calibre/recipes/guardian.recipe

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'

'''
www.guardian.co.uk
'''
from calibre import random_user_agent
from calibre.web.feeds.news import BasicNewsRecipe
from datetime import date


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


class Guardian(BasicNewsRecipe):

    title = u'The Guardian and The Observer'
    if date.today().weekday() == 6:
        base_url = "https://www.theguardian.com/observer"
    else:
        base_url = "https://www.theguardian.com/uk"

    __author__ = 'Kovid Goyal'
    language = 'en_GB'

    oldest_article = 7
    max_articles_per_feed = 100
    remove_javascript = True
    encoding = 'utf-8'
    remove_empty_feeds = True
    no_stylesheets = True
    remove_attributes = ['style', 'width', 'height']
    ignore_duplicate_articles = {'title', 'url'}

    timefmt = ' [%a, %d %b %Y]'

    remove_tags = [
        dict(attrs={'class': lambda x: x and '--twitter' in x}),
        dict(attrs={'class': lambda x: x and 'submeta' in x.split()}),
        dict(attrs={'data-component': ['share', 'social', 'nav', 'nav2']}),
        dict(attrs={'data-link-name': 'block share'}),
        dict(attrs={'data-print-layout': 'hide'}),
        dict(id=['dfp-ad--survey', 'sub-nav-root', 'the-caption', 'bannerandheader']),
        {'for': 'the-checkbox'},
        dict(href=['#maincontent', '#navigation']),
        dict(role=['navigation', 'button']),
        dict(attrs={'class': lambda x: x and 'inline-expand-image' in x}),
        dict(name='a', attrs={'aria-label': lambda x: x and 'Share On' in x}),
        dict(name='a', attrs={'class': lambda x: x and 'social__action js-social__action--top' in x}),
        dict(name='div', attrs={'id': 'share-count-root'}),
        dict(attrs={'class': lambda x: x and 'modern-visible' in x.split()}),
        classes('badge-slot reveal-caption__checkbox mobile-only element-rich-link'),
        dict(name=['link', 'meta', 'style', 'svg', 'input', 'source', 'noscript', 'button']),
        dict(name='img', src=lambda x: x and 'https://sb.scorecardresearch.com/' in x),
    ]
    remove_tags_after = [
        classes('content__article-body js-bottom-marker article-body-commercial-selector'),
    ]

    extra_css = """
            img {
                max-width: 100% !important;
                max-height: 100% !important;
            }

            a span {
                color: #E05E02;
            }

            figcaption span {
                font-size: 0.5em;
                color: #6B6B6B;
            }
        """

    def get_browser(self, *a, **kw):
        # This site returns images in JPEG-XR format if the user agent is IE
        if not hasattr(self, 'non_ie_ua'):
            try:
                self.non_ie_ua = random_user_agent(allow_ie=False)
            except TypeError:
                self.non_ie_ua = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.111 Safari/537.36'
        kw['user_agent'] = self.non_ie_ua
        br = BasicNewsRecipe.get_browser(self, *a, **kw)
        return br

    def get_cover_url(self):
        coverdate = date.today()
        if 'observer' in self.base_url:
            cover = (
                    'https://www.thepaperboy.com/frontpages/archive/The_Observer_' + str(coverdate.day) + '_' +
                    str(coverdate.month) + '_' + str(coverdate.year) + '_400.jpg')
        else:
            cover = (
                    'https://www.thepaperboy.com/frontpages/archive/The_Guardian_' + str(coverdate.day) + '_' +
                    str(coverdate.month) + '_' + str(coverdate.year) + '_400.jpg')

        return cover

    def parse_observer_index(self, soup):
        for section in soup.findAll('section'):
            articles = []
            title = self.tag_to_string(section.find('h2'))
            if not title:
                continue
            self.log('Found section:', title)
            for li in section.findAll('li'):
                a = li.find('a', attrs={'href': True, 'aria-label': True})
                if a:
                    url = a['href']
                    if url.startswith('/'):
                        url = self.base_url.rpartition('/')[0] + url
                    self.log('\t', a['aria-label'], url)
                    articles.append({'title': a['aria-label'], 'url': url})
            if articles:
                yield title, articles

    def parse_section(self, section_url, title_prefix=''):
        feeds = []
        soup = self.index_to_soup(section_url)
        if '/observer' in section_url:
            return list(self.parse_observer_index(soup))
        for section in soup.findAll('section'):
            title = title_prefix + self.tag_to_string(section.find(
                attrs={'class': 'fc-container__header__title'})).strip().capitalize()
            self.log('\nFound section:', title)
            if 'Video' in title:
                self.log('=======> Skip section:', title)
                continue
            feeds.append((title, []))
            for li in section.findAll('li'):
                for a in li.findAll('a', attrs={'data-link-name': 'article'}, href=True):
                    title = self.tag_to_string(a).strip()
                    url = a['href']
                    if url.startswith('/'):
                        url = self.base_url.rpartition('/')[0] + url
                    self.log(' ', title, url)
                    feeds[-1][1].append({'title': title, 'url': url})
                    break
        return feeds

    def parse_index(self):
        feeds = self.parse_section(self.base_url)
        feeds += self.parse_section(
            'https://www.theguardian.com/uk/sport', 'Sport - ')
        return feeds