mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-11-01 19:17:02 -04:00
102 lines
4.3 KiB
Plaintext
102 lines
4.3 KiB
Plaintext
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class ADRecipe(BasicNewsRecipe):
|
|
__license__ = 'GPL v3'
|
|
__author__ = 'kwetal'
|
|
language = 'nl'
|
|
country = 'NL'
|
|
version = 1
|
|
|
|
title = u'AD'
|
|
publisher = u'de Persgroep Publishing Nederland NV'
|
|
category = u'News, Sports, the Netherlands'
|
|
description = u'News and Sports from the Netherlands'
|
|
|
|
oldest_article = 1.2
|
|
max_articles_per_feed = 100
|
|
use_embedded_content = False
|
|
|
|
remove_empty_feeds = True
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
|
|
keep_only_tags = []
|
|
keep_only_tags.append(dict(name='div', attrs={'id': 'art_box2'}))
|
|
keep_only_tags.append(dict(name='p', attrs={'class': 'gen_footnote3'}))
|
|
|
|
remove_tags = []
|
|
remove_tags.append(dict(name='div', attrs={'class': 'gen_clear'}))
|
|
remove_tags.append(
|
|
dict(name='div', attrs={'class': re.compile(r'gen_spacer.*')}))
|
|
|
|
remove_attributes = ['style']
|
|
|
|
# feeds from
|
|
# http://ad.nl/ad/nl/1401/home/integration/nmc/frameset/ad_footer/rssFeeds.dhtml
|
|
feeds = []
|
|
feeds.append(
|
|
(u'Binnenland', u'http://www.ad.nl/nieuws/binnenland/rss.xml'))
|
|
feeds.append(
|
|
(u'Buitenland', u'http://www.ad.nl/nieuws/buitenland/rss.xml'))
|
|
feeds.append((u'Bizar', u'http://www.ad.nl/nieuws/bizar/rss.xml'))
|
|
feeds.append((u'Gezondheid & Wetenschap',
|
|
u'http://www.ad.nl/nieuws/gezondheidwetenschap/rss.xml'))
|
|
feeds.append((u'Economie', u'http://www.ad.nl/nieuws/economie/rss.xml'))
|
|
feeds.append((u'Nederlands Voetbal',
|
|
u'http://www.ad.nl/sportwereld/nederlandsvoetbal/rss.xml'))
|
|
feeds.append((u'Buitenlands Voetbal',
|
|
u'http://www.ad.nl/sportwereld/buitenlandsvoetbal/rss.xml'))
|
|
feeds.append((u'Champions League/Europa League',
|
|
u'http://www.ad.nl/sportwereld/championsleagueeuropaleague/rss.xml'))
|
|
feeds.append(
|
|
(u'Wielrennen', u'http://www.ad.nl/sportwereld/wielrennen/rss.xml'))
|
|
feeds.append((u'Tennis', u'http://www.ad.nl/sportwereld/tennis/rss.xml'))
|
|
feeds.append(
|
|
(u'Formule 1', u'http://www.ad.nl/sportwereld/formule1/rss.xml'))
|
|
feeds.append(
|
|
(u'Meer Sport', u'http://www.ad.nl/sportwereld/meersport/rss.xml'))
|
|
feeds.append((u'Celebs', u'http://www.ad.nl/showbizz/celebs/rss.xml'))
|
|
feeds.append((u'Film', u'http://www.ad.nl/showbizz/film/rss.xml'))
|
|
feeds.append((u'Muziek', u'http://www.ad.nl/showbizz/muziek/rss.xml'))
|
|
feeds.append((u'TV', u'http://www.ad.nl/showbizz/tv/rss.xml'))
|
|
feeds.append((u'Kunst & Literatuur',
|
|
u'http://www.ad.nl/showbizz/kunstenliteratuur/rss.xml'))
|
|
feeds.append((u'Jouw Wereld', u'http://www.ad.nl/you/rss.xml'))
|
|
feeds.append((u'Consument', u'http://www.ad.nl/consument/rss.xml'))
|
|
feeds.append((u'Autowereld', u'http://www.ad.nl/autowereld/rss.xml'))
|
|
feeds.append((u'Reiswereld', u'http://www.ad.nl/reiswereld/rss.xml'))
|
|
feeds.append((u'Internet', u'http://www.ad.nl/digitaal/internet/rss.xml'))
|
|
feeds.append((u'Games', u'http://www.ad.nl/digitaal/games/rss.xml'))
|
|
feeds.append(
|
|
(u'Multimedia', u'http://www.ad.nl/digitaal/multimedia/rss.xml'))
|
|
feeds.append((u'Planet Watch', u'http://www.ad.nl/planetwatch/rss.xml'))
|
|
|
|
extra_css = '''
|
|
body {font-family: verdana, arial, helvetica, geneva, sans-serif;}
|
|
div.captionEmbeddedMasterObject {font-size: x-small; font-style: italic; color: #696969;}
|
|
.gen_footnote3 {font-size: small; color: #666666; margin-top: 0.6em;}
|
|
'''
|
|
|
|
conversion_options = {'comments': description, 'tags': category, 'language': 'en',
|
|
'publisher': publisher}
|
|
|
|
def print_version(self, url):
|
|
parts = url.split('/')
|
|
print_url = 'http://' + parts[2] + '/' + parts[3] + '/' + parts[4] + '/' + parts[5] + '/' \
|
|
+ parts[10] + '/' + parts[7] + '/print/' + \
|
|
parts[8] + '/' + parts[9] + '/' + parts[13]
|
|
|
|
return print_url
|
|
|
|
def preprocess_html(self, soup):
|
|
for br in soup.findAll('br'):
|
|
prev = br.findPreviousSibling(True)
|
|
if hasattr(prev, 'name') and prev.name == 'br':
|
|
next = br.findNextSibling(True)
|
|
if hasattr(next, 'name') and next.name == 'br':
|
|
br.extract()
|
|
|
|
return soup
|