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

Fix volksrant.nl

Browse Source
This commit is contained in:
Kovid Goyal 2010-10-10 17:38:51 -06:00
parent cd4950b98e
commit 82305c2b1b
2 changed files with 59 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
resources/content_server/browse/browse.html
View File

@ -10,14 +10,14 @@
<meta http-equiv="X-UA-Compatible" content="IE=100" />
<link rel="icon" type="image/x-icon" href="http://calibre-ebook.com/favicon.ico" />
<link rel="stylesheet" type="text/css" href="browse.css" />
<link rel="stylesheet" type="text/css" href="/static/browse/browse.css" />
<link type="text/css" href="/static/jquery_ui/css/pepper-grinder/jquery-ui-1.8.5.custom.css" rel="stylesheet" />
<script type="text/javascript" src="/static/jquery.js"></script>
<script type="text/javascript" src="/static/jquery.corner.js"></script>
<script type="text/javascript" src="/static/jquery_ui/js/jquery-ui-1.8.5.custom.min.js"></script>
<script type="text/javascript" src="browse.js"></script>
<script type="text/javascript" src="/static/browse/browse.js"></script>
<script type="text/javascript">
$(document).ready(function() {{

69
resources/recipes/volksrant.recipe
View File

@ -6,7 +6,18 @@ __license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
'''
Modified by Tony Stegall
on 10/10/10 to include function to grab print version of articles
'''
from calibre.web.feeds.news import BasicNewsRecipe
'''
added by Tony Stegall
'''
#######################################################
from calibre.ptempfile import PersistentTemporaryFile
#######################################################
class AdvancedUserRecipe1249039563(BasicNewsRecipe):
title = u'De Volkskrant'
@ -16,20 +27,54 @@ class AdvancedUserRecipe1249039563(BasicNewsRecipe):
no_stylesheets = True
language = 'nl'
keep_only_tags = [dict(name='div', attrs={'id':'leftColumnArticle'}) ]
remove_tags = [
dict(name='div',attrs={'class':'article_tools'}),
dict(name='div',attrs={'id':'article_tools'}),
dict(name='div',attrs={'class':'articletools'}),
dict(name='div',attrs={'id':'articletools'}),
dict(name='div',attrs={'id':'myOverlay'}),
dict(name='div',attrs={'id':'trackback'}),
dict(name='div',attrs={'id':'googleBanner'}),
dict(name='div',attrs={'id':'article_headlines'}),
]
extra_css = '''
body{font-family:Arial,Helvetica,sans-serif; font-size:small;}
h1{font-size:large;}
'''
'''
Change Log:
Date: 10/10/10 - Modified code to include obfuscated to get the print version
Author: Tony Stegall
'''
#######################################################################################################
temp_files = []
articles_are_obfuscated = True
feeds = [(u'Laatste Nieuws', u'http://volkskrant.nl/rss/laatstenieuws.rss'), (u'Binnenlands nieuws', u'http://volkskrant.nl/rss/nederland.rss'), (u'Buitenlands nieuws', u'http://volkskrant.nl/rss/internationaal.rss'), (u'Economisch nieuws', u'http://volkskrant.nl/rss/economie.rss'), (u'Sportnieuws', u'http://volkskrant.nl/rss/sport.rss'), (u'Kunstnieuws', u'http://volkskrant.nl/rss/kunst.rss'), (u'Wetenschapsnieuws', u'http://feeds.feedburner.com/DeVolkskrantWetenschap'), (u'Technologienieuws', u'http://feeds.feedburner.com/vkmedia')]
def get_obfuscated_article(self, url):
br = self.get_browser()
br.open(url)
try:
response = br.follow_link(url_regex='.*?(2010)(\\/)(article)(\\/)(print)(\\/)', nr = 0)
html = response.read()
except:
response = br.open(url)
html = response.read()
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write(html)
self.temp_files[-1].close()
return self.temp_files[-1].name
###############################################################################################################
feeds = [
(u'Laatste Nieuws', u'http://volkskrant.nl/rss/laatstenieuws.rss'),
(u'Binnenlands nieuws', u'http://volkskrant.nl/rss/nederland.rss'),
(u'Buitenlands nieuws', u'http://volkskrant.nl/rss/internationaal.rss'),
(u'Economisch nieuws', u'http://volkskrant.nl/rss/economie.rss'),
(u'Sportnieuws', u'http://volkskrant.nl/rss/sport.rss'),
(u'Kunstnieuws', u'http://volkskrant.nl/rss/kunst.rss'),
#both of these rss feeds link back to the main volksrant.nl url a.k.a Broken
#If someone happens to know the correct paths then they can put them in here
#(u'Wetenschapsnieuws', u'http://feeds.feedburner.com/DeVolkskrantWetenschap'),
#(u'Technologienieuws', u'http://feeds.feedburner.com/vkmedia')
]
'''
example for formating
'''
# original url: http://www.volkskrant.nl/vk/nl/2668/Buitenland/article/detail/1031493/2010/10/10/Noord-Korea-ziet-nieuwe-leider.dhtml
# print url : http://www.volkskrant.nl/vk/nl/2668/2010/article/print/detail/1031493/Noord-Korea-ziet-nieuwe-leider.dhtml