Update taz.de (RSS)

This commit is contained in:
Kovid Goyal 2013-07-24 12:16:08 +05:30
parent cbf2bb0c4e
commit f3af580d5e

View File

@ -1,4 +1,3 @@
__license__ = 'GPL v3'
__copyright__ = '2013, Alexander Schremmer <alex@alexanderweb.de>, Robert Riemann <robert@riemann.cc>'
@ -43,15 +42,14 @@ class TazRSSRecipe(BasicNewsRecipe):
# use the cover presented on the homepage
cover_url = 'http://www.taz.de/digitaz/.s1jpeg320'
keep_only_tags = [dict(name='div', attrs={'class': 'sect sect_article'})]
no_stylesheets = True # default value is False, but True makes process much faster
keep_only_tags = [
dict(name=['div'], attrs={'class': re.compile(r".*\bsect_article\b.*")})
]
remove_tags = [
dict(name=['div'], attrs={'class': 'artikelwerbung'}),
dict(name=['ul'], attrs={'class': 'toolbar'}),
dict(name=['div'], attrs={'class': 'sectfoot'}),
# remove: taz paywall
dict(name=['div'], attrs={'id': 'tzi_paywall'}),
# remove: Artikel zum Thema (not working on Kindle)
dict(name=['div'], attrs={'class': re.compile(r".*\bsect_seealso\b.*")}),
dict(name=['div'], attrs={'class': 'sectfoot'})
dict(name=['div'], attrs={'id': 'tzi_paywall'})
]
# with article pictures on Kindle super-slow