From 2dea2852a73dd6075e0227bfca43bf579f9d8daa Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Thu, 25 Aug 2011 22:03:29 -0600 Subject: [PATCH] Improve Reuters --- recipes/reuters.recipe | 35 +++++++++++++++++------------------ 1 file changed, 17 insertions(+), 18 deletions(-) diff --git a/recipes/reuters.recipe b/recipes/reuters.recipe index 8cc638a760..313e6b8607 100644 --- a/recipes/reuters.recipe +++ b/recipes/reuters.recipe @@ -16,23 +16,25 @@ class Reuters(BasicNewsRecipe): remove_javascript = True extra_css = ''' - body{font-family:arial,helvetica,sans;} + body{font-family:arial,helvetica,sans;} h1{ font-size:larger ; font-weight:bold; } .byline{color:#006E97;font-size:x-small; font-weight:bold;} .location{font-size:x-small; font-weight:bold;} .timestamp{font-size:x-small; } - ''' + ''' keep_only_tags = [dict(name='div', attrs={'class':'column2 gridPanel grid8'})] - remove_tags = [dict(name='div', attrs={'id':['recommendedArticles','relatedNews','relatedVideo','relatedFactboxes']}), dict(name='p', attrs={'class':['relatedTopics']}), - dict(name='a', attrs={'id':['fullSizeLink']}), - dict(name='div', attrs={'class':['photoNav','relatedTopicButtons','articleComments','gridPanel grid8','footerHalf gridPanel grid1','gridPanel grid2','gridPanel grid3']}),] + dict(name='a', attrs={'id':['fullSizeLink']}), + dict(name='div', attrs={'class':['photoNav','relatedTopicButtons','articleComments','gridPanel grid8','footerHalf gridPanel grid1','gridPanel grid2','gridPanel grid3']}), + # Remove the Tweet, Share this, Email and Print links below article title too! + dict(name='div', attrs={'class':['columnRight']}), + ] preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in -[ + [ ##(r'.*?' , lambda match : ''), (r'
.*?', lambda match : ''), (r'.*?', lambda match : ''), @@ -40,18 +42,15 @@ class Reuters(BasicNewsRecipe): (r'.*?
', lambda match : ''), (r'

Share:

.*?', lambda match : ''), (r'
.*?
', lambda match : '
'), - ] - ] - + ]] feeds = [ ('Top Stories', 'http://feeds.reuters.com/reuters/topNews?format=xml'), - ('US News', 'http://feeds.reuters.com/reuters/domesticNews?format=xml'), - ('World News', 'http://feeds.reuters.com/reuters/worldNews?format=xml'), - ('Politics News', 'http://feeds.reuters.com/reuters/politicsNews?format=xml'), - ('Science News', 'http://feeds.reuters.com/reuters/scienceNews?format=xml'), - ('Environment News', 'http://feeds.reuters.com/reuters/Environment?format=xml'), - ('Technology News', 'http://feeds.reuters.com/reuters/technologyNews?format=xml'), - ('Oddly Enough News', 'http://feeds.reuters.com/reuters/oddlyEnoughNews?format=xml') - ] - + ('US News', 'http://feeds.reuters.com/reuters/domesticNews?format=xml'), + ('World News', 'http://feeds.reuters.com/reuters/worldNews?format=xml'), + ('Politics News', 'http://feeds.reuters.com/reuters/politicsNews?format=xml'), + ('Science News', 'http://feeds.reuters.com/reuters/scienceNews?format=xml'), + ('Environment News', 'http://feeds.reuters.com/reuters/Environment?format=xml'), + ('Technology News', 'http://feeds.reuters.com/reuters/technologyNews?format=xml'), + ('Oddly Enough News', 'http://feeds.reuters.com/reuters/oddlyEnoughNews?format=xml') + ]