Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 18:54:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Focus.de

Browse Source
This commit is contained in:
Kovid Goyal 2016-05-08 14:39:36 +05:30
parent 2db5e10bbd
commit 8ca3696dca
1 changed files with 52 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

92
recipes/focus_de.recipe
View File

@ -1,48 +1,60 @@
#!/usr/bin/env python2
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
'''
focus.de
'''
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1305567197(BasicNewsRecipe):
title = u'Focus (DE)'
title = 'Focus (DE)'
__author__ = 'Anonymous'
language = 'de'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
remove_javascript = True
description = 'RSS-Feeds von Focus.de'
language = 'de'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
remove_empty_feeds = True
ignore_duplicate_articles = {'title', 'url'}
feeds = [
('Politik', 'http://rss.focus.de/politik/'),
('Finanzen', 'http://rss.focus.de/finanzen/'),
('Gesundheit', 'http://rss.focus.de/gesundheit/'),
('Panorama', 'http://rss.focus.de/panorama/'),
('Digital', 'http://rss.focus.de/digital/'),
('Reisen', 'http://rss.focus.de/reisen/')
]
keep_only_tags = [
dict(name='div', attrs={'id':'article'})
]
remove_tags = [
dict(name='div', attrs={'class':['inimagebuttons',
'kolumneHead clearfix']})
]
remove_attributes = ['width', 'height']
extra_css = 'h1 {font-size: 1.6em; text-align: left; margin-top: 0em} \
h2 {font-size: 1em; text-align: left} \
.overhead {margin-bottom: 0em} \
.caption {font-size: 0.6em}'
def print_version(self, url):
return url + '?drucken=1'
keep_only_tags = [
dict(name='div', attrs={'id':['article']}) ]
remove_tags = [dict(name='div', attrs={'class':'sidebar'}),
dict(name='div', attrs={'class':'commentForm'}),
dict(name='div', attrs={'class':'comment clearfix oid-3534591 open'}),
dict(name='div', attrs={'class':'similarityBlock'}),
dict(name='div', attrs={'class':'footer'}),
dict(name='div', attrs={'class':'getMoreComments'}),
dict(name='div', attrs={'class':'moreComments'}),
dict(name='div', attrs={'class':'ads'}),
dict(name='div', attrs={'class':'articleContent'}),
]
remove_tags_after = [
dict(name='div',attrs={'class':['commentForm','title', 'actions clearfix']})
]
feeds = [ (u'Eilmeldungen', u'http://rss2.focus.de/c/32191/f/533875/index.rss'),
(u'Auto-News', u'http://rss2.focus.de/c/32191/f/443320/index.rss'),
(u'Digital-News', u'http://rss2.focus.de/c/32191/f/443315/index.rss'),
(u'Finanzen-News', u'http://rss2.focus.de/c/32191/f/443317/index.rss'),
(u'Gesundheit-News', u'http://rss2.focus.de/c/32191/f/443314/index.rss'),
(u'Immobilien-News', u'http://rss2.focus.de/c/32191/f/443318/index.rss'),
(u'Kultur-News', u'http://rss2.focus.de/c/32191/f/443321/index.rss'),
(u'Panorama-News', u'http://rss2.focus.de/c/32191/f/533877/index.rss'),
(u'Politik-News', u'http://rss2.focus.de/c/32191/f/443313/index.rss'),
(u'Reisen-News', u'http://rss2.focus.de/c/32191/f/443316/index.rss'),
(u'Sport-News', u'http://rss2.focus.de/c/32191/f/443319/index.rss'),
(u'Wissen-News', u'http://rss2.focus.de/c/32191/f/533876/index.rss'),
]
def preprocess_html(self, soup):
# remove useless references to videos
for item in soup.findAll('h2'):
if item.string:
txt = item.string.upper()
if txt.startswith('IM VIDEO:') or txt.startswith('VIDEO:'):
item.extract()
return soup