From 287fa218aa033a413b6f9a48da33d0bf3fc6c316 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sun, 16 Apr 2017 10:18:54 +0530 Subject: [PATCH] Update NYTimes Tech Beat --- recipes/nytimes_tech.recipe | 30 ++++++++++-------------------- 1 file changed, 10 insertions(+), 20 deletions(-) diff --git a/recipes/nytimes_tech.recipe b/recipes/nytimes_tech.recipe index c4647e0a69..efd3edfdbe 100644 --- a/recipes/nytimes_tech.recipe +++ b/recipes/nytimes_tech.recipe @@ -9,6 +9,13 @@ __docformat__ = 'restructuredtext en' from calibre.web.feeds.news import BasicNewsRecipe +def classes(classes): + q = frozenset(classes.split(' ')) + return dict( + attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)} + ) + + class NYTimesTechnology(BasicNewsRecipe): title = 'New York Times Technology Beat' language = 'en' @@ -20,30 +27,13 @@ class NYTimesTechnology(BasicNewsRecipe): remove_empty_feeds = True no_stylesheets = True language = 'en' - cover_url = 'http://bit.ly/g0SKJT' feeds = [ - (u'Bits', u'http://bits.blogs.nytimes.com/feed/'), - (u'Gadgetwise', u'http://gadgetwise.blogs.nytimes.com/feed/'), - (u'Open', u'http://open.blogs.nytimes.com/feed/') + (u'Gadgetwise', u'http://gadgetwise.blogs.nytimes.com/feed/'), ] keep_only_tags = [ - dict(name='div', attrs={'id': ['story-body', 'header', 'story-meta']}), dict(name='h1'), - dict(name='h2'), - dict(name='div', attrs={'class': 'entry-content'}) + classes('extended-byline story-body'), ] remove_tags = [ - dict(id='lede-ad'), - dict(attrs={'class': lambda x: x and 'ad' in x.split()}), - dict(attrs={'class': lambda x: x and 'nocontent' in x.split()}), + classes('visually-hidden newsletter-signup nocontent robots-nocontent hidden'), ] - extra_css = ''' - h1{font-family:Arial,Helvetica,sans-serif; - font-weight:bold;font-size:large;} - - h2{font-family:Arial,Helvetica,sans-serif; - font-weight:normal;font-size:small;} - - p{font-family:Arial,Helvetica,sans-serif;font-size:small;} - body{font-family:Helvetica,Arial,sans-serif;font-size:small;} - '''