Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update FAZ net

Browse Source
This commit is contained in:
Kovid Goyal 2014-10-25 08:00:48 +05:30
parent 86a0594246
commit e85f51f0ef
1 changed files with 35 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
recipes/faznet.recipe
View File

@ -8,7 +8,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class FazNet(BasicNewsRecipe): class FazNet(BasicNewsRecipe):
title = 'FAZ.NET' title = 'FAZ.NET'
__author__ = 'Kovid Goyal, Darko Miletic, Armin Geller' # AGe upd. V4 2014-01-14 __author__ = 'Kovid Goyal, Darko Miletic, Armin Geller' # AGe upd. V6 2014-10-24
description = 'Frankfurter Allgemeine Zeitung' description = 'Frankfurter Allgemeine Zeitung'
publisher = 'Frankfurter Allgemeine Zeitung GmbH' publisher = 'Frankfurter Allgemeine Zeitung GmbH'
category = 'news, politics, Germany' category = 'news, politics, Germany'
@ -20,54 +20,65 @@ class FazNet(BasicNewsRecipe):
encoding = 'utf-8' encoding = 'utf-8'
remove_javascript = True remove_javascript = True
keep_only_tags = [{'class':'FAZArtikelEinleitung'}, keep_only_tags = [{'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']})] remove_tags = [dict(name='div', attrs={'class':['ArtikelFooter','clear']}),
dict(name='a', attrs={'title':['Vergrößern']}), #AGe 2014-10-22
# recursions = 1 # AGe 2014-01-10 dict(name='img', attrs={'class':['VideoCtrlIcon']}), #AGe 2014-10-22
# match_regexps = [r'-p[2-9].html$'] # AGe 2014-01-10 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 New for multipages # AGe 2014-01-10 For multipages
INDEX = '' INDEX = ''
def append_page(self, soup, appendtag, position): # AGe upd 2014-01-14 def append_page(self, soup, appendtag, position):
pager = soup.find('a',attrs={'title':'Nächste Seite'}) pager = soup.find('a',attrs={'title':'Nächste Seite'})
if pager: if pager:
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 ('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}) 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
if div is not None:
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()
pager.extract() pager.extract()
appendtag.insert(position,texttag) appendtag.insert(position,texttag)
def preprocess_html(self, soup): # AGe upd 2014-01-14 def preprocess_html(self, soup):
self.append_page(soup, soup.body, 3) self.append_page(soup, soup.body, 3)
return self.adeify_images(soup) return self.adeify_images(soup)
def postprocess_html(self, soup, first_fetch): # AGe add 2014-01-14 def postprocess_html(self, soup, first_fetch):
for div in soup.findAll(id='ArticlePagerBottom'): for div in soup.findAll(id='ArticlePagerBottom'):
div.extract() div.extract()
for div in soup.findAll('div', attrs={'class':'clear'}): # AGe add 2014-10-24
div.extract()
return soup return soup