Hi Folks,
... after a couple of weeks fiddling about, here my "production quality" recipe for WirtschaftsWoche Online. - Enjoy
.
The template I began with is from Divingduck and I got his clearance for posting my modified version here:
Code:
__license__ = 'GPL v3'
__copyright__ = '2013, Armin Geller'
'''
Fetch WirtschaftsWoche Online
'''
import re
#import time
from calibre.web.feeds.news import BasicNewsRecipe
class WirtschaftsWocheOnline(BasicNewsRecipe):
title = u'WirtschaftsWoche Online'
__author__ = 'Armin Geller' # Update AGE 2013-01-05; Modified by Hegi 2013-04-28
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'
language = 'de_DE'
oldest_article = 7
max_articles_per_feed = 100
simultaneous_downloads= 20
auto_cleanup = False
no_stylesheets = True
remove_javascript = True
remove_empty_feeds = True
# 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 this:
# compress_news_images = True
# compress_news_images_auto_size = 16
# scale_news_images = (400,300)
timefmt = ' [%a, %d %b %Y]'
conversion_options = { 'smarten_punctuation' : True,
'authors' : publisher,
'publisher' : publisher }
language = 'de_DE'
encoding = 'UTF-8'
cover_source = 'http://www.wiwo-shop.de/wirtschaftswoche/wirtschaftswoche-emagazin-p1952.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':'container vorschau'})
return 'http://www.wiwo-shop.de'+preview_image_div.a.img['src']
# Insert ". " after "Place" in <span class="hcf-location-mark">Place</span>
# If you use .epub format you could also do this as extra_css '.hcf-location-mark:after {content: ". "}'
preprocess_regexps = [(re.compile(r'(<span class="hcf-location-mark">[^<]*)(</span>)', re.DOTALL|re.IGNORECASE), lambda match: match.group(1) + '. ' + match.group(2))]
extra_css = 'h1 {font-size: 1.6em; text-align: left} \
h2 {font-size: 1em; font-style: italic; font-weight: normal} \
h3 {font-size: 1.3em;text-align: left} \
h4, h5, h6, a {font-size: 1em;text-align: left} \
.hcf-caption {font-size: 1em;text-align: left; font-style: italic} \
.hcf-location-mark {font-style: italic}'
keep_only_tags = [
dict(name='div', attrs={'class':['hcf-column hcf-column1 hcf-teasercontainer hcf-maincol']}),
dict(name='div', attrs={'id':['contentMain']})
]
remove_tags = [
dict(name='div', attrs={'class':['hcf-link-block hcf-faq-open', 'hcf-article-related']})
]
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 no print version
]
def print_version(self, url):
main, sep, id = url.rpartition('/')
return main + '/v_detail_tab_print/' + id
Kovid, it would be great, if you could include this in one of the next releases.
Thanks to all who helped me getting there
!
Hegi.