,(u'Sluzbena beleska' , u'http://www.danas.rs/rss/rss.asp?column_id=48')
,(u'Suocavanja' , u'http://www.danas.rs/rss/rss.asp?column_id=49')
,(u'Moj Izbor' , u'http://www.danas.rs/rss/rss.asp?column_id=50')
,(u'Direktno' , u'http://www.danas.rs/rss/rss.asp?column_id=51')
,(u'I tome slicno' , u'http://www.danas.rs/rss/rss.asp?column_id=52')
,(u'No longer and not yet', u'http://www.danas.rs/rss/rss.asp?column_id=53')
,(u'Resetovanje' , u'http://www.danas.rs/rss/rss.asp?column_id=54')
,(u'Iza scene' , u'http://www.danas.rs/rss/rss.asp?column_id=60')
,(u'Drustvoslovlje' , u'http://www.danas.rs/rss/rss.asp?column_id=55')
,(u'Zvaka u pepeljari' , u'http://www.danas.rs/rss/rss.asp?column_id=56')
,(u'Vostani Serbie' , u'http://www.danas.rs/rss/rss.asp?column_id=57')
,(u'Med&Jad-a' , u'http://www.danas.rs/rss/rss.asp?column_id=58')
,(u'Svetlosti pozornice' , u'http://www.danas.rs/rss/rss.asp?column_id=59')
,(u'Dva cvancika' , u'http://www.danas.rs/rss/rss.asp?column_id=65')
,(u'Iz kornera' , u'http://www.danas.rs/rss/rss.asp?column_id=64')
]
def preprocess_html(self, soup):
for tagn in ['st1:place','st1:city','st1:country-region','st1:state']:
for item in soup.body.findAll(tagn):
item.name='span'
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('a'):
if item.has_key('name'):
item.extract()
for item in soup.findAll('img'):
if not item.has_key('alt'):
item['alt'] = 'image'
return soup
def print_version(self, url):
return url + '&action=print'
def get_cover_url(self):
cover_url = None
soup = self.index_to_soup('http://www.danas.rs/')
for citem in soup.findAll('img'):
if citem['src'].endswith('naslovna.jpg') or citem['src'].endswith('naslovna1.jpg'):
return 'http://www.danas.rs' + citem['src']
return cover_url