From c9a6bd6175e091cafd17180d1ca36c4df039010d Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 11 Feb 2012 22:51:41 +0530 Subject: [PATCH] Fix Daily Mirror --- recipes/daily_mirror.recipe | 47 +++++++++++++++++++++++++++---------- 1 file changed, 35 insertions(+), 12 deletions(-) diff --git a/recipes/daily_mirror.recipe b/recipes/daily_mirror.recipe index 800eaf10e9..d6794b1d97 100644 --- a/recipes/daily_mirror.recipe +++ b/recipes/daily_mirror.recipe @@ -5,7 +5,7 @@ class AdvancedUserRecipe1306061239(BasicNewsRecipe): description = 'News as provide by The Daily Mirror -UK' __author__ = 'Dave Asbury' - # last updated 26/12/11 + # last updated 11/2/12 language = 'en_GB' cover_url = 'http://yookeo.com/screens/m/i/mirror.co.uk.jpg' @@ -14,35 +14,58 @@ class AdvancedUserRecipe1306061239(BasicNewsRecipe): oldest_article = 1 - max_articles_per_feed = 20 + max_articles_per_feed = 5 remove_empty_feeds = True remove_javascript = True no_stylesheets = True auto_cleanup = True + #conversion_options = { 'linearize_tables' : True } + + + #keep_only_tags = [ + # dict(name='h1'), + # dict(name='div',attrs={'id' : 'body-content'}), + #dict(name='div',atts={'class' : 'article-body'}), + #dict(attrs={'class' : ['article-attr','byline append-1','published']}), + #dict(name='p'), + # ] + + #remove_tags_after = [dict (name='div',attrs={'class' : 'related'})] + remove_tags = [ dict(name='title'), dict(name='div',attrs={'class' : ['inline-ad span-16 last','caption']}), + # dict(name='div',attrs={'id' : ['sidebar','menu','search-box','roffers-top']}), + #dict(name='div',attrs={'class' :['inline-ad span-16 last','article-resize','related','list teasers']}), + #dict(attrs={'class' : ['channellink','article-tags','replace','append-html']}), ] + # preprocess_regexps = [ + #(re.compile(r'
.*?
', re.IGNORECASE | re.DOTALL), lambda match: '')] preprocess_regexps = [ (re.compile(r'- mirror.co.uk', re.IGNORECASE | re.DOTALL), lambda match: '')] preprocess_regexps = [ (re.compile(r'Advertisement >>', re.IGNORECASE | re.DOTALL), lambda match: '')] + #preprocess_regexps = [ + #(re.compile(r'Sponsored Links', re.IGNORECASE | re.DOTALL), lambda match: '')] feeds = [ - (u'News', u'http://www.mirror.co.uk/news/rss.xml') - ,(u'Tech News', u'http://www.mirror.co.uk/news/technology/rss.xml') - ,(u'Weird World','http://www.mirror.co.uk/news/weird-world/rss.xml') - ,(u'Film Gossip','http://www.mirror.co.uk/celebs/film/rss.xml') - ,(u'Music News','http://www.mirror.co.uk/celebs/music/rss.xml') - ,(u'Celebs and Tv Gossip','http://www.mirror.co.uk/celebs/tv/rss.xml') - ,(u'Sport','http://www.mirror.co.uk/sport/rss.xml') - ,(u'Life Style','http://www.mirror.co.uk/life-style/rss.xml') - ,(u'Advice','http://www.mirror.co.uk/advice/rss.xml') - ,(u'Travel','http://www.mirror.co.uk/advice/travel/rss.xml') + (u'UK News', u'http://feed43.com/0287771688643868.xml') + ,(u'Tech News', u'http://feed43.com/2455520588350501.xml') + ,(u'Weird World','http://feed43.com/0863800333634654.xml') + ,(u'Sport','http://feed43.com/7713243036546130.xml') + ,(u'Sport : Boxing ','http://feed43.com/0414732220804255.xml') + ,(u'Sport : Rugby Union','http://feed43.com/4710138762362383.xml') + ,(u'Sport : Other','http://feed43.com/4501416886323415.xml') + ,(u'TV and Film','http://feed43.com/5238302853765104.xml') + ,(u'Celebs','http://feed43.com/8770061048844683.xml') + ,(u'Life Style : Family','http://feed43.com/4356170742410338.xml') + ,(u'Travel','http://feed43.com/1436576006476607.xml') + + # example of commented out feed not needed ,(u'Travel','http://www.mirror.co.uk/advice/travel/rss.xml') ]