calibre/recipes/wirtscafts_woche.recipe
Kovid Goyal a6840fb462
pep8
2021-01-04 22:15:31 +05:30

110 lines
4.0 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2013, Armin Geller'
##
# Written: May 2013 (new coding)
# Version: 4.4
# Last update: 2020-12-29
##
'''
Fetch WirtschaftsWoche Online
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class WirtschaftsWocheOnline(BasicNewsRecipe):
title = u'WirtschaftsWoche Online'
__author__ = 'Armin Geller' # Update AGE 2013-01-05; 2018-03-01
description = u'German Online Portal of WirtschaftsWoche'
publisher = 'Verlagsgruppe Handelsblatt GmbH Redaktion WirtschaftsWoche Online'
category = 'business, economy, news, Germany'
publication_type = 'weekly magazine'
oldest_article = 7
max_articles_per_feed = 100
auto_cleanup = False
no_stylesheets = True
remove_javascript = True
remove_empty_feeds = True
timefmt = ' [%a, %d %b %Y]'
language = 'de_DE'
encoding = 'UTF-8'
cover_source = 'https://www.ikiosk.de/shop/epaper/wirtschaftswoche.html'
masthead_url = 'http://www.wiwo.de/images/wiwo_logo/5748610/1-formatOriginal.png'
def get_cover_url(self):
cover_source_soup = self.index_to_soup(self.cover_source)
preview_image_div = cover_source_soup.find(attrs={'class': 'gallery'})
return preview_image_div.a.img['src']
extra_css = '''
h1, h2 {font-size: 1.6em; text-align: left}
.c-leadtext {font-size: 1em; font-style: italic; font-weight: normal}
h4 {font-size: 1.3em;text-align: left}
h5, h6, a {font-size: 1em;text-align: left}
.c-metadata {font-size: .75em;text-align: left; font-style: italic}
'''
keep_only_tags = [
dict(
name='div',
attrs={
'class': [
'o-article__element', 'o-article__content c-richText',
'o-article__content-element o-article__content-element--richtext'
]
}
)
]
remove_tags = [
dict(
name='div',
attrs={
'class': [
'c-pagination u-flex',
'c-standard-article-teaser',
'c-pagination u-flex ajaxify',
'c-socialshare u-margin-xxl ',
'c-list', # AGe 2020-12-29
]
}
)
]
feeds = [
(u'Schlagzeilen', u'http://www.wiwo.de/contentexport/feed/rss/schlagzeilen'),
(u'Exklusiv', u'http://www.wiwo.de/contentexport/feed/rss/exklusiv'),
# (u'Themen', u'http://www.wiwo.de/contentexport/feed/rss/themen'), # AGE no print version
(u'Unternehmen', u'http://www.wiwo.de/contentexport/feed/rss/unternehmen'),
(u'Finanzen', u'http://www.wiwo.de/contentexport/feed/rss/finanzen'),
(u'Politik', u'http://www.wiwo.de/contentexport/feed/rss/politik'),
(u'Erfolg', u'http://www.wiwo.de/contentexport/feed/rss/erfolg'),
(u'Technologie', u'http://www.wiwo.de/contentexport/feed/rss/technologie'),
# (u'Green-WiWo', u'http://green.wiwo.de/feed/rss/') # AGE offline
]
# For hegi # AGE new 2018-03-21
# Add ': ' between headline part one and two
# Wandel kostet Milliarden + ': ' + SUV und China sollen Audi wieder nach vorne bringen
# https://www.wiwo.de/unternehmen/auto/wandel-kostet-milliarden-suv-und-china-sollen-audi-wieder-nach-vorne-bringen/21069566.html
preprocess_regexps = [
(
re.compile(
r'(c-overline--article">[^>]*)(</span>)', re.DOTALL | re.IGNORECASE
), lambda match: match.group(1) + ': ' + match.group(2)
),
]
# /For hegi
# one page n times url: https://www.wiwo.de/finanzen/geldanlage/bla-bla/21020646.html
# all in one page article url: https://www.wiwo.de/finanzen/geldanlage/bla-bla/21020646-all.html
def print_version(self, url):
main, sep, rest = url.rpartition('.')
return main + '-all' + sep + rest