Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update WirtschaftsWoche Online

Browse Source
This commit is contained in:
Kovid Goyal 2015-04-19 08:57:00 +05:30
parent 1af26bb71e
commit 22d5599373
1 changed files with 12 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
recipes/wirtscafts_woche.recipe
View File

@ -5,11 +5,11 @@ __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__ = 'Hegi' # Update AGE 2013-01-05; Modified by Hegi 2013-04-28
__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'
@ -29,9 +29,10 @@ class WirtschaftsWocheOnline(BasicNewsRecipe):
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 = True
# compress_news_images_auto_size = 16
# scale_news_images = (400,300)
scale_news_images = (400,300)
compress_news_images_max_size = 35
timefmt = ' [%a, %d %b %Y]'
@ -40,18 +41,19 @@ class WirtschaftsWocheOnline(BasicNewsRecipe):
'publisher' : publisher}
language = 'de_DE'
encoding = 'UTF-8'
cover_source = 'http://www.wiwo-shop.de/wirtschaftswoche/wirtschaftswoche-emagazin-p1952.html'
cover_source = 'https://kaufhaus.handelsblatt.com/downloads/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']
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
# 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))]
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} \
@ -83,4 +85,3 @@ class WirtschaftsWocheOnline(BasicNewsRecipe):
def print_version(self, url):
main, sep, id = url.rpartition('/')
return main + '/v_detail_tab_print/' + id