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 FAZ.NET

Browse Source
This commit is contained in:
Kovid Goyal 2017-09-06 07:02:28 +05:30
parent e767a32d39
commit ccc3be19ac
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 60 additions and 71 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

75
recipes/faznet.recipe
View File

@ -1,15 +1,19 @@
#!/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>'
'''
Profile to download FAZ.NET
'''
from calibre.web.feeds.news import BasicNewsRecipe
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' # AGe upd. V7 2016-01-26
__author__ = 'Kovid Goyal, Darko Miletic, Armin Geller'
description = 'Frankfurter Allgemeine Zeitung'
publisher = 'Frankfurter Allgemeine Zeitung GmbH'
category = 'news, politics, Germany'
@ -21,20 +25,18 @@ class FazNet(BasicNewsRecipe):
encoding = 'utf-8'
remove_javascript = True
keep_only_tags = [
{'class': ['FAZArtikelEinleitung']},
dict(name='div', attrs={'class': 'FAZSlimHeader'}),
{'id': 'ArtikelTabContent_0'}
]
keep_only_tags = [dict(name='article', attrs={'class':'atc'})]
remove_tags_after = [dict(name='article', attrs={'class':['atc']})]
remove_tags_after = [dict(name='div', attrs={'class': ['ArtikelFooter']})]
remove_tags = [
dict(name='div', attrs={'class': ['ArtikelFooter', 'clear']}),
# AGe 2016-01-26
dict(name='div', attrs={'id': ['berndsbox', 'dertagbox']}),
dict(name='a', attrs={'title': ['Vergrößern']}), # AGe 2014-10-22
dict(name='img', attrs={'class': ['VideoCtrlIcon']}), # AGe 2014-10-22
dict(name='span', attrs={'class': ['shareAutor']}) # AGe 2014-10-22
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 = [
@ -53,36 +55,25 @@ class FazNet(BasicNewsRecipe):
('Rhein-Main', 'http://www.faz.net/aktuell/rhein-main/?rssview=1')
]
# AGe 2014-01-10 For multipages
# For multipages:
INDEX = ''
def append_page(self, soup, appendtag, position):
pager = soup.find('a', attrs={'title': 'Nächste Seite'})
pager = soup.find('li',attrs={'class':'nvg-Paginator_Item nvg-Paginator_Item-to-next-page'})
if pager:
nexturl = self.INDEX + pager['href']
nexturl = self.INDEX + pager.a['href']
soup2 = self.index_to_soup(nexturl)
texttag = soup2.find('div', attrs={'class': 'FAZArtikelContent'})
texttag = soup2.find('article', attrs={'class':'atc'})
for cls in (
'ArtikelFooter', 'ArtikelAbbinder',
'ArtikelKommentieren Artikelfuss GETS;tk;boxen.top-lesermeinungen;tp;content',
'Anzeige GoogleAdsBuehne', 'ThemenLinks', 'rechtehinweis',
'stageModule Ressortmodul Rubrikenkopf clearfix', 'VideoCtrlIcon',
'ArtikelAbbinder clearfix',
'stageModule clearfix GETS;tk;artikel.empfehlungen.weitere-artikel;tp;content',
'ThemenLinks',
): # AGe 2014-10-22
'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()
for cls in (
'berndsbox', 'dertagbox'): # AGe 2016-01-26
div = texttag.find(attrs={'id': cls})
if div is not None:
div.extract()
# AGe 2014-10-22
div = texttag.find(attrs={'title': 'Vergrößern'})
if div is not None:
div.extract()
newpos = len(texttag.contents)
self.append_page(soup2,texttag,newpos)
texttag.extract()
@ -95,10 +86,8 @@ class FazNet(BasicNewsRecipe):
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(id='ArticlePagerBottom'):
div.extract()
# AGe add 2014-10-24
for div in soup.findAll('div', attrs={'class': 'clear'}):
for div in soup.findAll('div',attrs={'class':['atc-ContainerFunctions_Navigation','atc-ContainerFunctions_Interaction ']}):
div.extract()
return soup