mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Update FAZ.net
This commit is contained in:
parent
ff1a8f9eec
commit
2a4e027b0b
@ -20,33 +20,35 @@ class FazNet(BasicNewsRecipe):
|
||||
encoding = 'utf-8'
|
||||
remove_javascript = True
|
||||
|
||||
keep_only_tags = [{'class':['FAZArtikelEinleitung']},
|
||||
dict(name='div', attrs={'class':'FAZSlimHeader'}),
|
||||
{'id':'ArtikelTabContent_0'}
|
||||
]
|
||||
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='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
|
||||
]
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':['ArtikelFooter','clear']}),
|
||||
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')
|
||||
]
|
||||
('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 = ''
|
||||
@ -56,13 +58,17 @@ class FazNet(BasicNewsRecipe):
|
||||
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'): #AGe 2014-10-22
|
||||
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'): # AGe 2014-10-22
|
||||
div = texttag.find(attrs={'class':cls})
|
||||
if div is not None:
|
||||
div.extract()
|
||||
div = texttag.find(attrs={'title':'Vergrößern'}) #AGe 2014-10-22
|
||||
div = texttag.find(attrs={'title':'Vergrößern'}) # AGe 2014-10-22
|
||||
if div is not None:
|
||||
div.extract()
|
||||
|
||||
@ -74,6 +80,8 @@ class FazNet(BasicNewsRecipe):
|
||||
|
||||
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):
|
||||
|
Loading…
x
Reference in New Issue
Block a user