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

Improve Irish Times

Browse Source
This commit is contained in:
Kovid Goyal 2011-07-26 15:18:33 -06:00
parent dbbde2c494
commit 3cd3ca6acd
1 changed files with 20 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
recipes/irish_times.recipe
View File

@ -1,4 +1,4 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = "2008, Derry FitzGerald. 2009 Modified by Ray Kinsella and David O'Callaghan, 2011 Modified by Phil Burns" __copyright__ = "2008, Derry FitzGerald. 2009 Modified by Ray Kinsella and David O'Callaghan, 2011 Modified by Phil Burns"
''' '''
irishtimes.com irishtimes.com
@ -10,7 +10,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class IrishTimes(BasicNewsRecipe): class IrishTimes(BasicNewsRecipe):
title = u'The Irish Times' title = u'The Irish Times'
encoding = 'ISO-8859-15' encoding = 'ISO-8859-15'
__author__ = "Derry FitzGerald, Ray Kinsella, David O'Callaghan and Phil Burns" __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)'
@ -18,6 +18,7 @@ class IrishTimes(BasicNewsRecipe):
oldest_article = 1.0 oldest_article = 1.0
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
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'})]
@ -25,17 +26,17 @@ class IrishTimes(BasicNewsRecipe):
feeds = [ feeds = [
('Frontpage', 'http://www.irishtimes.com/feeds/rss/newspaper/index.rss'), ('Frontpage', 'http://www.irishtimes.com/feeds/rss/newspaper/index.rss'),
('Ireland', 'http://rss.feedsportal.com/c/851/f/10845/index.rss'), ('Ireland', 'http://www.irishtimes.com/feeds/rss/newspaper/ireland.rss'),
('World', 'http://rss.feedsportal.com/c/851/f/10846/index.rss'), ('World', 'http://www.irishtimes.com/feeds/rss/newspaper/world.rss'),
('Finance', 'http://rss.feedsportal.com/c/851/f/10847/index.rss'), ('Finance', 'http://www.irishtimes.com/feeds/rss/newspaper/finance.rss'),
('Features', 'http://rss.feedsportal.com/c/851/f/10848/index.rss'), ('Features', 'http://www.irishtimes.com/feeds/rss/newspaper/features.rss'),
('Sport', 'http://rss.feedsportal.com/c/851/f/10849/index.rss'), ('Sport', 'http://www.irishtimes.com/feeds/rss/newspaper/sport.rss'),
('Opinion', 'http://rss.feedsportal.com/c/851/f/10850/index.rss'), ('Opinion', 'http://www.irishtimes.com/feeds/rss/newspaper/opinion.rss'),
('Letters', 'http://rss.feedsportal.com/c/851/f/10851/index.rss'), ('Letters', 'http://www.irishtimes.com/feeds/rss/newspaper/letters.rss'),
('Magazine', 'http://www.irishtimes.com/feeds/rss/newspaper/magazine.rss'), ('Magazine', 'http://www.irishtimes.com/feeds/rss/newspaper/magazine.rss'),
('Health', 'http://rss.feedsportal.com/c/851/f/10852/index.rss'), ('Health', 'http://www.irishtimes.com/feeds/rss/newspaper/health.rss'),
('Education & Parenting', 'http://rss.feedsportal.com/c/851/f/10853/index.rss'), ('Education & Parenting', 'http://www.irishtimes.com/feeds/rss/newspaper/education.rss'),
('Motors', 'http://rss.feedsportal.com/c/851/f/10854/index.rss'), ('Motors', 'http://www.irishtimes.com/feeds/rss/newspaper/motors.rss'),
('An Teanga Bheo', 'http://www.irishtimes.com/feeds/rss/newspaper/anteangabheo.rss'), ('An Teanga Bheo', 'http://www.irishtimes.com/feeds/rss/newspaper/anteangabheo.rss'),
('Commercial Property', 'http://www.irishtimes.com/feeds/rss/newspaper/commercialproperty.rss'), ('Commercial Property', 'http://www.irishtimes.com/feeds/rss/newspaper/commercialproperty.rss'),
('Science Today', 'http://www.irishtimes.com/feeds/rss/newspaper/sciencetoday.rss'), ('Science Today', 'http://www.irishtimes.com/feeds/rss/newspaper/sciencetoday.rss'),
@ -49,10 +50,16 @@ class IrishTimes(BasicNewsRecipe):
def print_version(self, url): def print_version(self, url):
if url.count('rss.feedsportal.com'): if url.count('rss.feedsportal.com'):
u = url.replace('0Bhtml/story01.htm','_pf0Bhtml/story01.htm') #u = url.replace('0Bhtml/story01.htm','_pf0Bhtml/story01.htm')
u = url.find('irishtimes')
u = 'http://www.irishtimes.com' + url[u + 12:]
u = u.replace('0C', '/')
u = u.replace('A', '')
u = u.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