From d7a4db942a7040ac1dc4773246062826389c188d Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Tue, 8 Sep 2015 08:32:42 +0530 Subject: [PATCH] Update New York Times Technology Beat --- recipes/nytimes_tech.recipe | 29 ++++++++++++++++------------- 1 file changed, 16 insertions(+), 13 deletions(-) diff --git a/recipes/nytimes_tech.recipe b/recipes/nytimes_tech.recipe index 1e5ca9bd0a..64d03a5f2e 100644 --- a/recipes/nytimes_tech.recipe +++ b/recipes/nytimes_tech.recipe @@ -5,9 +5,6 @@ from __future__ import with_statement __license__ = 'GPL 3' __copyright__ = 'zotzo' __docformat__ = 'restructuredtext en' -""" -http://pogue.blogs.nytimes.com/ -""" from calibre.web.feeds.news import BasicNewsRecipe @@ -15,25 +12,31 @@ from calibre.web.feeds.news import BasicNewsRecipe class NYTimesTechnology(BasicNewsRecipe): title = 'New York Times Technology Beat' language = 'en' - __author__ = 'David Pogue' description = 'The latest in technology from David Pogue' publisher = 'The New York Times' category = 'Technology' oldest_article = 14 max_articles_per_feed = 25 + remove_empty_feeds = True no_stylesheets = True language = 'en' cover_url ='http://bit.ly/g0SKJT' feeds = [ - (u'News', u'http://pogue.blogs.nytimes.com/feed/'), - (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/') - ] - keep_only_tags = [dict(name='div', attrs={'id':'header'}), - dict(name='h1'), - dict(name='h2'), - dict(name='div', attrs={'class':'entry-content'})] + (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/') + ] + 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'}) + ] + 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()}), + ] extra_css = ''' h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}