mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
135 lines
5.0 KiB
Python
135 lines
5.0 KiB
Python
#!/usr/bin/env python
|
|
# vim:fileencoding=utf-8
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2013, Armin Geller'
|
|
|
|
##
|
|
# Written: May 2013 (new coding)
|
|
# Version: 5.1
|
|
# Last update: 2022-08-07
|
|
##
|
|
##
|
|
'''
|
|
Fetch WirtschaftsWoche Online
|
|
'''
|
|
|
|
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, 2022-08-05
|
|
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'
|
|
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'
|
|
|
|
recipe_specific_options = {
|
|
'days': {
|
|
'short': 'Oldest article to download from this news source. In days ',
|
|
'long': 'For example, 0.5, gives you articles from the past 12 hours',
|
|
'default': str(oldest_article)
|
|
}
|
|
}
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
BasicNewsRecipe.__init__(self, *args, **kwargs)
|
|
d = self.recipe_specific_options.get('days')
|
|
if d and isinstance(d, str):
|
|
self.oldest_article = float(d)
|
|
|
|
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={'data-macro': [
|
|
'lead-media',
|
|
]}),
|
|
dict(
|
|
name='div',
|
|
attrs={
|
|
'class': [
|
|
'o-article__element',
|
|
'o-article__content c-richText',
|
|
]
|
|
}
|
|
),
|
|
dict(name='div', attrs={'id': [
|
|
'biga_wrapper',
|
|
]})
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name='source'),
|
|
dict(
|
|
name='div',
|
|
attrs={
|
|
'class': [
|
|
'c-list',
|
|
'o-article__element u-margin-xxl u-font-s-md',
|
|
'c-advertisment__fullWidth c-advertisment--P4_desktop',
|
|
'c-advertisment__fullWidth c-advertisment--P3_mobile',
|
|
'c-advertisment__fullWidth c-advertisment--P2_mobile',
|
|
'c-advertisment__fullWidth c-advertisment--CT_contentteaser_mobile_1',
|
|
'c-teaser c-teaser-inline',
|
|
'c-teaser c-teaser-inline isPremiumTeaser',
|
|
'c-teaser c-teaser-inline c-teaser-inline--column',
|
|
'c-teaser c-teaser-inline c-teaser-inline--xl isPremiumTeaser',
|
|
'o-teaser-list js-tt o-artbox o-artbox--articleboxplus',
|
|
'o-article__content-element u-margin-xxl',
|
|
'o-article__content-element u-margin-xxl ajaxify',
|
|
'o-article__element o-article__element-block',
|
|
]
|
|
}
|
|
)
|
|
]
|
|
|
|
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')
|
|
]
|
|
|
|
def image_url_processor(self, baseurl, url):
|
|
if url.startswith('/images/'):
|
|
return 'https://www.wiwo.de' + url
|
|
return url
|
|
|
|
def preprocess_raw_html(self, raw, url):
|
|
# Slideshow image source need some help to find all images
|
|
soup = self.index_to_soup(raw)
|
|
for img in soup.findAll('img', attrs={'data-lazy': True}):
|
|
img['src'] = 'https://www.wiwo.de' + img['data-lazy']
|
|
return str(soup)
|
|
|
|
def print_version(self, url):
|
|
main, sep, rest = url.rpartition('.')
|
|
return main + '-all' + sep + rest
|