mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
89 lines
4.4 KiB
Plaintext
89 lines
4.4 KiB
Plaintext
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class Handelsblatt(BasicNewsRecipe):
|
|
title = u'Handelsblatt'
|
|
__author__ = 'malfi' # modified by Hegi, last change 2013-05-20
|
|
description = u'Handelsblatt - basierend auf den RRS-Feeds von Handelsblatt.de'
|
|
tags = 'Nachrichten, Blog, Wirtschaft'
|
|
publisher = 'Verlagsgruppe Handelsblatt GmbH'
|
|
category = 'business, economy, news, Germany'
|
|
publication_type = 'daily newspaper'
|
|
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.handelsblatt-shop.com/epaper/482/'
|
|
# masthead_url = 'http://www.handelsblatt.com/images/hb_logo/6543086/1-format3.jpg'
|
|
masthead_url = 'http://www.handelsblatt-chemie.de/wp-content/uploads/2012/01/hb-logo.gif'
|
|
|
|
def get_cover_url(self):
|
|
cover_source_soup = self.index_to_soup(self.cover_source)
|
|
preview_image_div = cover_source_soup.find(attrs={'class':'vorschau'})
|
|
return 'http://www.handelsblatt-shop.com'+preview_image_div.a.img['src']
|
|
|
|
# remove_tags_before = dict(attrs={'class':'hcf-overline'})
|
|
# remove_tags_after = dict(attrs={'class':'hcf-footer'})
|
|
# Alternatively use this:
|
|
|
|
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'Handelsblatt Exklusiv',u'http://www.handelsblatt.com/rss/exklusiv'),
|
|
(u'Handelsblatt Top-Themen',u'http://www.handelsblatt.com/rss/top-themen'),
|
|
(u'Handelsblatt Schlagzeilen',u'http://www.handelsblatt.com/rss/ticker/'),
|
|
(u'Handelsblatt Finanzen',u'http://www.handelsblatt.com/rss/finanzen/'),
|
|
(u'Handelsblatt Unternehmen',u'http://www.handelsblatt.com/rss/unternehmen/'),
|
|
(u'Handelsblatt Politik',u'http://www.handelsblatt.com/rss/politik/'),
|
|
(u'Handelsblatt Technologie',u'http://www.handelsblatt.com/rss/technologie/'),
|
|
(u'Handelsblatt Meinung',u'http://www.handelsblatt.com/rss/meinung'),
|
|
(u'Handelsblatt Magazin',u'http://www.handelsblatt.com/rss/magazin/'),
|
|
(u'Handelsblatt Weblogs',u'http://www.handelsblatt.com/rss/blogs')
|
|
]
|
|
|
|
# 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}'
|
|
|
|
def print_version(self, url):
|
|
main, sep, id = url.rpartition('/')
|
|
return main + '/v_detail_tab_print/' + id
|
|
|