mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
63 lines
2.3 KiB
Plaintext
63 lines
2.3 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = "2008, Derry FitzGerald. 2009 Modified by Ray Kinsella and David O'Callaghan, 2011 Modified by Phil Burns, 2013 Tom Scholl"
|
|
'''
|
|
irishtimes.com
|
|
'''
|
|
import urlparse
|
|
import re
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ptempfile import PersistentTemporaryFile
|
|
|
|
|
|
class IrishTimes(BasicNewsRecipe):
|
|
title = u'The Irish Times'
|
|
__author__ = "Derry FitzGerald, Ray Kinsella, David O'Callaghan and Phil Burns, Tom Scholl"
|
|
language = 'en_IE'
|
|
|
|
masthead_url = 'http://www.irishtimes.com/assets/images/generic/website/logo_theirishtimes.png'
|
|
|
|
encoding = 'utf-8'
|
|
oldest_article = 1.0
|
|
max_articles_per_feed = 100
|
|
remove_empty_feeds = True
|
|
no_stylesheets = True
|
|
temp_files = []
|
|
articles_are_obfuscated = True
|
|
|
|
feeds = [
|
|
('News', 'http://www.irishtimes.com/cmlink/the-irish-times-news-1.1319192'),
|
|
('World', 'http://www.irishtimes.com/cmlink/irishtimesworldfeed-1.1321046'),
|
|
('Politics', 'http://www.irishtimes.com/cmlink/irish-times-politics-rss-1.1315953'),
|
|
('Business', 'http://www.irishtimes.com/cmlink/the-irish-times-business-1.1319195'),
|
|
('Culture', 'http://www.irishtimes.com/cmlink/the-irish-times-culture-1.1319213'),
|
|
('Sport', 'http://www.irishtimes.com/cmlink/the-irish-times-sport-1.1319194'),
|
|
('Debate', 'http://www.irishtimes.com/cmlink/debate-1.1319211'),
|
|
('Life & Style', 'http://www.irishtimes.com/cmlink/the-irish-times-life-style-1.1319214'),
|
|
]
|
|
|
|
def get_obfuscated_article(self, url):
|
|
# Insert a pic from the original url, but use content from the print
|
|
# url
|
|
pic = None
|
|
pics = self.index_to_soup(url)
|
|
div = pics.find('div', {'class': re.compile('image-carousel')})
|
|
if div:
|
|
pic = div.img
|
|
if pic:
|
|
try:
|
|
pic['src'] = urlparse.urljoin(url, pic['src'])
|
|
pic.extract()
|
|
except:
|
|
pic = None
|
|
|
|
content = self.index_to_soup(
|
|
url + '?mode=print&ot=example.AjaxPageLayout.ot')
|
|
if pic:
|
|
content.p.insert(0, pic)
|
|
|
|
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
|
|
self.temp_files[-1].write(content.prettify())
|
|
self.temp_files[-1].close()
|
|
return self.temp_files[-1].name
|