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

...

Browse Source
This commit is contained in:
Kovid Goyal 2014-01-11 09:16:48 +05:30
parent 594906102c
commit da1648b94d
1 changed files with 33 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
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' __author__ = 'Kovid Goyal, Darko Miletic, Armin Geller' # AGe upd. V4 2014-01-10
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'
@ -23,10 +23,11 @@ class FazNet(BasicNewsRecipe):
keep_only_tags = [{'class':'FAZArtikelEinleitung'}, keep_only_tags = [{'class':'FAZArtikelEinleitung'},
{'id':'ArtikelTabContent_0'}] {'id':'ArtikelTabContent_0'}]
remove_tags_after = dict(name='div', attrs={'class':['ArtikelFooter']}) # AGe add 2013-12-19 remove_tags_after = [dict(name='div', attrs={'class':['ArtikelFooter']})]
remove_tags = [dict(name='div', attrs={'class':['ArtikelFooter']})] # AGe add 2013-12-19 remove_tags = [dict(name='div', attrs={'class':['ArtikelFooter']})]
recursions = 1
match_regexps = [r'-p[2-9].html$'] # recursions = 1 # AGe 2014-01-10
# match_regexps = [r'-p[2-9].html$'] # AGe 2014-01-10
feeds = [ feeds = [
('FAZ.NET Aktuell', 'http://www.faz.net/aktuell/?rssview=1'), ('FAZ.NET Aktuell', 'http://www.faz.net/aktuell/?rssview=1'),
@ -34,7 +35,7 @@ class FazNet(BasicNewsRecipe):
('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'), # AGe add 2013-12-19 ('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'),
@ -43,3 +44,29 @@ class FazNet(BasicNewsRecipe):
('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
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'})
texttag.find('div', attrs={'class':'ArtikelFooter'}).extract()
texttag.find('div', attrs={'class':'ArtikelAbbinder'}).extract()
texttag.find('div', attrs={'class':'ArtikelKommentieren Artikelfuss GETS;tk;boxen.top-lesermeinungen;tp;content'}).extract()
texttag.find('div', attrs={'class':'Anzeige GoogleAdsBuehne'}).extract()
texttag.find('div', attrs={'id':'ArticlePagerBottom'}).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)
pager = soup.find('div',attrs={'id':'ArticlePagerBottom'})
if pager:
pager.extract()
return self.adeify_images(soup)