home *** CD-ROM | disk | FTP | other *** search
- __license__ = 'GPL v3'
- __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
- '''
- www.foreignpolicy.com
- '''
-
- from calibre.web.feeds.news import BasicNewsRecipe
-
- class ForeignPolicy(BasicNewsRecipe):
- title = 'Foreign Policy'
- __author__ = 'Darko Miletic'
- description = 'International News'
- publisher = 'Washingtonpost.Newsweek Interactive, LLC'
- category = 'news, politics, USA'
- oldest_article = 31
- max_articles_per_feed = 200
- no_stylesheets = True
- encoding = 'utf8'
- use_embedded_content = False
- language = 'en'
- remove_empty_feeds = True
- extra_css = ' body{font-family: Georgia,"Times New Roman",Times,serif } img{margin-bottom: 0.4em} h1,h2,h3,h4,h5,h6{font-family: Arial,Helvetica,sans-serif} '
-
- conversion_options = {
- 'comment' : description
- , 'tags' : category
- , 'publisher' : publisher
- , 'language' : language
- }
-
- keep_only_tags = [dict(attrs={'id':['art-mast','art-body','auth-bio']})]
- remove_tags = [dict(name='iframe'),dict(attrs={'id':['share-box','base-ad']})]
- remove_attributes = ['height','width']
-
-
- feeds = [(u'Articles', u'http://www.foreignpolicy.com/node/feed')]
-
- def print_version(self, url):
- return url + '?print=yes&page=full'
-
- def preprocess_html(self, soup):
- for item in soup.findAll(style=True):
- del item['style']
- return soup
-
-