__license__ = 'GPL v3' __copyright__ = '2010, Darko Miletic ' ''' gamasutra.com ''' import re from calibre.web.feeds.news import BasicNewsRecipe class Gamasutra(BasicNewsRecipe): title = 'Gamasutra Featured articles' __author__ = 'Darko Miletic' description = 'The Art and Business of Making Games' publisher = 'Gamasutra' category = 'news, games, IT' oldest_article = 2 max_articles_per_feed = 200 no_stylesheets = True encoding = 'cp1252' use_embedded_content = False language = 'en' remove_empty_feeds = True masthead_url = 'http://www.gamasutra.com/images/gamasutra_logo.gif' extra_css = ' body{font-family: Verdana,Arial,Helvetica,sans-serif } img{margin-bottom: 0.4em} .title{font-size: x-large; font-weight: bold} ' conversion_options = { 'comment' : description , 'tags' : category , 'publisher' : publisher , 'language' : language , 'linearize_tables' : True } preprocess_regexps = [ (re.compile(r'.*?', re.DOTALL|re.IGNORECASE),lambda match: '<head><title>') ,(re.compile(r'.*?', re.DOTALL|re.IGNORECASE),lambda match: '') ,(re.compile(r'', re.DOTALL|re.IGNORECASE),lambda match: '') ] remove_tags = [ dict(name=['object','embed','iframe']) ,dict(attrs={'class':'adBox'}) ] remove_tags_before = dict(attrs={'class':'title'}) remove_attributes = ['width','height','name'] feeds = [(u'Feature Articles', u'http://feeds.feedburner.com/GamasutraFeatureArticles')] def print_version(self, url): return url + '?print=1' def get_article_url(self, article): return article.get('guid', None) def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] return self.adeify_images(soup)