From 7944a8a022782e1216d61391c151c0bb79ba3553 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Mon, 4 Apr 2022 14:53:53 +0530 Subject: [PATCH] Update Indian Express --- recipes/indian_express.recipe | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/recipes/indian_express.recipe b/recipes/indian_express.recipe index f0a9f8252a..ed3817488c 100644 --- a/recipes/indian_express.recipe +++ b/recipes/indian_express.recipe @@ -14,11 +14,13 @@ class IndianExpress(BasicNewsRecipe): oldest_article = 1 # days max_articles_per_feed = 25 encoding = 'utf-8' + masthead_url = 'https://indianexpress.com/wp-content/themes/indianexpress/images/indian-express-logo-n.svg' no_stylesheets = True use_embedded_content = False remove_attributes = ['style','height','width'] ignore_duplicate_articles = {'url'} + extra_css = '#storycenterbyline {font-size:small};' keep_only_tags = [ classes('heading-part full-details') @@ -29,7 +31,10 @@ class IndianExpress(BasicNewsRecipe): dict(name='a', attrs={'href':'https://indianexpress.com/section/explained/?utm_source=newbanner'}), dict(name='img', attrs={'src':'https://images.indianexpress.com/2021/06/opinion-button-300-ie.jpeg'}), dict(name='a', attrs={'href':'https://indianexpress.com/section/opinion/?utm_source=newbanner'}), - classes('share-social appstext story-tags ie-int-campign-ad ie-breadcrumb custom_read_button unitimg copyright') + classes( + 'share-social appstext ie-int-campign-ad ie-breadcrumb custom_read_button unitimg copyright' + ' storytags pdsc-related-modify news-guard' + ) ] feeds = [ ('Front Page', 'https://indianexpress.com/print/front-page/feed/'), @@ -41,9 +46,18 @@ class IndianExpress(BasicNewsRecipe): ('Delhi Confidential', 'https://indianexpress.com/section/delhi-confidential/feed'), ('Economy', 'https://indianexpress.com/print/economy/feed'), ('Express Network', 'https://indianexpress.com/print/express-network/'), + ('Research', 'https://indianexpress.com/section/research/feed/'), + ('UPSC-CSE Key','https://indianexpress.com/section/upsc-current-affairs/feed/'), + ('World','https://indianexpress.com/section/world/feed/'), + ('Business', 'https://indianexpress.com/section/business/feed/'), # Want to add more? go-to:https://indianexpress.com/syndication/ ] + def get_cover_url(self): + soup = self.index_to_soup('https://www.magzter.com/IN/The-Indian-Express-Ltd./The-Indian-Express-Mumbai/Newspaper/') + for citem in soup.findAll('meta', content=lambda s: s and s.endswith('view/3.jpg')): + return citem['content'] + def preprocess_html(self, soup): for img in soup.findAll('img'): noscript = img.findParent('noscript')