diff --git a/recipes/nypost.recipe b/recipes/nypost.recipe index 95aa130008..32792026a1 100644 --- a/recipes/nypost.recipe +++ b/recipes/nypost.recipe @@ -1,35 +1,35 @@ #!/usr/bin/env python # vim:fileencoding=utf-8 -from __future__ import absolute_import, division, print_function, unicode_literals - -from calibre.web.feeds.news import BasicNewsRecipe - - -def classes(classes): - q = frozenset(classes.split(' ')) - return dict( - attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}) +from calibre.web.feeds.news import BasicNewsRecipe, classes class NewYorkPost(BasicNewsRecipe): title = 'New York Post' - __author__ = 'Darko Miletic' + __author__ = 'unkn0wn' description = 'Daily newspaper' publisher = 'NYP Holdings, Inc.' category = 'news, politics, USA' - oldest_article = 2 - max_articles_per_feed = 20 + oldest_article = 1 no_stylesheets = True - encoding = 'utf8' + encoding = 'utf-8' use_embedded_content = False language = 'en_US' - extra_css = ' body{font-family: Arial,Helvetica,sans-serif } img{margin-bottom: 0.4em} ' + remove_attributes = ['style', 'height', 'width'] + masthead_url = 'https://static.storied.co/gQlwL7PA4X5XM6b8/projects/JYX3m27B8zP9BW4D/assets/images/81e851fd6c5d8fc747c41064d8aee316.png' + extra_css = '.byline, .date, .article-header__top, .calibre-nuked-tag-figcaption { font-size: small; }' + + def get_cover_url(self): + soup = self.index_to_soup('https://www.frontpages.com/new-york-post/') + return ( + 'https://www.frontpages.com' + + soup.find('img', attrs={'id': 'giornale-img'})['src'] + ) recipe_specific_options = { 'days': { 'short': 'Oldest article to download from this news source. In days ', 'long': 'For example, 0.5, gives you articles from the past 12 hours', - 'default': str(oldest_article) + 'default': str(oldest_article), } } @@ -39,55 +39,41 @@ class NewYorkPost(BasicNewsRecipe): if d and isinstance(d, str): self.oldest_article = float(d) - conversion_options = { - 'comment': description, 'tags': category, 'publisher': publisher, 'language': language - } ignore_duplicate_articles = {'title', 'url'} keep_only_tags = [ - dict(itemprop=['headline', 'articleBody']), - dict(name='h1'), - classes( - 'byline byline-date source article-info entry-content entry-content-read-more featured-image' - ' headline--single date meta meta--byline Date published' - ), + classes('article-header single__content'), ] - remove_tags = [ - dict(itemprop=['sharebar-trigger-desktop', ]), + remove_tags = [ + dict(attrs={'id': ['connatix-outstream-video']}), classes( - 'floating-share floating-share-wrap sharedaddy sd-sharing-enabled tag-list module-wrapper' - ' inline-module--author inline-module--columnist inline-module--primary-tag' - ' author-flyout modal__email-author button gowatchit-inline updated select-share__title' + 'article-header__social-icons wpcom-liveblog-container nyp-s2n-wrapper ' + 'nyp-slideshow-modal-image__icon inline-module inline-module__inner' ), - dict(name=['link', 'meta']), + dict(name=['svg', 'link', 'meta', 'aside']), ] + # https://nypost.com/rssfeeds/ feeds = [ - ('All Stories','https://nypost.com/feed'), - ('News','https://nypost.com/news/feed'), - ('Metro', 'http://nypost.com/metro/feed/'), - ('Business', 'http://nypost.com/business/feed/'), - ('Opinion', 'http://nypost.com/opinion/feed/'), - ('Technology', 'http://nypost.com/tech/feed/'), - ('Media', 'http://nypost.com/media/feed/'), - ('Entertainment', 'http://nypost.com/entertainment/feed/'), - ('Living', 'http://nypost.com/living/feed/'), - ('Page 6', 'http://pagesix.com/feed/'), + ('US-News', 'https://nypost.com/us-news/feed/'), + ('Metro', 'https://nypost.com/metro/feed/'), + ('Politics', 'https://nypost.com/politics/feed/'), + ('World News', 'https://nypost.com/world-news/feed/'), + ('Sports', 'https://nypost.com/sports/feed/'), + ('Business', 'https://nypost.com/business/feed/'), + ('Opinion', 'https://nypost.com/opinion/feed/'), + ('Entertainment', 'https://nypost.com/entertainment/feed/'), + ('Fashion & Beauty', 'https://nypost.com/fashion-and-beauty/feed/'), + ('Lifestyle', 'https://nypost.com/lifestyle/feed/'), + ('Tech', 'https://nypost.com/tech/feed/'), + ('Media', 'https://nypost.com/media/feed/'), + ('Real Estate', 'https://nypost.com/real-estate/feed/'), + ('Page Six', 'https://pagesix.com/feed/'), + ('Others', 'https://nypost.com/feed/'), ] - def print_version(self, url): - return url.replace('nypost.com/p/', 'nypost.com/f/print/') - def preprocess_html(self, soup): - for img in soup.findAll('img', attrs={'data-srcset': True}): - img['src'] = img['data-srcset'].split()[0] - for pic in soup.findAll('picture'): - source = pic.find('source', srcset=True) - if source is not None: - img = pic.find('img') - if img is not None: - img['src'] = source['srcset'].split()[0] - for source in pic.findAll('source'): - source.extract() + for img in soup.findAll('img', attrs={'src': True}): + img['src'] = img['src'].split('?')[0] + '?w=600' return soup