calibre/recipes/economist.recipe

#!/usr/bin/env  python2

__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''
economist.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag, NavigableString
from collections import OrderedDict

import re
import cookielib


class Economist(BasicNewsRecipe):

    title = 'The Economist'
    language = 'en'

    __author__ = "Kovid Goyal"
    INDEX = 'https://www.economist.com/printedition'
    description = ('Global news and current affairs from a European'
                   ' perspective. Best downloaded on Friday mornings (GMT)')
    extra_css      = '''
        .headline {font-size: x-large;}
        h2 { font-size: small;  }
        h1 { font-size: medium;  }
        em.Bold {font-weight:bold;font-style:normal;}
        em.Italic {font-style:italic;}
        p.xhead {font-weight:bold;}
        .pullquote {
            float: right;
            font-size: larger;
            font-weight: bold;
            font-style: italic;
            page-break-inside:avoid;
            border-bottom: 3px solid black;
            border-top: 3px solid black;
            width: 228px;
            margin: 0px 0px 10px 15px;
            padding: 7px 0px 9px;
        }
        '''
    oldest_article = 7.0
    resolve_internal_links = True
    remove_tags = [
        dict(name=['script', 'noscript', 'title',
                   'iframe', 'cf_floatingcontent']),
        dict(attrs={'class': ['dblClkTrk', 'ec-article-info',
                              'share_inline_header', 'related-items',
                              'main-content-container', 'ec-topic-widget']}),
        {'class': lambda x: x and 'share-links-header' in x},
    ]
    keep_only_tags = [dict(name='article', id=lambda x: not x)]
    no_stylesheets = True
    preprocess_regexps = [(re.compile('</html>.*', re.DOTALL),
                           lambda x:'</html>')]

    # economist.com has started throttling after about 60% of the total has
    # downloaded with connection reset by peer (104) errors.
    delay = 1

    needs_subscription = False

    def get_browser(self):
        br = BasicNewsRecipe.get_browser(self)
        # Add a cookie indicating we have accepted Economist's cookie
        # policy (needed when running from some European countries)
        ck = cookielib.Cookie(
            version=0, name='notice_preferences', value='2:', port=None,
            port_specified=False, domain='.economist.com',
            domain_specified=False, domain_initial_dot=True, path='/',
            path_specified=False, secure=False, expires=None, discard=False,
            comment=None, comment_url=None, rest={'HttpOnly': None},
            rfc2109=False)
        br.cookiejar.set_cookie(ck)
        return br

    def parse_index(self):
        return self.economist_parse_index()

    def economist_parse_index(self):
        # return [('Articles', [{'title':'test',
        # 'url':'https://www.economist.com/news/americas/21699494-guide-cutting-corners-way-jos'}])]
        soup = self.index_to_soup(self.INDEX)
        div = soup.find('div', attrs={'class': 'issue-image'})
        if div is not None:
            img = div.find('img', src=True)
            if img is not None:
                self.cover_url = re.sub('thumbnail', 'full', img['src'])
        feeds = OrderedDict()
        for section in soup.findAll(attrs={'class': lambda x: x and 'section' in
                                           x}):
            h4 = section.find('h4')
            if h4 is None:
                continue
            section_title = self.tag_to_string(h4).strip()
            if not section_title:
                continue
            self.log('Found section: %s' % section_title)
            articles = []
            subsection = ''
            for node in section.findAll(attrs={'class': 'article'}):
                subsec = node.findPreviousSibling('h5')
                if subsec is not None:
                    subsection = self.tag_to_string(subsec)
                prefix = (subsection + ': ') if subsection else ''
                a = node.find('a', href=True)
                if a is not None:
                    url = a['href']
                    if url.startswith('/'):
                        url = 'https://www.economist.com' + url
                    url += '/print'
                    title = self.tag_to_string(a)
                    if title:
                        title = prefix + title
                        self.log('\tFound article:', title)
                        articles.append({'title': title, 'url': url,
                                         'description': '', 'date': ''})

            if articles:
                if section_title not in feeds:
                    feeds[section_title] = []
                feeds[section_title] += articles

        ans = [(key, val) for key, val in feeds.iteritems()]
        if not ans:
            raise Exception('Could not find any articles, either the '
                            'economist.com server is having trouble and you should '
                            'try later or the website format has changed and the '
                            'recipe needs to be updated.')
        return ans

    def eco_find_image_tables(self, soup):
        for x in soup.findAll('table', align=['right', 'center']):
            if len(x.findAll('font')) in (1, 2) and len(x.findAll('img')) == 1:
                yield x

    def postprocess_html(self, soup, first):
        body = soup.find('body')
        for name, val in body.attrs:
            del body[name]

        for table in list(self.eco_find_image_tables(soup)):
            caption = table.find('font')
            img = table.find('img')
            div = Tag(soup, 'div')
            div['style'] = 'text-align:left;font-size:70%'
            ns = NavigableString(self.tag_to_string(caption))
            div.insert(0, ns)
            div.insert(1, Tag(soup, 'br'))
            del img['width']
            del img['height']
            img.extract()
            div.insert(2, img)
            table.replaceWith(div)
        return soup

    def canonicalize_internal_url(self, url, is_link=True):
        if url.endswith('/print'):
            url = url.rpartition('/')[0]
        return BasicNewsRecipe.canonicalize_internal_url(self, url, is_link=is_link)