Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Improved Irish Times

Browse Source
This commit is contained in:
Kovid Goyal 2011-03-31 18:47:39 -06:00
parent 191d30c27e
commit cdd8c44396
1 changed files with 28 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
recipes/irish_times.recipe
View File

@ -1,5 +1,5 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = "2008, Derry FitzGerald. 2009 Modified by Ray Kinsella and David O'Callaghan" __copyright__ = "2008, Derry FitzGerald. 2009 Modified by Ray Kinsella and David O'Callaghan, 2011 Modified by Phil Burns"
''' '''
irishtimes.com irishtimes.com
''' '''
@ -9,17 +9,20 @@ from calibre.web.feeds.news import BasicNewsRecipe
class IrishTimes(BasicNewsRecipe): class IrishTimes(BasicNewsRecipe):
title = u'The Irish Times' title = u'The Irish Times'
__author__ = "Derry FitzGerald, Ray Kinsella and David O'Callaghan" encoding = 'ISO-8859-15'
__author__ = "Derry FitzGerald, Ray Kinsella, David O'Callaghan and Phil Burns"
language = 'en_IE' language = 'en_IE'
timefmt = ' (%A, %B %d, %Y)' timefmt = ' (%A, %B %d, %Y)'
oldest_article = 3
oldest_article = 1.0
max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
simultaneous_downloads= 1 simultaneous_downloads= 5
r = re.compile('.*(?P<url>http:\/\/(www.irishtimes.com)|(rss.feedsportal.com\/c)\/.*\.html?).*') r = re.compile('.*(?P<url>http:\/\/(www.irishtimes.com)|(rss.feedsportal.com\/c)\/.*\.html?).*')
remove_tags = [dict(name='div', attrs={'class':'footer'})] remove_tags = [dict(name='div', attrs={'class':'footer'})]
extra_css = '.headline {font-size: x-large;} \n .fact { padding-top: 10pt }' extra_css = 'p, div { margin: 0pt; border: 0pt; text-indent: 0.5em } .headline {font-size: large;} \n .fact { padding-top: 10pt }'
feeds = [ feeds = [
('Frontpage', 'http://www.irishtimes.com/feeds/rss/newspaper/index.rss'), ('Frontpage', 'http://www.irishtimes.com/feeds/rss/newspaper/index.rss'),
@ -30,15 +33,29 @@ class IrishTimes(BasicNewsRecipe):
('Sport', 'http://www.irishtimes.com/feeds/rss/newspaper/sport.rss'), ('Sport', 'http://www.irishtimes.com/feeds/rss/newspaper/sport.rss'),
('Opinion', 'http://www.irishtimes.com/feeds/rss/newspaper/opinion.rss'), ('Opinion', 'http://www.irishtimes.com/feeds/rss/newspaper/opinion.rss'),
('Letters', 'http://www.irishtimes.com/feeds/rss/newspaper/letters.rss'), ('Letters', 'http://www.irishtimes.com/feeds/rss/newspaper/letters.rss'),
('Magazine', 'http://www.irishtimes.com/feeds/rss/newspaper/magazine.rss'),
('Health', 'http://www.irishtimes.com/feeds/rss/newspaper/health.rss'),
('Education & Parenting', 'http://www.irishtimes.com/feeds/rss/newspaper/education.rss'),
('Motors', 'http://www.irishtimes.com/feeds/rss/newspaper/motors.rss'),
('An Teanga Bheo', 'http://www.irishtimes.com/feeds/rss/newspaper/anteangabheo.rss'),
('Commercial Property', 'http://www.irishtimes.com/feeds/rss/newspaper/commercialproperty.rss'),
('Science Today', 'http://www.irishtimes.com/feeds/rss/newspaper/sciencetoday.rss'),
('Property', 'http://www.irishtimes.com/feeds/rss/newspaper/property.rss'),
('The Tickets', 'http://www.irishtimes.com/feeds/rss/newspaper/theticket.rss'),
('Weekend', 'http://www.irishtimes.com/feeds/rss/newspaper/weekend.rss'),
('News features', 'http://www.irishtimes.com/feeds/rss/newspaper/newsfeatures.rss'),
('Obituaries', 'http://www.irishtimes.com/feeds/rss/newspaper/obituaries.rss'),
] ]
def print_version(self, url): def print_version(self, url):
if url.count('rss.feedsportal.com'): if url.count('rss.feedsportal.com'):
u = 'http://www.irishtimes.com' + \ u = url.replace('0Bhtml/story01.htm','_pf0Bhtml/story01.htm')
(((url[70:].replace('0C','/')).replace('0A','0'))).replace('0Bhtml/story01.htm','_pf.html') else:
else: u = url.replace('.html','_pf.html')
u = url.replace('.html','_pf.html') return u
return u
def get_article_url(self, article): def get_article_url(self, article):
return article.link return article.link