From 462431c4a97518eefe8e8d7cac7d5b5106da7178 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Wed, 20 Apr 2022 21:10:36 +0530 Subject: [PATCH] Update Business Standard --- recipes/business_standard.recipe | 38 +++++++++++++++++++------------- 1 file changed, 23 insertions(+), 15 deletions(-) diff --git a/recipes/business_standard.recipe b/recipes/business_standard.recipe index 868ce20750..2f3522a970 100644 --- a/recipes/business_standard.recipe +++ b/recipes/business_standard.recipe @@ -17,8 +17,8 @@ class BusinessStandard(BasicNewsRecipe): title = 'Business Standard' __author__ = 'Darko Miletic' description = "India's most respected business daily" - oldest_article = 7 - max_articles_per_feed = 100 + oldest_article = 1 + max_articles_per_feed = 20 no_stylesheets = True use_embedded_content = False encoding = 'utf-8' @@ -26,25 +26,33 @@ class BusinessStandard(BasicNewsRecipe): category = 'news, business, money, india, world' language = 'en_IN' - conversion_options = { - 'comments': description, 'tags': category, 'language': language, 'publisher': publisher, 'linearize_tables': True - } + masthead_url = 'https://bsmedia.business-standard.com/include/_mod/site/html5/images/business-standard-logo.png' + + def get_cover_url(self): + soup = self.index_to_soup('https://www.magzter.com/IN/Business-Standard-Private-Ltd/Business-Standard/Newspaper/') + for citem in soup.findAll('meta', content=lambda s: s and s.endswith('view/3.jpg')): + return citem['content'] + remove_attributes = ['width', 'height', 'style'] + keep_only_tags = [ - classes('headline alternativeHeadline full-img story-content pubDate'), + classes('headline alternativeHeadline full-img article-content__img pubDate'), + dict(name='span', attrs={'class':'p-content'}), ] remove_tags = [ classes('also-read-panel') ] feeds = [ - (u'News Now', u'http://feeds.business-standard.com/rss/online.xml'), - (u'Banking & finance', u'http://feeds.business-standard.com/rss/3_0.xml'), - (u'Companies & Industry', u'http://feeds.business-standard.com/rss/2_0.xml'), - (u'Economy & Policy', u'http://feeds.business-standard.com/rss/4_0.xml'), - (u'Tech World', u'http://feeds.business-standard.com/rss/8_0.xml'), - (u'Life & Leisure', u'http://feeds.business-standard.com/rss/6_0.xml'), - (u'Markets & Investing', u'http://feeds.business-standard.com/rss/1_0.xml'), - (u'Management & Mktg', u'http://feeds.business-standard.com/rss/7_0.xml'), - (u'Opinion', u'http://feeds.business-standard.com/rss/5_0.xml') + (u'Companies', u'https://www.business-standard.com/rss/companies-101.rss'), + (u'Economy and Policy', u'https://www.business-standard.com/rss/economy-policy-102.rss'), + (u'Finance', u'https://www.business-standard.com/rss/finance-103.rss'), + (u'Beyond Business', u'https://www.business-standard.com/rss/beyond-business-104.rss'), + (u'Opinion', 'https://www.business-standard.com/rss/opinion-105.rss'), + (u'Markets', u'https://www.business-standard.com/rss/markets-106.rss'), + (u'Technology', u'https://www.business-standard.com/rss/technology-108.rss'), + (u'Personal Finance', u'https://www.business-standard.com/rss/pf-114.rss'), + (u'International', u'https://www.business-standard.com/rss/international-116.rss'), + # (u'Today\'s Paper', u'https://www.business-standard.com/rss/todays-paper.rss'), + # for todays paper - subscrition required ]