#!/usr/bin/env python from calibre.web.feeds.news import BasicNewsRecipe, classes class HindustanTimes(BasicNewsRecipe): title = u'Hindustan Times' description = 'News from India.' language = 'en_IN' __author__ = 'unkn0wn' oldest_article = 1 # days max_articles_per_feed = 50 encoding = 'utf-8' use_embedded_content = False masthead_url = 'https://epaper.hindustantimes.com//Images/logo/logo.png' no_stylesheets = True remove_attributes = ['style', 'height', 'width'] ignore_duplicate_articles = {'url'} extra_css = '.about-authors { font-size: smaller }' keep_only_tags = [ classes('fullStory dateTime storyBy storyDetails detail freemiumText paywall'), ] remove_tags = [ classes('htsWrapper shareArticle new__newsletter__signup signup__box subscribe freemium-card adMinHeight313' ' storyTopics embed_div shareIcons close-btn mainCoachmarks sharePopUp'), dict(name='div', attrs={'class':[]}), dict(name=['footer', 'button']), ] feeds = [ ('Editorial','https://www.hindustantimes.com/feeds/rss/editorials/rssfeed.xml'), ('Opinion','https://www.hindustantimes.com/feeds/rss/opinion/rssfeed.xml'), ('HT Insight','https://www.hindustantimes.com/feeds/rss/ht-insight/rssfeed.xml'), ('Analysis','https://www.hindustantimes.com/feeds/rss/analysis/rssfeed.xml'), ('India News','https://www.hindustantimes.com/feeds/rss/india-news/rssfeed.xml'), ('World News','https://www.hindustantimes.com/feeds/rss/world-news/rssfeed.xml'), ('Business','https://www.hindustantimes.com/feeds/rss/business/rssfeed.xml'), ('Science','https://www.hindustantimes.com/feeds/rss/science/rssfeed.xml'), ('Education','https://www.hindustantimes.com/feeds/rss/education/rssfeed.xml'), ('Elections','https://www.hindustantimes.com/feeds/rss/elections/rssfeed.xml'), ('Sports','https://www.hindustantimes.com/feeds/rss/sports/rssfeed.xml'), ('Books','https://www.hindustantimes.com/feeds/rss/books/rssfeed.xml'), ('HT Weekend','https://www.hindustantimes.com/feeds/rss/ht-weekend/rssfeed.xml'), # ('Entertainment','https://www.hindustantimes.com/feeds/rss/entertainment/rssfeed.xml'), # ('Lifestyle',''https://www.hindustantimes.com/feeds/rss/lifestyle/rssfeed.xml'), # ('Cities',''https://www.hindustantimes.com/feeds/rss/cities/rssfeed.xml'), # ('Budget',''https://www.hindustantimes.com/feeds/rss/budget/rssfeed.xml') ] def get_cover_url(self): soup = self.index_to_soup('https://www.magzter.com/IN/HT-Digital-Streams-Ltd./Hindustan-Times-Delhi/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', attrs={'data-src': True}): img['src'] = img['data-src'] return soup