from calibre.web.feeds.news import BasicNewsRecipe class DrawAndCook(BasicNewsRecipe): title = 'DrawAndCook' __author__ = 'Starson17' description = 'Drawings of recipes!' language = 'en' publisher = 'Starson17' category = 'news, food, recipes' use_embedded_content= False no_stylesheets = True oldest_article = 24 remove_javascript = True remove_empty_feeds = True cover_url = 'http://farm5.static.flickr.com/4043/4471139063_4dafced67f_o.jpg' max_articles_per_feed = 30 remove_attributes = ['style', 'font'] def parse_index(self): feeds = [] for title, url in [ ("They Draw and Cook", "http://www.theydrawandcook.com/") ]: articles = self.make_links(url) if articles: feeds.append((title, articles)) print 'feeds are: ', feeds return feeds def make_links(self, url): soup = self.index_to_soup(url) title = '' date = '' current_articles = [] soup = self.index_to_soup(url) recipes = soup.findAll('div', attrs={'class': 'date-outer'}) for recipe in recipes: title = recipe.h3.a.string page_url = recipe.h3.a['href'] current_articles.append({'title': title, 'url': page_url, 'description':'', 'date':date}) return current_articles keep_only_tags = [dict(name='h3', attrs={'class':'post-title entry-title'}) ,dict(name='div', attrs={'class':'post-body entry-content'}) ] remove_tags = [dict(name='div', attrs={'class':['separator']}) ,dict(name='div', attrs={'class':['post-share-buttons']}) ] extra_css = ''' h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;} h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;} img {max-width:100%; min-width:100%;} p{font-family:Arial,Helvetica,sans-serif;font-size:small;} body{font-family:Helvetica,Arial,sans-serif;font-size:small;} '''