mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-08 10:44:09 -04:00
Update Neu Osnabrücker Zeitung
Merge branch 'master' of https://github.com/aimylios/calibre
This commit is contained in:
Kovid Goyal
commit
e43705a3a3
|
Before Width: | Height: | Size: 547 B After Width: | Height: | Size: 547 B |
@ -1,117 +0,0 @@
|
||||
# vim:fileencoding=utf-8
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class AdvancedUserRecipe1380105782(BasicNewsRecipe):
|
||||
title = u'Neue Osnabrücker Zeitung'
|
||||
__author__ = 'vo_he'
|
||||
description = 'HNY 2014'
|
||||
encoding = 'utf-8'
|
||||
language = 'de'
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
cover_url = 'http://www.noz.de/apple-touch-icon-144x144-precomposed.png'
|
||||
|
||||
remove_tags_before = dict(id='feedContent')
|
||||
remove_tags_before = dict(id='headline')
|
||||
|
||||
remove_tags_after = [dict(id='footer-start')]
|
||||
remove_tags_after = [dict(name='div', attrs={'class': 'accordion-group'})]
|
||||
remove_tags_after = [
|
||||
dict(name='div', attrs={'class': 'accordion accordion-two-column most-read'})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'id': 'ui-datepicker-div'}),
|
||||
dict(name='div', attrs={'class': 'nav-second'}),
|
||||
dict(name='div', attrs={'class': 'nav-first'}),
|
||||
dict(name='div', attrs={'class': 'icon-print'}),
|
||||
dict(name='div', attrs={'class': 'social-button'}),
|
||||
dict(name='div', attrs={'class': 'social-media-bar'}),
|
||||
dict(name='div', attrs={'class': 'pull-right'}),
|
||||
dict(name='div', attrs={'class': 'btn btn-primary flat-button'}),
|
||||
dict(name='div', attrs={'class': 'carousel-wrapper'}),
|
||||
dict(name='a', attrs={
|
||||
'class': 'right-content merchandising hidden-tablet'}),
|
||||
dict(name='div', attrs={'class': 'border-circle pull-left'}),
|
||||
dict(name='div', attrs={
|
||||
'class': 'row show-grid general-infoimageContainer '}),
|
||||
dict(name='div', attrs={'class': 'location-list'}),
|
||||
dict(name='div', attrs={'class': 'block'}),
|
||||
dict(name='div', attrs={'class': 'furtherGalleries largeSpaceTop'}),
|
||||
dict(name='div', attrs={'class': 'accordion-group'}),
|
||||
dict(name='div', attrs={'class': 'accordion-heading'}),
|
||||
dict(name='div', attrs={'class': 'accordion-toggle'}),
|
||||
dict(name='div', attrs={'class': 'accordion-inner'})
|
||||
]
|
||||
|
||||
feeds = [(u'Melle', u'http://www.noz.de/rss/ressort/Melle'),
|
||||
(u'Nordrhein Westfalen',
|
||||
u'http://www.noz.de/rss/ressort/Nordrhein-Westfalen'),
|
||||
(u'Niedersachsen', u'http://www.noz.de/rss/ressort/Niedersachsen'),
|
||||
(u'Vermischtes', u'http://www.noz.de/rss/ressort/Vermischtes'),
|
||||
(u'GutzuWissen', u'http://www.noz.de/rss/ressort/Gut%20zu%20Wissen'),
|
||||
(u'Sport', u'http://www.noz.de/rss/ressort/Sport'),
|
||||
(u'Kultur', u'http://www.noz.de/rss/ressort/Kultur'),
|
||||
(u'Medien', u'http://www.noz.de/rss/ressort/Medien'),
|
||||
(u'Belm', u'http://www.noz.de/rss/ressort/Belm'),
|
||||
(u'Bissendorf',
|
||||
u' [url]http://www.noz.de/rss/ressort/Bissendorf[/url]'),
|
||||
(u'Osnabrueck', u'http://www.noz.de/rss/ressort/Osnabr%C3%BCck'),
|
||||
(u'Bad Essen', u'http://www.noz.de/rss/ressort/Bad%20Essen'),
|
||||
(u'Politik', u'http://www.noz.de/rss/ressort/Politik'),
|
||||
(u'Wirtschaft', u'http://www.noz.de/rss/ressort/Wirtschaft'),
|
||||
# (u'Fussball', u'http:/www.noz.de/rss/ressort/Fußball'),
|
||||
# (u'VfL Osnabrueck', u'http://www.noz.de/rss/ressort/VfL%20Osnabr%C3%BCck'),
|
||||
# (u'SF Lotte', u'http://www.noz.de/rss/ressort/SF%20Lotte'),
|
||||
# (u'SV Meppen', u'http://www.noz.de/rss/ressort/SV%20Meppen'),
|
||||
# (u'Artland Dragons', u'http://www.noz.de/rss/ressort/Artland%20Dragons'),
|
||||
# (u'Panthers', u'http://www.noz.de/rss/ressort/Panthers'),
|
||||
# (u'OS-Sport', u'http://www.noz.de/rss/ressort/OS-Sport'),
|
||||
# (u'Emsland Sport', u'http://www.noz.de/rss/ressort/EL-Sport'),
|
||||
# (u'Lingen', u'http://www.noz.de/rss/ressort/Lingen'),
|
||||
# (u'Lohne', u'http://www.noz.de/rss/ressort/Lohne'),
|
||||
# (u'Emsbueren', u'http://www.noz.de/rss/ressort/Emsb%C3%BCren'),
|
||||
# (u'Salzbergen', u'http://www.noz.de/rss/ressort/Salzbergen'),
|
||||
# (u'Spelle', u'http://www.noz.de/rss/ressort/Spelle'),
|
||||
# (u'Freren', u'http://www.noz.de/rss/ressort/Freren'),
|
||||
# (u'Lengerich', u'http://www.noz.de/rss/ressort/Lengerich'),
|
||||
# (u'Bad Iburg', u'http://www.noz.de/rss/ressort/Bad%20Iburg'),
|
||||
# (u'Bad Laer', u'http://www.noz.de/rss/ressort/Bad%20Laer'),
|
||||
# (u'Bad Rothenfelde', u'http://www.noz.de/rss/ressort/Bad%20Rothenfelde'),
|
||||
# (u'GMHütte', u'http://www.noz.de/rss/ressort/Georgsmarienh%C3%BCtte'),
|
||||
# (u'Glandorf', u'http://www.noz.de/rss/ressort/Glandorf'),
|
||||
# (u'Hagen', u'http://www.noz.de/rss/ressort/Hagen'),
|
||||
# (u'Hasbergen', u'http://www.noz.de/rss/ressort/Hasbergen'),
|
||||
# (u'Hilter', u'http://www.noz.de/rss/ressort/Hilter'),
|
||||
# (u'Lotte', u'http://www.noz.de/rss/ressort/Lotte'),
|
||||
# (u'Wallenhorst', u'http://www.noz.de/rss/ressort/Wallenhorst'),
|
||||
# (u'Westerkappeln', u'http://www.noz.de/rss/ressort/Westerkappeln'),
|
||||
# (u'Artland', u'http://www.noz.de/rss/ressort/Artland'),
|
||||
# (u'Bersenbrück', u'http://www.noz.de/rss/ressort/Bersenbr%C3%BCck'),
|
||||
# (u'Fürstenau', u'http://www.noz.de/rss/ressort/F%C3%BCrstenau'),
|
||||
# (u'Neuenkirchen', u'http://www.noz.de/rss/ressort/Neuenkirchen'),
|
||||
# (u'Lokalsport', u'http://www.noz.de/rss/ressort/Lokalsport%20Nordkreis'),
|
||||
(u'Bramsche', u'http://www.noz.de/rss/ressort/Bramsche'),
|
||||
(u'Bramsche Ortsteile',
|
||||
u'http://www.noz.de/rss/ressort/Bramscher%20Ortsteile'),
|
||||
# (u'Neuenkirchen Vörden', u'http://www.noz.de/rss/ressort/Neuenkirchen-V%C3%B6rden'),
|
||||
# (u'Papenburg', u'http://www.noz.de/rss/ressort/Papenburg'),
|
||||
# (u'Dörpen', u'http://www.noz.de/rss/ressort/D%C3%B6rpen'),
|
||||
# (u'Rhede', u'http://www.noz.de/rss/ressort/Rhede'),
|
||||
# (u'Lathen', u'http://www.noz.de/rss/ressort/Lathen'),
|
||||
# (u'Sögel', u'http://www.noz.de/rss/ressort/S%C3%B6gel'),
|
||||
# (u'Nordhümmling', u'http://www.noz.de/rss/ressort/Nordh%C3%BCmmling'),
|
||||
# (u'Werlte', u'http://www.noz.de/rss/ressort/Werlte'),
|
||||
# (u'Westoverledingen', u'http://www.noz.de/rss/ressort/Westoverledingen'),
|
||||
# (u'Geeste', u'http://www.noz.de/rss/ressort/Geeste'),
|
||||
# (u'Haren', u'http://www.noz.de/rss/ressort/Haren'),
|
||||
# (u'Haselünne', u'http://www.noz.de/rss/ressort/Hasel%C3%BCnne'),
|
||||
# (u'Herzlake', u'http://www.noz.de/rss/ressort/Herzlake'),
|
||||
# (u'Meppen', u'http://www.noz.de/rss/ressort/Meppen'),
|
||||
# (u'Twist', u'http://www.noz.de/rss/ressort/Twist'),
|
||||
# (u'Bohmte', u'http://www.noz.de/rss/ressort/Bohmte'),
|
||||
(u'Ostercappeln', u'http://www.noz.de/rss/ressort/Ostercappeln')
|
||||
]
|
||||
@ -1,31 +1,122 @@
|
||||
#!/usr/bin/env python2
|
||||
# vim:fileencoding=utf-8
|
||||
|
||||
from __future__ import unicode_literals, division, absolute_import, print_function
|
||||
|
||||
'''
|
||||
noz.de
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class AdvancedUserRecipe1344926684(BasicNewsRecipe):
|
||||
title = u'Neue Osnabrücker Zeitung'
|
||||
__author__ = 'Krittika Goyal'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
class NeueOsnabrueckerZeitung(BasicNewsRecipe):
|
||||
title = 'Neue Osnabrücker Zeitung'
|
||||
__author__ = 'vo_he'
|
||||
description = 'RSS-Feeds von noz.de'
|
||||
publisher = 'Neue Osnabrücker Zeitung GmbH & Co. KG'
|
||||
publication_type = 'newspaper'
|
||||
language = 'de'
|
||||
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 5
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
remove_empty_feeds = True
|
||||
ignore_duplicate_articles = {'title', 'url'}
|
||||
|
||||
keep_only_tags = [dict(name='h1', attrs={'class': 'enlargeable'}), dict(name='h2', attrs={'class': 'enlargeable vorspann'}), dict(
|
||||
name='div', attrs={'id': 'largePicContainer'}), dict(name='span', attrs={'id': 'articletext'})]
|
||||
remove_tags = [dict(name='div', attrs={'id': 'retresco-title'}), dict(name='div', attrs={
|
||||
'class': 'retresco-item s1 relative'}), dict(name='a', attrs={'class': 'medium2 largeSpaceTop icon'})]
|
||||
masthead_url = 'http://www.noz.de/bundles/nozplatform/images/logos/osnabruecker-zeitung.png'
|
||||
|
||||
feeds = [(u'Lokales', u'http://www.noz.de/rss/Lokales'),
|
||||
(u'Vermischtes', u'http://www.noz.de/rss/Vermischtes'),
|
||||
(u'Politik', u'http://www.noz.de/rss/Politik'),
|
||||
(u'Wirtschaft', u'http://www.noz.de/rss/Wirtschaft'),
|
||||
(u'Kultur', u'http://www.noz.de/rss/Kultur'),
|
||||
(u'Medien', u'http://www.noz.de/rss/Medien'),
|
||||
(u'Wissenschaft', u'http://www.noz.de/rss/wissenschaft'),
|
||||
(u'Sport', u'http://www.noz.de/rss/Sport'),
|
||||
(u'Computer', u'http://www.noz.de/rss/Computer'),
|
||||
(u'Musik', u'http://www.noz.de/rss/Musik'),
|
||||
(u'Szene', u'http://www.noz.de/rss/Szene'),
|
||||
(u'Niedersachsen', u'http://www.noz.de/rss/Niedersachsen'),
|
||||
(u'Kino', u'http://www.noz.de/rss/Kino')]
|
||||
feeds = [
|
||||
('Politik', 'http://www.noz.de/rss/ressort/Politik'),
|
||||
('Wirtschaft', 'http://www.noz.de/rss/ressort/Wirtschaft'),
|
||||
('Kultur', 'http://www.noz.de/rss/ressort/Kultur'),
|
||||
('Medien', 'http://www.noz.de/rss/ressort/Medien'),
|
||||
('Gut zu wissen', 'http://www.noz.de/rss/ressort/Gut%20zu%20wissen'),
|
||||
('Vermischtes', 'http://www.noz.de/rss/ressort/Vermischtes'),
|
||||
('Sport', 'http://www.noz.de/rss/ressort/Sport'),
|
||||
('Fußball', 'http://www.noz.de/rss/ressort/Fu%C3%9Fball'),
|
||||
('Niedersachsen', 'http://www.noz.de/rss/ressort/Niedersachsen'),
|
||||
('Nordrhein-Westfalen', 'http://www.noz.de/rss/ressort/Nordrhein-Westfalen'),
|
||||
# Neue Osnabrücker Zeitung
|
||||
# ('Bad Iburg', 'http://www.noz.de/rss/ressort/Bad%20Iburg'),
|
||||
# ('Bad Laer', 'http://www.noz.de/rss/ressort/Bad%20Laer'),
|
||||
# ('Bad Rothenfelde', 'http://www.noz.de/rss/ressort/Bad%20Rothenfelde'),
|
||||
# ('Belm', 'http://www.noz.de/rss/ressort/Belm'),
|
||||
# ('Bissendorf', 'http://www.noz.de/rss/ressort/Bissendorf'),
|
||||
# ('Dissen', 'http://www.noz.de/rss/ressort/Dissen'),
|
||||
# ('GMHütte', 'http://www.noz.de/rss/ressort/Georgsmarienh%C3%BCtte'),
|
||||
# ('Glandorf', 'http://www.noz.de/rss/ressort/Glandorf'),
|
||||
# ('Hagen', 'http://www.noz.de/rss/ressort/Hagen'),
|
||||
# ('Hasbergen', 'http://www.noz.de/rss/ressort/Hasbergen'),
|
||||
# ('Hilter', 'http://www.noz.de/rss/ressort/Hilter'),
|
||||
# ('Lotte', 'http://www.noz.de/rss/ressort/Lotte'),
|
||||
# ('SF Lotte', 'http://www.noz.de/rss/ressort/SF%20Lotte'),
|
||||
# ('Osnabrück', 'http://www.noz.de/rss/ressort/Osnabr%C3%BCck'),
|
||||
# ('OS-Sport', 'http://www.noz.de/rss/ressort/OS-Sport'),
|
||||
# ('Panthers', 'http://www.noz.de/rss/ressort/Panthers'),
|
||||
# ('Wallenhorst', 'http://www.noz.de/rss/ressort/Wallenhorst'),
|
||||
# ('Westerkappeln', 'http://www.noz.de/rss/ressort/Westerkappeln'),
|
||||
# Bersenbrücker Kreisblatt
|
||||
# ('Artland', 'http://www.noz.de/rss/ressort/Samtgemeinde%20Artland'),
|
||||
# ('Artland Dragons', 'http://www.noz.de/rss/ressort/Artland%20Dragons'),
|
||||
# ('Bersenbrück', 'http://www.noz.de/rss/ressort/Samtgemeinde%20Bersenbr%C3%BCck'),
|
||||
# ('Fürstenau', 'http://www.noz.de/rss/ressort/Samtgemeinde%20F%C3%BCrstenau'),
|
||||
# ('Neuenkirchen', 'http://www.noz.de/rss/ressort/Samtgemeinde%20Neuenkirchen'),
|
||||
# Bramscher Nachrichten
|
||||
# ('Bramsche', 'http://www.noz.de/rss/ressort/Bramsche'),
|
||||
# ('Neuenkirchen-Vörden', 'http://www.noz.de/rss/ressort/Neuenkirchen-V%C3%B6rden'),
|
||||
# Delmenhorster Kreisblatt
|
||||
# ('Bremen', 'http://www.noz.de/rss/ressort/Bremen'),
|
||||
# ('Delmenhorst', 'http://www.noz.de/rss/ressort/Delmenhorst'),
|
||||
# ('Ganderkesee', 'http://www.noz.de/rss/ressort/Ganderkesee'),
|
||||
# ('Stuhr', 'http://www.noz.de/rss/ressort/Stuhr'),
|
||||
# Ems-Zeitung
|
||||
# ('Dörpen', 'http://www.noz.de/rss/ressort/D%C3%B6rpen'),
|
||||
# ('Lathen', 'http://www.noz.de/rss/ressort/Lathen'),
|
||||
# ('Nordhümmling', 'http://www.noz.de/rss/ressort/Nordh%C3%BCmmling'),
|
||||
# ('Papenburg', 'http://www.noz.de/rss/ressort/Papenburg'),
|
||||
# ('Rhede', 'http://www.noz.de/rss/ressort/Rhede'),
|
||||
# ('Sögel', 'http://www.noz.de/rss/ressort/S%C3%B6gel'),
|
||||
# ('Werlte', 'http://www.noz.de/rss/ressort/Werlte'),
|
||||
# ('Westoverledingen', 'http://www.noz.de/rss/ressort/Westoverledingen'),
|
||||
# Lingener Tagespost
|
||||
# ('Emsbueren', 'http://www.noz.de/rss/ressort/Emsb%C3%BCren'),
|
||||
# ('Freren', 'http://www.noz.de/rss/ressort/Freren'),
|
||||
# ('Lengerich', 'http://www.noz.de/rss/ressort/Lengerich'),
|
||||
# ('Lingen', 'http://www.noz.de/rss/ressort/Lingen'),
|
||||
# ('Lohne', 'http://www.noz.de/rss/ressort/Lohne'),
|
||||
# ('Salzbergen', 'http://www.noz.de/rss/ressort/Salzbergen'),
|
||||
# ('Spelle', 'http://www.noz.de/rss/ressort/Spelle'),
|
||||
# Meller Kreisblatt
|
||||
# ('Melle', 'http://www.noz.de/rss/ressort/Melle'),
|
||||
# Wittlager Kreisblatt
|
||||
# ('Bad Essen', 'http://www.noz.de/rss/ressort/Bad%20Essen'),
|
||||
# ('Bohmte', 'http://www.noz.de/rss/ressort/Bohmte'),
|
||||
# ('Ostercappeln', 'http://www.noz.de/rss/ressort/Ostercappeln'),
|
||||
# Meppener Tagespost
|
||||
# ('Geeste', 'http://www.noz.de/rss/ressort/Geeste'),
|
||||
# ('Haren', 'http://www.noz.de/rss/ressort/Haren'),
|
||||
# ('Haselünne', 'http://www.noz.de/rss/ressort/Hasel%C3%BCnne'),
|
||||
# ('Herzlake', 'http://www.noz.de/rss/ressort/Herzlake'),
|
||||
# ('Meppen', 'http://www.noz.de/rss/ressort/Meppen'),
|
||||
# ('SV Meppen', 'http://www.noz.de/rss/ressort/SV%20Meppen'),
|
||||
# ('Twist', 'http://www.noz.de/rss/ressort/Twist')
|
||||
]
|
||||
|
||||
extra_css = '''
|
||||
h2 {margin-top: 0em}
|
||||
'''
|
||||
|
||||
def print_version(self, url):
|
||||
url_split = url.split('/')
|
||||
return 'http://www.noz.de/socialmediabar/print/' + url_split[-2]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
# remove first paragraph
|
||||
paragraph = soup.find('p')
|
||||
if paragraph:
|
||||
paragraph.extract()
|
||||
else:
|
||||
self.abort_article()
|
||||
return soup
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user