[Divingduck]

A new update to skip some not wanted advertising.

Spoiler:

__license__ = 'GPL v3'
__copyright__ = '2008-2011, Kovid Goyal <kovid at kovidgoyal.net>, Darko Miletic <darko at gmail.com>'
'''
Profile to download FAZ.NET
'''

from calibre.web.feeds.news import BasicNewsRecipe

class FazNet(BasicNewsRecipe):
title = 'FAZ.NET'
__author__ = 'Kovid Goyal, Darko Miletic, Armin Geller' # AGe upd. V7 2016-01-26
description = 'Frankfurter Allgemeine Zeitung'
publisher = 'Frankfurter Allgemeine Zeitung GmbH'
category = 'news, politics, Germany'
use_embedded_content = False
language = 'de'

max_articles_per_feed = 30
no_stylesheets = True
encoding = 'utf-8'
remove_javascript = True

keep_only_tags = [
{'class':['FAZArtikelEinleitung']},
dict(name='div', attrs={'class':'FAZSlimHeader'}),
{'id':'ArtikelTabContent_0'}
]

remove_tags_after = [dict(name='div', attrs={'class':['ArtikelFooter']})]
remove_tags = [
dict(name='div', attrs={'class':['ArtikelFooter','clear']}),
dict(name='div', attrs={'id':['berndsbox','dertagbox']}), # AGe 2016-01-26
dict(name='a', attrs={'title':['Vergrößern']}), # AGe 2014-10-22
dict(name='img', attrs={'class':['VideoCtrlIcon']}), # AGe 2014-10-22
dict(name='span', attrs={'class':['shareAutor']}) # AGe 2014-10-22
]

feeds = [
('FAZ.NET Aktuell', 'http://www.faz.net/aktuell/?rssview=1'),
('Politik', 'http://www.faz.net/aktuell/politik/?rssview=1'),
('Wirtschaft', 'http://www.faz.net/aktuell/wirtschaft/?rssview=1'),
('Feuilleton', 'http://www.faz.net/aktuell/feuilleton/?rssview=1'),
('Sport', 'http://www.faz.net/aktuell/sport/?rssview=1'),
('Lebensstil', 'http://www.faz.net/aktuell/lebensstil/?rssview=1'),
('Gesellschaft', 'http://www.faz.net/aktuell/gesellschaft/?rssview=1'),
('Finanzen', 'http://www.faz.net/aktuell/finanzen/?rssview=1'),
('Technik & Motor', 'http://www.faz.net/aktuell/technik-motor/?rssview=1'),
('Wissen', 'http://www.faz.net/aktuell/wissen/?rssview=1'),
('Reise', 'http://www.faz.net/aktuell/reise/?rssview=1'),
('Beruf & Chance', 'http://www.faz.net/aktuell/beruf-chance/?rssview=1'),
('Rhein-Main', 'http://www.faz.net/aktuell/rhein-main/?rssview=1')
]

# AGe 2014-01-10 For multipages
INDEX = ''
def append_page(self, soup, appendtag, position):
pager = soup.find('a',attrs={'title':'Nächste Seite'})
if pager:
nexturl = self.INDEX + pager['href']
soup2 = self.index_to_soup(nexturl)
texttag = soup2.find('div', attrs={'class':'FAZArtikelContent'})
for cls in (
'ArtikelFooter', 'ArtikelAbbinder',
'ArtikelKommentieren Artikelfuss GETS;tk;boxen.top-lesermeinungen;tp;content',
'Anzeige GoogleAdsBuehne', 'ThemenLinks', 'rechtehinweis',
'stageModule Ressortmodul Rubrikenkopf clearfix', 'VideoCtrlIcon',
'ArtikelAbbinder clearfix',
'stageModule clearfix GETS;tk;artikel.empfehlungen.weitere-artikel;tp;content',
'ThemenLinks',
): # AGe 2014-10-22
div = texttag.find(attrs={'class':cls})
if div is not None:
div.extract()
for cls in (
'berndsbox','dertagbox'): # AGe 2016-01-26
div = texttag.find(attrs={'id':cls})
if div is not None:
div.extract()
div = texttag.find(attrs={'title':'Vergrößern'}) # AGe 2014-10-22
if div is not None:
div.extract()
newpos = len(texttag.contents)
self.append_page(soup2,texttag,newpos)
texttag.extract()
pager.extract()
appendtag.insert(position,texttag)

def preprocess_html(self, soup):
self.append_page(soup, soup.body, 3)
for img in soup.findAll('img', attrs={'data-src':True}):
img['src'] = img['data-src']
return self.adeify_images(soup)

def postprocess_html(self, soup, first_fetch):
for div in soup.findAll(id='ArticlePagerBottom'):
div.extract()
for div in soup.findAll('div', attrs={'class':'clear'}): # AGe add 2014-10-24
div.extract()
return soup

As always, let me know if there are any issues with this version.

DivingDuck