Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Improve Reuters

Browse Source
This commit is contained in:
Kovid Goyal 2011-08-25 22:03:29 -06:00
parent 1f903f4b70
commit 2dea2852a7
1 changed files with 17 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
recipes/reuters.recipe
View File

@ -16,23 +16,25 @@ class Reuters(BasicNewsRecipe):
remove_javascript = True remove_javascript = True
extra_css = ''' extra_css = '''
body{font-family:arial,helvetica,sans;} body{font-family:arial,helvetica,sans;}
h1{ font-size:larger ; font-weight:bold; } h1{ font-size:larger ; font-weight:bold; }
.byline{color:#006E97;font-size:x-small; font-weight:bold;} .byline{color:#006E97;font-size:x-small; font-weight:bold;}
.location{font-size:x-small; font-weight:bold;} .location{font-size:x-small; font-weight:bold;}
.timestamp{font-size:x-small; } .timestamp{font-size:x-small; }
''' '''
keep_only_tags = [dict(name='div', attrs={'class':'column2 gridPanel grid8'})] keep_only_tags = [dict(name='div', attrs={'class':'column2 gridPanel grid8'})]
remove_tags = [dict(name='div', attrs={'id':['recommendedArticles','relatedNews','relatedVideo','relatedFactboxes']}), remove_tags = [dict(name='div', attrs={'id':['recommendedArticles','relatedNews','relatedVideo','relatedFactboxes']}),
dict(name='p', attrs={'class':['relatedTopics']}), dict(name='p', attrs={'class':['relatedTopics']}),
dict(name='a', attrs={'id':['fullSizeLink']}), 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 preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
[ [
##(r'<HEAD>.*?</HEAD>' , lambda match : '<HEAD></HEAD>'), ##(r'<HEAD>.*?</HEAD>' , lambda match : '<HEAD></HEAD>'),
(r'<div id="apple-rss-sidebar-background">.*?<!-- start Entries -->', lambda match : ''), (r'<div id="apple-rss-sidebar-background">.*?<!-- start Entries -->', lambda match : ''),
(r'<!-- end apple-rss-content-area -->.*?</body>', lambda match : '</body>'), (r'<!-- end apple-rss-content-area -->.*?</body>', lambda match : '</body>'),
@ -40,18 +42,15 @@ class Reuters(BasicNewsRecipe):
(r'<body>.*?<div class="contentBand">', lambda match : '<body>'), (r'<body>.*?<div class="contentBand">', lambda match : '<body>'),
(r'<h3>Share:</h3>.*?</body>', lambda match : '<!-- END:: Shared Module id=36615 --></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">'), (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'), feeds = [ ('Top Stories', 'http://feeds.reuters.com/reuters/topNews?format=xml'),
('US News', 'http://feeds.reuters.com/reuters/domesticNews?format=xml'), ('US News', 'http://feeds.reuters.com/reuters/domesticNews?format=xml'),
('World News', 'http://feeds.reuters.com/reuters/worldNews?format=xml'), ('World News', 'http://feeds.reuters.com/reuters/worldNews?format=xml'),
('Politics News', 'http://feeds.reuters.com/reuters/politicsNews?format=xml'), ('Politics News', 'http://feeds.reuters.com/reuters/politicsNews?format=xml'),
('Science News', 'http://feeds.reuters.com/reuters/scienceNews?format=xml'), ('Science News', 'http://feeds.reuters.com/reuters/scienceNews?format=xml'),
('Environment News', 'http://feeds.reuters.com/reuters/Environment?format=xml'), ('Environment News', 'http://feeds.reuters.com/reuters/Environment?format=xml'),
('Technology News', 'http://feeds.reuters.com/reuters/technologyNews?format=xml'), ('Technology News', 'http://feeds.reuters.com/reuters/technologyNews?format=xml'),
('Oddly Enough News', 'http://feeds.reuters.com/reuters/oddlyEnoughNews?format=xml') ('Oddly Enough News', 'http://feeds.reuters.com/reuters/oddlyEnoughNews?format=xml')
] ]