calibre/recipes/deutsche_welle_sr.recipe
2019-03-22 23:47:49 +05:30

77 lines
2.9 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
dw-world.de
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class DeutscheWelle_sr(BasicNewsRecipe):
title = 'Deutsche Welle'
__author__ = 'Darko Miletic'
description = 'Vesti iz Nemacke i sveta'
publisher = 'Deutsche Welle'
category = 'news, politics, Germany'
oldest_article = 1
max_articles_per_feed = 100
use_embedded_content = False
no_stylesheets = True
language = 'sr'
publication_type = 'newsportal'
remove_empty_feeds = True
masthead_url = 'http://www.dw-world.de/skins/std/channel1/pics/dw_logo1024.gif'
extra_css = """
@font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
body{font-family: Arial,sans1,sans-serif}
img{margin-top: 0.5em; margin-bottom: 0.2em; display: block}
.caption{font-size: x-small; display: block; margin-bottom: 0.4em}
"""
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
remove_tags = [
dict(name=['iframe', 'embed', 'object', 'form', 'base', 'meta', 'link']), dict(
attrs={'class': 'actionFooter'})
]
keep_only_tags = [dict(attrs={'class': 'ArticleDetail detail'})]
remove_attributes = ['height', 'width', 'onclick', 'border', 'lang']
feeds = [
(u'Politika', u'http://rss.dw-world.de/rdf/rss-ser-pol'),
(u'Srbija', u'http://rss.dw-world.de/rdf/rss-ser-pol-ser'),
(u'Region', u'http://rss.dw-world.de/rdf/rss-ser-pol-region'),
(u'Evropa', u'http://rss.dw-world.de/rdf/rss-ser-pol-eu'),
(u'Nemacka', u'http://rss.dw-world.de/rdf/rss-ser-pol-ger'),
(u'Svet', u'http://rss.dw-world.de/rdf/rss-ser-pol-ger'),
(u'Pregled stampe', u'http://rss.dw-world.de/rdf/rss-ser-pol-ger'),
(u'Nauka Tehnika Medicina', u'http://rss.dw-world.de/rdf/rss-ser-science'),
(u'Kultura', u'feed:http://rss.dw-world.de/rdf/rss-ser-cul')
]
def print_version(self, url):
artl = url.rpartition('/')[2]
return 'http://www.dw-world.de/popups/popup_printcontent/' + artl
def preprocess_html(self, soup):
for item in soup.findAll('a'):
limg = item.find('img')
if item.string is not None:
str = item.string
item.replaceWith(str)
else:
if limg:
item.name = 'div'
del item['href']
item['target'] = ''
del item['target']
else:
str = self.tag_to_string(item)
item.replaceWith(str)
return soup