calibre/recipes/handelsblatt.recipe

#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2016, Aimylios <aimylios at gmx.de>

from __future__ import unicode_literals, division, absolute_import, print_function

'''
handelsblatt.com
'''

import re
from calibre.web.feeds.news import BasicNewsRecipe


class Handelsblatt(BasicNewsRecipe):
    title = 'Handelsblatt'
    __author__ = 'Aimylios'  # based on the work of malfi and Hegi
    description = 'RSS-Feeds von Handelsblatt.com'
    publisher = 'Verlagsgruppe Handelsblatt GmbH'
    publication_type = 'newspaper'
    needs_subscription = 'optional'
    language = 'de'

    oldest_article = 2
    max_articles_per_feed = 15
    simultaneous_downloads = 10
    no_stylesheets = True
    remove_javascript = True
    remove_empty_feeds = True
    ignore_duplicate_articles = {'title', 'url'}

    conversion_options = {'smarten_punctuation': True,
                          'publisher': publisher}

    # uncomment this to reduce file size
    # compress_news_images          = True
    # compress_news_images_max_size = 16

    login_url = 'https://id.handelsblatt.com/login/credentials?service=https://www.handelsblatt.com'
    cover_source = 'https://kaufhaus.handelsblatt.com/downloads/handelsblatt-epaper-p1951.html'
    masthead_url = 'https://www.handelsblatt.com/images/logo_handelsblatt/11002806/8-formatOriginal.png'

    feeds = [
        ('Top-Themen', 'http://www.handelsblatt.com/contentexport/feed/top-themen'),
        ('Politik', 'http://www.handelsblatt.com/contentexport/feed/politik'),
        ('Unternehmen', 'http://www.handelsblatt.com/contentexport/feed/unternehmen'),
        ('Finanzen', 'http://www.handelsblatt.com/contentexport/feed/finanzen'),
        ('Technologie', 'http://www.handelsblatt.com/contentexport/feed/technologie'),
        ('Panorama', 'http://www.handelsblatt.com/contentexport/feed/panorama')
    ]

    keep_only_tags = [
        dict(name='div', attrs={'class': ['vhb-article-container']})
    ]

    remove_tags = [
        dict(name='span', attrs={'class': ['vhb-colon', 'vhb-label-premium']}),
        dict(name='aside', attrs={'class': ['vhb-article-element vhb-left',
                                            'vhb-article-element vhb-left vhb-teasergallery',
                                            'vhb-article-element vhb-left vhb-shorttexts']}),
        dict(name='aside', attrs={'class': re.compile('vhb-club-events')}),
        dict(name='article', attrs={'class': ['vhb-imagegallery vhb-teaser',
                                              'vhb-teaser vhb-type-video']}),
        dict(name='small', attrs={'class': ['vhb-credit']}),
        dict(name='ul', attrs={'class': ['hcf-redaktion']}),
        dict(name='div', attrs={'class': ['white_content', 'fb-post',
                                          'opinary-widget-wrapper', 'dg_health',
                                          'vhb-article__content-element--shorttextgallery',
                                          'vhb-hollow-area vhb-hollow-area--col-1']}),
        dict(name='div', attrs={'class': re.compile('vhb-imagegallery')}),
        dict(name='div', attrs={'id': ['highcharts_infografik']}),
        dict(name='div', attrs={'id': re.compile('dax-sentiment')}),
        dict(name=['div', 'section'], attrs={'class': re.compile('slider')}),
        dict(name='a', attrs={'class': ['twitter-follow-button']}),
        dict(name='img', attrs={'alt': re.compile('Handelsblatt Morning Briefing')}),
        dict(name='img', attrs={'alt': re.compile('Kolumnenkabinet')}),
        dict(name=['link', 'blockquote'])
    ]

    preprocess_regexps = [
        # insert ". " after the location at the beginning of an article
        (re.compile(r'(<span class="hcf-location-mark">[^<]+)(</span>)',
                    re.IGNORECASE), lambda match: match.group(1) + '. ' + match.group(2)),
        # insert ": " between title and text of captions
        (re.compile(r'(<em itemtype="text" itemprop="name" class="vhb-title">[^<]+)(</em>)',
                    re.IGNORECASE), lambda match: match.group(1) + ': ' + match.group(2)),
        # convert "data-src" to "src" attributes
        (re.compile(r'( data-src=")([^"]*")', re.IGNORECASE), lambda match: ' src="' + match.group(2))
    ]

    extra_css = 'h2 {font-size: 1em; text-align: left} \
                 h3 {font-size: 1em; text-align: left} \
                 h4 {font-size: 1em; text-align: left; margin-bottom: 0em} \
                 em {font-style: normal; font-weight: bold} \
                 .vhb-subline {font-weight: normal; text-transform: uppercase} \
                 .vhb-headline {font-size: 1.6em} \
                 .vhb-teaser-head {margin-top: 1em; margin-bottom: 1em} \
                 .vhb-hollow-area--innercontent {font-size: 0.6em} \
                 .hcf-location-mark {font-weight: bold} \
                 .panel-body p {margin-top: 0em}'

    def get_browser(self):
        br = BasicNewsRecipe.get_browser(self)
        if self.username is not None and self.password is not None:
            br.open(self.login_url)
            br.select_form(nr=0)
            br['username'] = self.username
            br['password'] = self.password
            br.submit()
        return br

    def get_cover_url(self):
        soup = self.index_to_soup(self.cover_source)
        style = soup.find('img', alt='Handelsblatt ePaper',
                          style=True)['style']
        self.cover_url = style.partition('(')[-1].rpartition(')')[0]
        return self.cover_url

    def print_version(self, url):
        main, sep, id = url.rpartition('/')
        return main + '/v_detail_tab_print/' + id

    def preprocess_html(self, soup):
        # remove all articles without relevant content (e.g., videos)
        article = soup.find('div', {'class': 'vhb-article-container'})
        if article is None:
            self.abort_article()
        return soup

    def postprocess_html(self, soup, first_fetch):
        # convert lists of author(s) and date(s) into simple text
        for cap in soup.findAll('div', {'class': re.compile('vhb-article-caption')}):
            cap.replaceWith(cap.renderContents().decode('utf-8').strip() + ' ')
        for row in soup.findAll('div', {'class': 'vhb-article-author-row'}):
            for ul in row.findAll('ul'):
                entry = ''
                for li in ul.findAll(lambda tag: tag.name == 'li' and not tag.attrs):
                    entry = entry + self.tag_to_string(li).strip() + ', '
                for li in ul.findAll(lambda tag: tag.name == 'li' and tag.attrs):
                    entry = entry + self.tag_to_string(li)
                ul.parent.replaceWith(entry)
        # remove all local hyperlinks
        for a in soup.findAll('a', {'href': True}):
            if '.handelsblatt.com/' in a['href']:
                a.replaceWith(a.renderContents().decode('utf-8'))
        # make sure that all figure captions (including the source) are shown
        # without linebreaks by using the alternative text given within <img/>
        # instead of the original text (which is oddly formatted)
        for fig in soup.findAll('figcaption', {'class': 'vhb-inline-picture'}):
            cap = fig.find('img')['alt']
            fig.find('div', {'class': 'vhb-caption'}).replaceWith(cap)
        # remove references to related articles
        for strong in soup.findAll('strong'):
            if strong.string and re.match('^Mehr:? ?', strong.string):
                p_parent = strong.find_parent('p')
                if p_parent:
                    p_parent.decompose()
                    break
        # clean up remainders of embedded content
        for div in soup.findAll('div', {'style': True}):
            if len(div.attrs) == 1:
                del div['style']
        return soup