from calibre.web.feeds.news import BasicNewsRecipe, classes

class BusinessLine(BasicNewsRecipe):
    title = 'The Hindu BusinessLine'
    __author__ = 'unkn0wn'
    description = (
        'The Hindu BusinessLine is known for its credibility, accuracy, in-depth analysis of markets and sober coverage'
        ' of business news. BusinessLine reduces the daily grind of business to relevant, readable, byte-sized stories.'
        ' The newspaper is extensively followed by the decision makers and change leaders from the world of business.')
    no_stylesheets = True
    use_embedded_content = False
    oldest_article = 1.15  # days
    max_articles_per_feed = 50
    encoding = 'utf-8'
    language = 'en_IN'
    remove_attributes = ['height', 'width', 'padding-bottom'] 
    masthead_url = 'https://www.thehindubusinessline.com/theme/images/bl-online/bllogo.png'
    ignore_duplicate_articles = {'title', 'url'}
    remove_empty_feeds = True
    
    def get_cover_url(self):
        soup = self.index_to_soup('https://www.magzter.com/IN/THG-publishing-pvt-ltd/The-Hindu-Business-Line/Newspaper/')
        for citem in soup.findAll('meta', content=lambda s: s and s.endswith('view/3.jpg')):
            return citem['content']
    
    keep_only_tags = [
        classes('tp-title-inf bi-line leadtext lead-img-caption slide-moadal img-container'),
        dict(name='div', attrs={'id': lambda x: x and x.startswith('content-body-')})
    ]
    
    remove_tags = [classes('swiper-button-prev left-arrow swiper-button-next right-arrow close cursor tagsBtm share-topic comment-rules vuukle-div paywallbox ')]
    
    feeds = [
        ('Markets', 'https://www.thehindubusinessline.com/markets/feeder/default.rss'),
        ('Companies','https://www.thehindubusinessline.com/companies/feeder/default.rss'),
        ('Opinion', 'https://www.thehindubusinessline.com/opinion/feeder/default.rss'),
        ('Economy', 'https://www.thehindubusinessline.com/economy/feeder/default.rss'),
        ('Portfolio Premium', 'https://www.thehindubusinessline.com/portfolio/feeder/default.rss'),
        ('Info-Tech', 'https://www.thehindubusinessline.com/info-tech/feeder/default.rss'),
        ('Data-Stories', 'https://www.thehindubusinessline.com/data-stories/feeder/default.rss'),
        ('Money & Banking', 'https://www.thehindubusinessline.com/money-and-banking/feeder/default.rss'),
        ('News', 'https://www.thehindubusinessline.com/news/feeder/default.rss'),
    ]
                      
    def preprocess_html(self, soup):
        for image in soup.findAll('source', attrs={'srcset' : True}):
            image['src'] = image['srcset']
        for img in soup.findAll('img', attrs={'data-src-template': True}):
            img['src'] = img['data-src-template']
        return soup
    

calibre_most_common_ua = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.87 Safari/537.36'