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 2016-01-27 08:57:01 +05:30
parent da1c151e1f
commit 8a1263f987
1 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
recipes/faznet.recipe
View File

@ -8,7 +8,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class FazNet(BasicNewsRecipe):
title = 'FAZ.NET'
__author__ = 'Kovid Goyal, Darko Miletic, Armin Geller' # AGe upd. V6 2014-10-24
__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'
@ -29,6 +29,7 @@ class FazNet(BasicNewsRecipe):
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
@ -64,14 +65,20 @@ class FazNet(BasicNewsRecipe):
'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
'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()