home *** CD-ROM | disk | FTP | other *** search
- __license__ = 'GPL v3'
- __copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
-
- '''
- www.esquire.com
- '''
-
- from calibre.web.feeds.news import BasicNewsRecipe
-
- class Esquire(BasicNewsRecipe):
- title = 'Esquire'
- __author__ = 'Darko Miletic'
- description = 'Esquire: Man at His Best'
- publisher = 'Hearst Communications, Inc.'
- category = 'magazine, men, women we love, style, the guide, sex, screen'
- oldest_article = 30
- max_articles_per_feed = 100
- no_stylesheets = True
- encoding = 'cp1250'
- use_embedded_content = False
- language = 'en'
- publication_type = 'magazine'
- masthead_url = 'http://www.esquire.com/cm/shared/site_images/print_this/esquire_logo.gif'
-
- conversion_options = {
- 'comment' : description
- , 'tags' : category
- , 'publisher' : publisher
- , 'language' : language
- }
-
- keep_only_tags = [dict(name='div', attrs={'id':['article_header','article_content']})]
- remove_tags = [dict(name=['object','link','embed','iframe','base'])]
- remove_attributes = ['width','height']
-
- feeds = [
- (u'Style' , u'http://www.esquire.com/style/rss/' )
- ,(u'Women' , u'http://www.esquire.com/women/rss/' )
- ,(u'Features' , u'http://www.esquire.com/features/rss/' )
- ,(u'Fiction' , u'http://www.esquire.com/fiction/rss/' )
- ,(u'Frontpage', u'http://www.esquire.com/rss/' )
- ]
-
- def preprocess_html(self, soup):
- for item in soup.findAll(style=True):
- del item['style']
- return soup
-