Code:
class AdvancedUserRecipe1341650280(BasicNewsRecipe):
title = u'Empire Magazine'
description = 'Author D.Asbury. Film articles from Empire Mag. '
__author__ = 'Dave Asbury'
# last updated 7/7/12
remove_empty_feeds = True
remove_javascript = True
no_stylesheets = True
#oldest_article = 7
max_articles_per_feed = 20
cover_url = 'http://www.empireonline.com/images/magazine/cover.jpg'
conversion_options = {
'linearize_tables' : True,
}
#auto_cleanup = True
preprocess_regexps = [
(re.compile(r'<a href="http://twitter.com/share.*?</a>', re.IGNORECASE | re.DOTALL), lambda match: ''),
(re.compile(r'<head>.*?<!-- CONTENT: START -->', re.IGNORECASE | re.DOTALL), lambda match: '<head></head><!-- CONTENT: START -->'),
(re.compile(r'<!-- LATEST NEWS HEADLINES: START -->.*?<!-- LATEST NEWS HEADLINES: END -->', re.IGNORECASE | re.DOTALL), lambda match: '<!-- LATEST NEWS HEADLINES: START --><!-- LATEST NEWS HEADLINES: END -->'),
(re.compile(r'<!-- RELATED FUTURE FILMS: START -->.*?<!-- RELATED FUTURE FILMS: END -->', re.IGNORECASE | re.DOTALL), lambda match: '<!-- RELATED FUTURE FILMS: START --><!-- RELATED FUTURE FILMS: END -->'),
(re.compile(r'<!-- CURRENT HIGHLIGHTS: START-->.*?<!-- CURRENT HIGHLIGHTS: END -->', re.IGNORECASE | re.DOTALL), lambda match: '<!-- CURRENT HIGHLIGHTS: START--><!-- CURRENT HIGHLIGHTS: END -->'),
(re.compile(r'<!-- RELATED REVIEWS: START -->.*?<!-- RELATED REVIEWS: END -->', re.IGNORECASE | re.DOTALL), lambda match: '<!-- RELATED REVIEWS: START --><!-- RELATED REVIEWS: END -->'),
(re.compile(r'<!-- RELATED INTERVIEWS -->.*?<!-- RELATED REVIEWS: END -->', re.IGNORECASE | re.DOTALL), lambda match: '<!-- RELATED INTERVIEWS --><!-- RELATED REVIEWS: END -->'),
(re.compile(r'<!-- CONTENT: END -->.*?</body>', re.IGNORECASE | re.DOTALL), lambda match: '<!-- CONTENT: END --></body>'),
(re.compile(r'<!-- STORY: END -->.*?</body>', re.IGNORECASE | re.DOTALL), lambda match: '<!-- STORY: END --></body>'),
(re.compile(r'<!-- RATINGS GUIDE: START-->.*?<!-- RATINGS GUIDE: END-->', re.IGNORECASE | re.DOTALL), lambda match: '<!-- RATINGS GUIDE: START--><!-- RATINGS GUIDE: END-->'),
(re.compile(r'<strong>SUBSCRIBE TO EMPIRE</strong>.*?</tbody>', re.IGNORECASE | re.DOTALL), lambda match: '</tbody>'),
(re.compile(r'<!-- USER REVIEWS: START -->.*?<!-- USER REVIEWS: END -->', re.IGNORECASE | re.DOTALL), lambda match: '<!-- USER REVIEWS: START --><!-- USER REVIEWS: END -->'),
(re.compile(r'Advertisement', re.IGNORECASE | re.DOTALL), lambda match: ''),
(re.compile(r'<a name="haveyoursay".*?now to have your say.', re.IGNORECASE | re.DOTALL), lambda match: ''),
]
keep_only_tags = [
# dict(name='h1'),
# dict(attrs={'class' : 'mediumblack'}),
]
remove_tags = [dict(name='td', attrs={'width':'200', 'valign' : 'top'}),
dict(name='b'),
dict(name='a',attrs={'name' : 'haveyoursay'}),
dict(attrs={'class' : 'newslink'}),
]
feeds = [(u'News', u'http://feed43.com/7338478755673147.xml'),
(u'Recent Features',u'http://feed43.com/4346347750304760.xml'),
(u'Interviews',u'http://feed43.com/3418350077724081.xml'),
(u'Film Reviews',u'http://feed43.com/2643703076510627.xml'),
]
07-07-2012, 09:20 AM
Similar Threads