mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
94 lines
4.3 KiB
Python
94 lines
4.3 KiB
Python
#!/usr/bin/env python2
|
|
# vim:fileencoding=utf-8
|
|
from __future__ import unicode_literals, division, absolute_import, print_function
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2008-2011, Kovid Goyal <kovid at kovidgoyal.net>, Darko Miletic <darko at gmail.com>'
|
|
|
|
|
|
class FazNet(BasicNewsRecipe):
|
|
# Version 8.0
|
|
# Update 2017-09-01
|
|
# Armin Geller
|
|
# new web page layout
|
|
|
|
title = 'FAZ.NET'
|
|
__author__ = 'Kovid Goyal, Darko Miletic, Armin Geller'
|
|
description = 'Frankfurter Allgemeine Zeitung'
|
|
publisher = 'Frankfurter Allgemeine Zeitung GmbH'
|
|
category = 'news, politics, Germany'
|
|
use_embedded_content = False
|
|
language = 'de'
|
|
|
|
max_articles_per_feed = 30
|
|
no_stylesheets = True
|
|
encoding = 'utf-8'
|
|
remove_javascript = True
|
|
|
|
keep_only_tags = [dict(name='article', attrs={'class':'atc'})]
|
|
|
|
remove_tags_after = [dict(name='article', attrs={'class':['atc']})]
|
|
|
|
remove_tags = [
|
|
dict(name='aside', attrs={'class':['atc-ContainerMore ',
|
|
'atc-ContainerMore atc-ContainerMoreOneTeaser sld-TeaserMoreOneTeaser js-slider-teaser-more'
|
|
]}),
|
|
dict(name='div', attrs={'class':['atc-ContainerSocialMedia',
|
|
'atc-ContainerFunctions_Interaction ',
|
|
'ctn-PlaceholderContent ctn-PlaceholderContent-is-in-article-medium '
|
|
]})
|
|
]
|
|
|
|
feeds = [
|
|
('FAZ.NET Aktuell', 'http://www.faz.net/aktuell/?rssview=1'),
|
|
('Politik', 'http://www.faz.net/aktuell/politik/?rssview=1'),
|
|
('Wirtschaft', 'http://www.faz.net/aktuell/wirtschaft/?rssview=1'),
|
|
('Feuilleton', 'http://www.faz.net/aktuell/feuilleton/?rssview=1'),
|
|
('Sport', 'http://www.faz.net/aktuell/sport/?rssview=1'),
|
|
('Lebensstil', 'http://www.faz.net/aktuell/lebensstil/?rssview=1'),
|
|
('Gesellschaft', 'http://www.faz.net/aktuell/gesellschaft/?rssview=1'),
|
|
('Finanzen', 'http://www.faz.net/aktuell/finanzen/?rssview=1'),
|
|
('Technik & Motor', 'http://www.faz.net/aktuell/technik-motor/?rssview=1'),
|
|
('Wissen', 'http://www.faz.net/aktuell/wissen/?rssview=1'),
|
|
('Reise', 'http://www.faz.net/aktuell/reise/?rssview=1'),
|
|
('Beruf & Chance', 'http://www.faz.net/aktuell/beruf-chance/?rssview=1'),
|
|
('Rhein-Main', 'http://www.faz.net/aktuell/rhein-main/?rssview=1')
|
|
]
|
|
|
|
# For multipages:
|
|
|
|
INDEX = ''
|
|
|
|
def append_page(self, soup, appendtag, position):
|
|
pager = soup.find('li',attrs={'class':'nvg-Paginator_Item nvg-Paginator_Item-to-next-page'})
|
|
if pager:
|
|
nexturl = self.INDEX + pager.a['href']
|
|
soup2 = self.index_to_soup(nexturl)
|
|
texttag = soup2.find('article', attrs={'class':'atc'})
|
|
for cls in (
|
|
'atc-Header',
|
|
'ctn-PlaceholderContent ctn-PlaceholderContent-is-in-article-medium ',
|
|
'ctn-PlaceholderContent ctn-PlaceholderContent-is-in-article-medium ctn-PlaceholderContent-has-centered-content ',
|
|
'atc-ContainerMore '
|
|
):
|
|
div = texttag.find(attrs={'class':cls})
|
|
if div is not None:
|
|
div.extract()
|
|
newpos = len(texttag.contents)
|
|
self.append_page(soup2,texttag,newpos)
|
|
texttag.extract()
|
|
pager.extract()
|
|
appendtag.insert(position,texttag)
|
|
|
|
def preprocess_html(self, soup):
|
|
self.append_page(soup, soup.body, 3)
|
|
for img in soup.findAll('img', attrs={'data-src':True}):
|
|
img['src'] = img['data-src']
|
|
return self.adeify_images(soup)
|
|
|
|
# Some last cleanup
|
|
def postprocess_html(self, soup, first_fetch):
|
|
for div in soup.findAll('div',attrs={'class':['atc-ContainerFunctions_Navigation','atc-ContainerFunctions_Interaction ']}):
|
|
div.extract()
|
|
return soup
|