__license__ = 'GPL v3' __copyright__ = '2011, Darko Miletic ' ''' www.clubdelebook.com ''' from calibre.web.feeds.news import BasicNewsRecipe class ElClubDelEbook(BasicNewsRecipe): title = 'El club del ebook' __author__ = 'Darko Miletic' description = 'El Club del eBook, es la primera fuente de informacion sobre ebooks de Argentina. Aca vas a encontrar noticias, tips, tutoriales, recursos y opiniones sobre el mundo de los libros electronicos.' # noqa tags = 'ebook, libro electronico, e-book, ebooks, libros electronicos, e-books' oldest_article = 7 max_articles_per_feed = 100 language = 'es_AR' encoding = 'utf-8' no_stylesheets = True use_embedded_content = True publication_type = 'blog' masthead_url = 'http://dl.dropbox.com/u/2845131/elclubdelebook.png' extra_css = """ body{font-family: Arial,Helvetica,sans-serif} img{ margin-bottom: 0.8em; border: 1px solid #333333; padding: 4px; display: block } """ conversion_options = { 'comment': description, 'tags': tags, 'publisher': title, 'language': language } remove_tags = [dict(attrs={'id': 'crp_related'})] remove_tags_after = dict(attrs={'id': 'crp_related'}) feeds = [(u'Articulos', u'http://feeds.feedburner.com/ElClubDelEbook')] def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] for item in soup.findAll('a'): limg = item.find('img') if item.string is not None: str = item.string item.replaceWith(str) else: if limg: item.name = 'div' item.attrs = [] else: str = self.tag_to_string(item) item.replaceWith(str) for item in soup.findAll('img', alt=False): item['alt'] = 'image' return soup