Update WirtchaftsWoche Online

This commit is contained in:
Kovid Goyal 2020-12-29 15:29:52 +05:30
parent 2e367ac402
commit aa72949779
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C

View File

@ -1,115 +1,102 @@
__license__ = 'GPL v3'
__license__ = 'GPL v3'
__copyright__ = '2013, Armin Geller'
##
# Written: May 2013 (new coding)
# Version: 4.4
# Last update: 2018-03-22
# Update AGE 2013-01-05; 2018-03-01; 2018-03-21; Modified by Hegi 2013-04-28, 2015-04-18, 2018-03-13, 2018-03-22
## 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'
description = u'Wirtschaftswoche Online - basierend auf den RRS-Feeds von Wiwo.de'
tags = 'Nachrichten, Blog, Wirtschaft'
publisher = 'Verlagsgruppe Handelsblatt GmbH / Redaktion WirtschaftsWoche Online'
category = 'business, economy, news, Germany'
publication_type = 'weekly magazine'
oldest_article = 7
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
simultaneous_downloads = 20
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://kaufhaus.handelsblatt.com/downloads/wirtschaftswoche-emagazin-p1952.html'
masthead_url = 'http://www.wiwo.de/images/wiwo_logo/5748610/1-formatOriginal.png'
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'
conversion_options = {'smarten_punctuation': True,
'authors': publisher,
'publisher': publisher}
# don't duplicate articles from "Schlagzeilen" / "Exklusiv" to other rubrics
ignore_duplicate_articles = {'title', 'url'}
# if you want to reduce size for an b/w or E-ink device, uncomment the following 4 lines:
# compress_news_images = True
# compress_news_images_auto_size = 16
# scale_news_images = (400,300)
# compress_news_images_max_size = 35
def get_cover_url(self):
soup = self.index_to_soup(self.cover_source)
style = soup.find('img', alt='WirtschaftsWoche eMagazin', style=True)[
'style']
self.cover_url = style.partition('(')[-1].rpartition(')')[0]
return self.cover_url
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']
preprocess_regexps = [
(
re.compile(
r'(<span class="hcf-location-mark">[^<]*)(</span>)', re.DOTALL | re.IGNORECASE),
lambda match: match.group(1) + '. ' + match.group(2)
),
(
re.compile(
r'(c-overline--article">[^>]*)(</span>)', re.DOTALL | re.IGNORECASE),
lambda match: match.group(1) + ': ' + match.group(2)
)
]
extra_css = '''
h1, h2 {font-size: 1.6em; text-align: left}
.c-leadtext {font-size: 1.2em; font-weight:bold; text-align: left}
h3, 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}
.hcf-location-mark {font-style: italic; font-weight:bold}
.c-overline {font-size: 1em; text-align: left;font-style: normal; font-weight:bold}
'''
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',
'o-article__content c-richText', 'c-leadtext'
]})
]
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-advertisment__fullWidth c-advertisment--P3_desktop'
]}),
dict(attrs={'class': lambda x: x and 'c-socialshare' in x.split()})
]
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
]
(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
# debug:
# input: <h2 class="c-headline c-headline--article u-margin-m"><span class="c-overline c-overline--alternate u-uppercase u-letter-spacing u-margin-m c-overline--article">Wandel kostet Milliarden</span> SUV und China sollen Audi wieder nach vorne bringen</h2>
# parsed: <h2 class="c-headline c-headline--article u-margin-m"><span class="c-overline c-overline--alternate u-uppercase u-letter-spacing u-margin-m c-overline--article">Wandel kostet Milliarden</span> SUV und China sollen Audi wieder nach vorne bringen</h2>
# processed: <h2 class="c-headline"><span class="c-overline">Wandel kostet Milliarden</span> SUV und China sollen Audi wieder nach vorne bringen</h2>
# structure: <h2 class="c-headline c-headline--article u-margin-m"><span class="c-overline c-overline--alternate u-uppercase u-letter-spacing u-margin-m c-overline--article">Wandel kostet Milliarden</span> SUV und China sollen Audi wieder nach vorne bringen</h2>
# epub: <h2 class="c-headline"><span class="c-overline">Wandel kostet Milliarden</span> SUV und China sollen Audi wieder nach vorne bringen</h2>
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, tail = url.rpartition('.')
return main + '-all' + sep + tail
main, sep, rest = url.rpartition('.')
return main + '-all' + sep + rest