__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
financialexpress.com
'''

from calibre.web.feeds.news import BasicNewsRecipe


def classes(classes):
    q = frozenset(classes.split(' '))
    return dict(attrs={
        'class': lambda x: x and frozenset(x.split()).intersection(q)})


class FE_India(BasicNewsRecipe):
    title = 'The Financial Express'
    __author__ = 'Darko Miletic'
    description = 'Financial news from India'
    publisher = 'The Indian Express Limited'
    category = 'news, politics, finances, India'
    oldest_article = 2
    max_articles_per_feed = 200
    no_stylesheets = True
    encoding = 'utf-8'
    use_embedded_content = False
    language = 'en_IN'
    remove_empty_feeds = True
    ignore_duplicate_articles = {'url'}
    publication_type = 'magazine'

    conversion_options = {
        'comment': description, 'tags': category, 'publisher': publisher, 'language': language
    }

    keep_only_tags = [classes('wp-block-post-title wp-block-post-excerpt ie-network-post-meta-wrapper wp-block-post-featured-image wp-block-post-content')]
    remove_tags = [classes('parent_also_read')]
    remove_attributes = ['width', 'height']

    feeds = [
        # https://www.financialexpress.com/syndication/
        # Print feeds
        ('Front Page','https://www.financialexpress.com/print/front-page/feed/'),
        ('Corporate Markets','https://www.financialexpress.com/print/corporate-markets/feed/'),
        ('Economy','https://www.financialexpress.com/print/economy-print/feed/'),
        ('Opinion','https://www.financialexpress.com/print/edits-columns/feed/'),
        ('personal Finance','https://www.financialexpress.com/print/personal-finance-print/feed/'),
        # ('Brandwagon', 'https://www.financialexpress.com/print/brandwagon/feed/'),
        # Other Feeds
        ('Economy', 'https://www.financialexpress.com/economy/feed/'),
        ('Banking & finance', 'https://www.financialexpress.com/industry/banking-finance/feed/'),
        ('Opinion', 'https://www.financialexpress.com/opinion/feed/'),
        ('Editorial', 'https://www.financialexpress.com/editorial/feed/'),
        ('Budget', 'https://www.financialexpress.com/budget/feed/'),
        ('Industry', 'https://www.financialexpress.com/industry/feed/'),
        ('Market', 'https://www.financialexpress.com/market/feed/'),
        ('Jobs', 'https://www.financialexpress.com/jobs/feed/'),
        ('SME', 'https://www.financialexpress.com/industry/sme/feed/'),
        ('Mutual Funds', 'https://www.financialexpress.com/money/mutual-funds/feed/'),
        ('Health','https://www.financialexpress.com/lifestyle/health/feed'),
        # ('Health Care','https://www.financialexpress.com/healthcare/feed'),
        ('Science','https://www.financialexpress.com/lifestyle/science/feed'),
        ('Infrastructure','https://www.financialexpress.com/infrastructure/feed'),
        ('Money','https://www.financialexpress.com/money/feed'),
    ]

    def get_cover_url(self):
        soup = self.index_to_soup('https://www.magzter.com/IN/The-Indian-Express-Ltd./Financial-Express-Mumbai/Business/')
        for citem in soup.findAll('meta', content=lambda s: s and s.endswith('view/3.jpg')):
            return citem['content']

    def preprocess_html(self, soup, *a):
        for img in soup.findAll(attrs={'data-src': True}):
            img['src'] = img['data-src']
        return soup