mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
74 lines
3.4 KiB
Plaintext
74 lines
3.4 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2008-2011, Kovid Goyal <kovid at kovidgoyal.net>, Darko Miletic <darko at gmail.com>'
|
|
'''
|
|
Profile to download FAZ.NET
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class FazNet(BasicNewsRecipe):
|
|
title = 'FAZ.NET'
|
|
__author__ = 'Kovid Goyal, Darko Miletic, Armin Geller' # AGe upd. V4 2014-01-14
|
|
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 = [{'class':'FAZArtikelEinleitung'},
|
|
{'id':'ArtikelTabContent_0'}]
|
|
|
|
remove_tags_after = [dict(name='div', attrs={'class':['ArtikelFooter']})]
|
|
remove_tags = [dict(name='div', attrs={'class':['ArtikelFooter']})]
|
|
|
|
# recursions = 1 # AGe 2014-01-10
|
|
# match_regexps = [r'-p[2-9].html$'] # AGe 2014-01-10
|
|
|
|
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')
|
|
]
|
|
|
|
# AGe 2014-01-10 New for multipages
|
|
INDEX = ''
|
|
def append_page(self, soup, appendtag, position): # AGe upd 2014-01-14
|
|
pager = soup.find('a',attrs={'title':'Nächste Seite'})
|
|
if pager:
|
|
nexturl = self.INDEX + pager['href']
|
|
soup2 = self.index_to_soup(nexturl)
|
|
texttag = soup2.find('div', attrs={'class':'FAZArtikelContent'})
|
|
texttag.find('div', attrs={'class':'ArtikelFooter'}).extract()
|
|
texttag.find('div', attrs={'class':'ArtikelAbbinder'}).extract()
|
|
texttag.find('div', attrs={'class':'ArtikelKommentieren Artikelfuss GETS;tk;boxen.top-lesermeinungen;tp;content'}).extract()
|
|
texttag.find('div', attrs={'class':'Anzeige GoogleAdsBuehne'}).extract()
|
|
newpos = len(texttag.contents)
|
|
self.append_page(soup2,texttag,newpos)
|
|
texttag.extract()
|
|
pager.extract()
|
|
appendtag.insert(position,texttag)
|
|
|
|
def preprocess_html(self, soup): # AGe upd 2014-01-14
|
|
self.append_page(soup, soup.body, 3)
|
|
return self.adeify_images(soup)
|
|
|
|
def postprocess_html(self, soup, first_fetch): # AGe add 2014-01-14
|
|
for div in soup.findAll(id='ArticlePagerBottom'):
|
|
div.extract()
|
|
return soup
|