from calibre.web.feeds.news import BasicNewsRecipe from collections import defaultdict BASE = 'https://www.newsweek.com' def href_to_url(a, add_piano=False): return BASE + a.get('href') + ('?piano_d=1' if add_piano else '') def class_sels(*args): q = set(args) return dict(attrs={'class': lambda x: x and set(x.split()).intersection(q)}) class Newsweek(BasicNewsRecipe): title = 'Newsweek' __author__ = 'Kovid Goyal' description = 'Weekly news and current affairs in the US' language = 'en' encoding = 'utf-8' no_stylesheets = True requires_version = (1, 40, 0) keep_only_tags = [ dict(id='block-nw-magazine-article-header'), class_sels('article-header', 'article-body') ] remove_tags = [ dict(name=['aside', 'meta', 'source']), class_sels( 'block-openadstream', 'block-ibtmedia-social', 'issue-next', 'most-popular', 'ibt-media-stories', 'user-btn-group', 'trial-link', 'trc_related_container', 'block-ibtmedia-top-stories', 'videocontent', 'newsletter-signup', 'in-text-slideshows', 'content-correction', 'article-navigation' ), dict(id=['taboola-below-main-column', 'piano-root', 'block-nw-magazine-magazine-more-from-issue']), ] remove_attributes = ['style'] def parse_index(self): root = self.index_to_soup( 'https://www.newsweek.com/archive', as_tree=True) li = root.xpath( '//ul[contains(@class, "magazine-archive-items")]/li')[0] a = li.xpath('descendant::a[@href]')[0] url = href_to_url(a, add_piano=True) self.timefmt = self.tag_to_string(a) img = li.xpath('descendant::a[@href]//img[@src]')[0] self.cover_url = img.get('src') root = self.index_to_soup(url, as_tree=True) features = [] href_xpath = 'descendant::*[local-name()="h1" or local-name()="h2" or local-name()="h3" or local-name()="h4"]/a[@href]' try: div = root.xpath('//div[@id="block-nw-magazine-magazine-features"]')[0] except IndexError: pass else: for a in div.xpath(href_xpath): title = self.tag_to_string(a) article = a.xpath('ancestor::article')[0] desc = '' s = article.xpath('descendant::div[@class="summary"]') if s: desc = self.tag_to_string(s[0]) features.append({'title': title, 'url': href_to_url(a), 'description': desc}) self.log(title, href_to_url(a)) index = [] if features: index.append(('Features', features)) sections = defaultdict(list) for block in ('magazine-magazine-issue-story-list', 'editors-pick'): div = root.xpath( '//div[@id="block-nw-{}"]'.format(block)) if not div: continue div = div[0] for a in div.xpath(href_xpath): title = self.tag_to_string(a) article = a.xpath('ancestor::article')[0] desc = '' s = article.xpath('descendant::div[@class="summary"]') if s: desc = self.tag_to_string(s[0]) sec = article.xpath('descendant::div[@class="category"]') if sec: sec = self.tag_to_string(sec[0]) else: sec = 'Articles' sections[sec].append( {'title': title, 'url': href_to_url(a), 'description': desc}) self.log(title, href_to_url(a)) if desc: self.log('\t' + desc) self.log('') for k in sorted(sections): index.append((k, sections[k])) return index def print_version(self, url): return url + '?piano_d=1' def preprocess_html(self, soup): # Parallax images in the articles are loaded as background images # on tags. Convert them to normal images. for span in soup.findAll('span', attrs={'class': lambda x: x and 'parallax' in x.split()}): s = span.find(style=True) if s is not None: url = s['style'].partition('(')[-1][:-1] s['style'] = 'display: block' s.name = 'img' s['src'] = url return soup