calibre/recipes/times_online.recipe
Kovid Goyal 567040ee1e Perform PEP8 compliance checks on the entire codebase
Some bits of PEP 8 are turned off via setup.cfg
2016-07-29 21:25:17 +05:30

97 lines
3.6 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2009-2013, Darko Miletic <darko.miletic at gmail.com>'
'''
www.thetimes.co.uk
'''
import urllib
from calibre.web.feeds.news import BasicNewsRecipe
class TimesOnline(BasicNewsRecipe):
title = 'The Times UK'
__author__ = 'Darko Miletic'
description = 'news from United Kingdom and World'
language = 'en_GB'
publisher = 'Times Newspapers Ltd'
category = 'news, politics, UK'
oldest_article = 3
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
delay = 1
needs_subscription = True
auto_cleanup = False
publication_type = 'newspaper'
masthead_url = 'http://www.thetimes.co.uk/tto/public/img/the_times_460.gif'
INDEX = 'http://www.thetimes.co.uk'
PREFIX = u'http://www.thetimes.co.uk/tto/'
extra_css = """
.f-ha{font-size: xx-large; font-weight: bold}
.f-author{font-family: Arial,Helvetica,sans-serif}
.caption{font-size: small}
body{font-family: Georgia,"Times New Roman",Times,serif}
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open('http://www.thetimes.co.uk/tto/news/')
if self.username is not None and self.password is not None:
data = urllib.urlencode({
'gotoUrl': self.INDEX, 'username': self.username, 'password': self.password
})
br.open('https://login.thetimes.co.uk/', data)
return br
remove_tags = [
dict(name=['object', 'link', 'iframe', 'base', 'meta']), dict(
attrs={'class': 'tto-counter'})
]
remove_attributes = ['lang']
keep_only_tags = [
dict(attrs={'class': 'heading'}), dict(attrs={'class': 'f-author'}), dict(
attrs={'class': ['media', 'byline-timestamp']}), dict(attrs={'id': 'bodycopy'})
]
feeds = [
(u'UK News', PREFIX + u'news/uk/?view=list'),
(u'World', PREFIX + u'news/world/?view=list'),
(u'Politics', PREFIX + u'news/politics/?view=list'),
(u'Health', PREFIX + u'health/news/?view=list'),
(u'Education', PREFIX + u'education/?view=list'),
(u'Technology', PREFIX + u'technology/?view=list'),
(u'Science', PREFIX + u'science/?view=list'),
(u'Environment', PREFIX + u'environment/?view=list'),
(u'Faith', PREFIX + u'faith/?view=list'),
(u'Opinion', PREFIX + u'opinion/?view=list'),
(u'Sport', PREFIX + u'sport/?view=list'),
(u'Business', PREFIX + u'business/?view=list'),
(u'Money', PREFIX + u'money/?view=list'),
(u'Life', PREFIX + u'life/?view=list'),
(u'Arts', PREFIX + u'arts/?view=list')
]
def parse_index(self):
totalfeeds = []
lfeeds = self.get_feeds()
for feedobj in lfeeds:
feedtitle, feedurl = feedobj
self.report_progress(0, _('Fetching feed') + ' %s...' %
(feedtitle if feedtitle else feedurl))
articles = []
soup = self.index_to_soup(feedurl)
for item in soup.findAll('td', attrs={'class': 'title'}):
atag = item.find('a')
url = self.INDEX + atag['href']
title = self.tag_to_string(atag)
articles.append({
'title': title, 'date': '', 'url': url, 'description': ''
})
totalfeeds.append((feedtitle, articles))
return totalfeeds