Improve Reuters

This commit is contained in:
Kovid Goyal 2011-08-25 22:03:29 -06:00
parent 1f903f4b70
commit 2dea2852a7

View File

@ -25,11 +25,13 @@ class Reuters(BasicNewsRecipe):
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='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
[
@ -40,9 +42,7 @@ class Reuters(BasicNewsRecipe):
(r'<body>.*?<div class="contentBand">', lambda match : '<body>'),
(r'<h3>Share:</h3>.*?</body>', lambda match : '<!-- END:: Shared Module id=36615 --></body>'),
(r'<div id="atools" class="articleTools">.*?<div class="linebreak">', lambda match : '<div class="linebreak">'),
]
]
]]
feeds = [ ('Top Stories', 'http://feeds.reuters.com/reuters/topNews?format=xml'),
@ -54,4 +54,3 @@ class Reuters(BasicNewsRecipe):
('Technology News', 'http://feeds.reuters.com/reuters/technologyNews?format=xml'),
('Oddly Enough News', 'http://feeds.reuters.com/reuters/oddlyEnoughNews?format=xml')
]