diff --git a/recipes/national_post.recipe b/recipes/national_post.recipe index 00eb918d02..f7818314ee 100644 --- a/recipes/national_post.recipe +++ b/recipes/national_post.recipe @@ -1,5 +1,4 @@ from calibre.web.feeds.recipes import BasicNewsRecipe -from calibre.ebooks.BeautifulSoup import BeautifulSoup class NYTimes(BasicNewsRecipe): @@ -11,22 +10,8 @@ class NYTimes(BasicNewsRecipe): needs_subscription = False no_stylesheets = True - #remove_tags_before = dict(name='h1', attrs={'class':'heading'}) - remove_tags_after = dict(name='div', attrs={'class':'npStoryTools npWidth1-6 npRight npTxtStrong'}) - remove_tags = [ - dict(name='iframe'), - dict(name='div', attrs={'class':['story-tools', 'npStoryTools npWidth1-6 npRight npTxtStrong']}), - #dict(name='div', attrs={'id':['qrformdiv', 'inSection', 'alpha-inner']}), - #dict(name='form', attrs={'onsubmit':''}), - dict(name='ul', attrs={'class':'npTxtAlt npGroup npTxtCentre npStoryShare npTxtStrong npTxtDim'}), - ] - - # def preprocess_html(self, soup): - # table = soup.find('table') - # if table is not None: - # table.extract() - # return soup - + auto_cleanup = True + auto_cleanup_keep = '//*[@class="npStoryPhoto npTxtPlain"]' #TO GET ARTICLE TOC @@ -53,14 +38,14 @@ class NYTimes(BasicNewsRecipe): if current_section is not None and x.name == 'h5': # Article found title = self.tag_to_string(x) - a = x.find('a', href=lambda x: x and 'story' in x) + a = x.find('a', href=True) if a is None: continue url = a.get('href', False) if not url or not title: continue #if url.startswith('story'): - url = 'http://www.nationalpost.com/todays-paper/'+url + #url = 'http://www.nationalpost.com/todays-paper/'+url self.log('\t\tFound article:', title) self.log('\t\t\t', url) current_articles.append({'title': title, 'url':url, @@ -70,11 +55,4 @@ class NYTimes(BasicNewsRecipe): feeds.append((current_section, current_articles)) return feeds - def preprocess_html(self, soup): - story = soup.find(name='div', attrs={'id':'npContentMain'}) - ##td = heading.findParent(name='td') - ##td.extract() - soup = BeautifulSoup('t') - body = soup.find(name='body') - body.insert(0, story) - return soup +