calibre/recipes/sunday_times_magazine.recipe

__license__ = 'GPL v3'
__copyright__ = '2010-2019'
'''
www.thetimes.co.uk/magazine/the-sunday-times-magazine/
'''

from mechanize import Request

from calibre import random_user_agent
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 TimesOnline(BasicNewsRecipe):
    title = 'The Sunday Times Magazine UK'
    __author__ = 'Bobby Steel & Darko Miletic'
    description = 'Newsmagazine from United Kingdom and World'
    language = 'en_GB'
    publisher = 'Times Newspapers Ltd'
    category = 'news, politics, UK'
    oldest_article = 3
    max_articles_per_feed = 500
    no_stylesheets = True
    use_embedded_content = False
    encoding = 'utf-8'
    delay = 1
    needs_subscription = True
    publication_type = 'newspaper'
    INDEX = 'https://www.thetimes.co.uk'
    LOGIN = 'https://login.thetimes.co.uk/'
    PREFIX = u'https://www.thetimes.co.uk'
    extra_css = """
        .author-name,.authorName{font-style: italic}
        .published-date,.multi-position-photo-text{
            font-family: Arial,Helvetica,sans-serif;
            font-size: small; color: gray;
            display:block; margin-bottom: 0.5em}
        body{font-family: Georgia,"Times New Roman",Times,serif}
    """

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

    def get_browser(self, *a, **kw):
        start_url = self.INDEX
        kw['user_agent'] = random_user_agent(allow_ie=False)
        br = BasicNewsRecipe.get_browser(self, *a, **kw)
        self.log('Starting login process...')
        res = br.open(start_url)
        sso_url = res.geturl()
        self.log(sso_url)
        request_query = {
            'username': self.username,
            'password': self.password,
            's': 1,
            'gotoUrl': self.INDEX,
        }
        rq = Request(self.LOGIN, headers={
            'Accept': 'text/html',
            'Accept-Language': 'en-US,en;q=0.8',
            'X-HTTP-Method-Override': 'POST',
            'X-Requested-With': 'XMLHttpRequest',
        }, data=request_query)
        self.log('Sending login request...')
        res = br.open(rq)
        return br
    # }}}

    def get_cover_url(self):
        from datetime import date
        from datetime import timedelta
        today = date.today()
        today_index = today.weekday()
        if (today_index == 5):  # new edition drops on Saturday AM
            today += timedelta(1)
        elif (today_index < 5):  # Mon-Thurs
            today_index = (
                today_index + 1
            ) % 7  # Recalibrate to days back MON = 0, SUN = 6 -> SUN = 0 .. SAT = 6
            today = today - timedelta(today_index)  # Rewind to most recent Sunday
        cover = 'https://cdn2-img.pressreader.com/pressdisplay/docserver/getimage.aspx?file=1174' + today.strftime(
            '%Y') + today.strftime('%m') + today.strftime(
                '%d') + '00000000001001&page=1&scale=100'
        self.log(cover)
        br = BasicNewsRecipe.get_browser(self)
        try:
            br.open(cover)
        except:
            self.log("\nCover unavailable")
            cover = None
        return cover

    remove_tags = [
        classes('Topics is-hidden Tooltip Toolbar Comments RelatedLinks'),
        {'name': ['object', 'link', 'iframe', 'base', 'meta', 'script']}, {
            'attrs': {
                'class': [
                    'tools comments-parent', 'u-hide', 'Tooltip',
                    'Toolbar Toolbar--bottom', 'Comments Article-container',
                    'ArticlePager', 'Media-caption', 'RelatedLinks']}}, {
                        'attrs': {
                            'class': lambda x: x and 'Toolbar' in x}}]
    remove_attributes = ['lang']
    keep_only_tags = [
        dict(attrs={'id': 'article-main'}),
        dict(attrs={'class': 'f-author'}),
        dict(attrs={'id': 'bodycopy'})]

    feeds = [(
        u'The Sunday Times Magazine',
        u'http://www.thetimes.co.uk/magazine/the-sunday-times-magazine/'),
             (u'Sunday Times Style', u'http://www.thetimes.co.uk/magazine/style/')]

    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        return self.adeify_images(soup)

    def parse_index(self):
        totalfeeds = []
        lfeeds = self.get_feeds()
        for feedobj in lfeeds:
            feedtitle, feedurl = feedobj
            self.report_progress(
                0,
                _('Fetching feed') + ' %s...' %
                (feedtitle if feedtitle else feedurl))
            articles = []
            soup = self.index_to_soup(feedurl)
            for atag in soup.findAll('a', href=True):
                parentName = atag.parent.name
                title = self.tag_to_string(atag).strip()
                if (
                    parentName == 'h2' or
                    parentName == 'h3') and title is not None and title != '':
                    url = self.INDEX + atag['href']
                    articles.append({
                        'title': title,
                        'date': '',
                        'url': url,
                        'description': ''})
            totalfeeds.append((feedtitle, articles))
        return totalfeeds