__license__ = 'GPL v3' __copyright__ = '2011, Darko Miletic ' ''' www.washingtonpost.com ''' from calibre.web.feeds.news import BasicNewsRecipe from html5_parser import parse import json class TheWashingtonPost(BasicNewsRecipe): title = 'The Washington Post' __author__ = 'Darko Miletic, unkn0wn' description = 'Leading source for news, video and opinion on politics, business, world and national news, science, travel, entertainment and more. Our local coverage includes reporting on education, crime, weather, traffic, real estate, jobs and cars for DC, Maryland and Virginia. Offering award-winning opinion writing, entertainment information and restaurant reviews.' # noqa publisher = 'The Washington Post Company' category = 'news, politics, USA' oldest_article = 1.2 max_articles_per_feed = 200 no_stylesheets = True encoding = 'utf8' use_embedded_content = False language = 'en' remove_empty_feeds = True ignore_duplicate_articles = {'url'} masthead_url = 'https://www.washingtonpost.com/pb/resources/img/twp-masthead-415x57.svg' publication_type = 'newspaper' remove_attributes = ['style', 'width', 'height'] extra_css = ''' .img { text-align:center; font-size:small; } .auth { font-weight:bold; font-size:small; } .time { font-size:small; color: #202020; } ''' def get_browser(self): return BasicNewsRecipe.get_browser(self, verify_ssl_certificates=False, user_agent='common_words/based') # Official feeds: https://www.washingtonpost.com/discussions/2018/10/12/washington-post-rss-feeds/ feeds = [ (u'Politics', u'http://feeds.washingtonpost.com/rss/politics'), (u'Opinions', u'http://feeds.washingtonpost.com/rss/opinions'), (u'Local', u'http://feeds.washingtonpost.com/rss/local'), (u'Sports', u'http://feeds.washingtonpost.com/rss/sports'), (u'Technology', u'http://feeds.washingtonpost.com/rss/business/technology'), (u'National', u'http://feeds.washingtonpost.com/rss/national'), (u'World', u'http://feeds.washingtonpost.com/rss/world'), (u'Business', u'http://feeds.washingtonpost.com/rss/business'), (u'Lifestyle', u'http://feeds.washingtonpost.com/rss/lifestyle'), (u'Entertainment', u'http://feeds.washingtonpost.com/rss/entertainment'), # Undocumented feeds. (u'White House', u'http://feeds.washingtonpost.com/rss/politics/whitehouse'), (u'Commanders', u'http://feeds.washingtonpost.com/rss/sports/redskins'), ] def preprocess_raw_html(self, raw, *a): root = parse(raw) m = root.xpath('//script[@id="__NEXT_DATA__"]') data = json.loads(m[0].text) data = data['props']['pageProps']['globalContent'] title = '

' + data['headlines']['basic'] + '

' subhead = '

' + data['description'].get('basic', '') + '

' author = '' if 'credits' in data: author = '

' + 'By ' + ', '.join(x['name'] for x in data['credits']['by']) \ + ' | ' + data['publish_date'][:-14] + '

' body = '' for x in data['content_elements']: if x['type'] == 'text': body += '

' + x['content'] + '

' elif x['type'] == 'video': if 'promo_image' in x: body += '

{}

'.format( x['promo_image']['url'], x['description'].get('basic', '') ) elif x['type'] == 'image': body += '

{}

'.format(x['url'], x['credits_caption_display']) return '

' + title + subhead + author + body + '

' def preprocess_html(self, soup): for img in soup.findAll('img', attrs={'src':True}): img['src'] = 'https://www.washingtonpost.com/wp-apps/imrs.php?src=' + img['src'] + '&w=916' return soup