Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update FAZ.net

Browse Source
This commit is contained in:
Kovid Goyal 2015-02-04 08:24:44 +05:30
parent ff1a8f9eec
commit 2a4e027b0b
1 changed files with 36 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

64
recipes/faznet.recipe
View File

@ -20,33 +20,35 @@ class FazNet(BasicNewsRecipe):
encoding = 'utf-8' encoding = 'utf-8'
remove_javascript = True remove_javascript = True
keep_only_tags = [{'class':['FAZArtikelEinleitung']}, keep_only_tags = [
dict(name='div', attrs={'class':'FAZSlimHeader'}), {'class':['FAZArtikelEinleitung']},
{'id':'ArtikelTabContent_0'} dict(name='div', attrs={'class':'FAZSlimHeader'}),
] {'id':'ArtikelTabContent_0'}
]
remove_tags_after = [dict(name='div', attrs={'class':['ArtikelFooter']})] remove_tags_after = [dict(name='div', attrs={'class':['ArtikelFooter']})]
remove_tags = [dict(name='div', attrs={'class':['ArtikelFooter','clear']}), remove_tags = [
dict(name='a', attrs={'title':['Vergrößern']}), #AGe 2014-10-22 dict(name='div', attrs={'class':['ArtikelFooter','clear']}),
dict(name='img', attrs={'class':['VideoCtrlIcon']}), #AGe 2014-10-22 dict(name='a', attrs={'title':['Vergrößern']}), # AGe 2014-10-22
dict(name='span', attrs={'class':['shareAutor']}) #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 = [ feeds = [
('FAZ.NET Aktuell', 'http://www.faz.net/aktuell/?rssview=1'), ('FAZ.NET Aktuell', 'http://www.faz.net/aktuell/?rssview=1'),
('Politik', 'http://www.faz.net/aktuell/politik/?rssview=1'), ('Politik', 'http://www.faz.net/aktuell/politik/?rssview=1'),
('Wirtschaft', 'http://www.faz.net/aktuell/wirtschaft/?rssview=1'), ('Wirtschaft', 'http://www.faz.net/aktuell/wirtschaft/?rssview=1'),
('Feuilleton', 'http://www.faz.net/aktuell/feuilleton/?rssview=1'), ('Feuilleton', 'http://www.faz.net/aktuell/feuilleton/?rssview=1'),
('Sport', 'http://www.faz.net/aktuell/sport/?rssview=1'), ('Sport', 'http://www.faz.net/aktuell/sport/?rssview=1'),
('Lebensstil', 'http://www.faz.net/aktuell/lebensstil/?rssview=1'), ('Lebensstil', 'http://www.faz.net/aktuell/lebensstil/?rssview=1'),
('Gesellschaft', 'http://www.faz.net/aktuell/gesellschaft/?rssview=1'), ('Gesellschaft', 'http://www.faz.net/aktuell/gesellschaft/?rssview=1'),
('Finanzen', 'http://www.faz.net/aktuell/finanzen/?rssview=1'), ('Finanzen', 'http://www.faz.net/aktuell/finanzen/?rssview=1'),
('Technik & Motor', 'http://www.faz.net/aktuell/technik-motor/?rssview=1'), ('Technik & Motor', 'http://www.faz.net/aktuell/technik-motor/?rssview=1'),
('Wissen', 'http://www.faz.net/aktuell/wissen/?rssview=1'), ('Wissen', 'http://www.faz.net/aktuell/wissen/?rssview=1'),
('Reise', 'http://www.faz.net/aktuell/reise/?rssview=1'), ('Reise', 'http://www.faz.net/aktuell/reise/?rssview=1'),
('Beruf & Chance', 'http://www.faz.net/aktuell/beruf-chance/?rssview=1'), ('Beruf & Chance', 'http://www.faz.net/aktuell/beruf-chance/?rssview=1'),
('Rhein-Main', 'http://www.faz.net/aktuell/rhein-main/?rssview=1') ('Rhein-Main', 'http://www.faz.net/aktuell/rhein-main/?rssview=1')
] ]
# AGe 2014-01-10 For multipages # AGe 2014-01-10 For multipages
INDEX = '' INDEX = ''
@ -56,16 +58,20 @@ class FazNet(BasicNewsRecipe):
nexturl = self.INDEX + pager['href'] nexturl = self.INDEX + pager['href']
soup2 = self.index_to_soup(nexturl) soup2 = self.index_to_soup(nexturl)
texttag = soup2.find('div', attrs={'class':'FAZArtikelContent'}) texttag = soup2.find('div', attrs={'class':'FAZArtikelContent'})
for cls in ('ArtikelFooter', 'ArtikelAbbinder', 'ArtikelKommentieren Artikelfuss GETS;tk;boxen.top-lesermeinungen;tp;content', 'Anzeige GoogleAdsBuehne', for cls in (
'ThemenLinks', 'rechtehinweis', 'stageModule Ressortmodul Rubrikenkopf clearfix', 'VideoCtrlIcon', 'ArtikelAbbinder clearfix', 'ArtikelFooter', 'ArtikelAbbinder',
'stageModule clearfix GETS;tk;artikel.empfehlungen.weitere-artikel;tp;content'): #AGe 2014-10-22 '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}) div = texttag.find(attrs={'class':cls})
if div is not None: if div is not None:
div.extract() 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: if div is not None:
div.extract() div.extract()
newpos = len(texttag.contents) newpos = len(texttag.contents)
self.append_page(soup2,texttag,newpos) self.append_page(soup2,texttag,newpos)
texttag.extract() texttag.extract()
@ -74,6 +80,8 @@ class FazNet(BasicNewsRecipe):
def preprocess_html(self, soup): def preprocess_html(self, soup):
self.append_page(soup, soup.body, 3) 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) return self.adeify_images(soup)
def postprocess_html(self, soup, first_fetch): def postprocess_html(self, soup, first_fetch):