#!/usr/bin/env python __license__ = 'GPL v3' __copyright__ = '2009, Darko Miletic ' ''' www.uncrate.com ''' from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.ebooks.BeautifulSoup import Tag def new_tag(soup, name, attrs=()): impl = getattr(soup, 'new_tag', None) if impl is not None: return impl(name, attrs=dict(attrs)) return Tag(soup, name, attrs=attrs or None) class Uncrate(BasicNewsRecipe): title = 'Uncrate' __author__ = 'Darko Miletic' description = 'Uncrate is a web magazine for guys who love stuff. Our team digs up the best gadgets, clothes, cars, DVDs and more. New items are posted daily. Enjoy responsively.' # noqa oldest_article = 7 max_articles_per_feed = 100 no_stylesheets = True use_embedded_content = False encoding = 'utf-8' publisher = 'Zombie corp.' category = 'news, gadgets, clothes, cars, DVDs' lang = 'en-US' language = 'en' html2lrf_options = [ '--comment', description, '--category', category, '--publisher', publisher ] html2epub_options = 'publisher="' + publisher + \ '"\ncomments="' + description + '"\ntags="' + category + '"' keep_only_tags = [dict(name='div', attrs={'class': 'lefttext'})] remove_tags_after = dict(name='div', attrs={'class': 'serif'}) remove_tags = [dict(name=['object', 'link', 'script', 'iframe', 'form'])] extra_css = ''' .serif{font-family:Georgia,Rockwell,'Times New Roman',Times,serif; font-weight:normal; font-size: x-small; } h1{ font-family:Verdana,Arial,Helvetica,sans-serif;font-size:x-large; font-weight:bold;} .byline{ font-family:Verdana,Arial,Helvetica,sans-serif;font-size: x-small; color:#FF4000;} .posted{ font-family:Verdana,Arial,Helvetica,sans-serif;font-size: x-small;} .answer{ font-family:Verdana,Arial,Helvetica,sans-serif;font-size: x-small;} a{color:#FF4000;} ''' feeds = [(u'Articles', u'http://feeds.feedburner.com/uncrate')] def preprocess_html(self, soup): mlang = new_tag(soup, 'meta', [ ("http-equiv", "Content-Language"), ("content", self.lang)]) mcharset = new_tag(soup, 'meta', [ ("http-equiv", "Content-Type"), ("content", "text/html; charset=utf-8")]) soup.head.insert(0, mlang) soup.head.insert(1, mcharset) for item in soup.findAll(style=True): del item['style'] return self.adeify_images(soup)