mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
110 lines
4.2 KiB
Plaintext
110 lines
4.2 KiB
Plaintext
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2010-2013, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
www.thesundaytimes.co.uk
|
|
'''
|
|
import urllib
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class TimesOnline(BasicNewsRecipe):
|
|
title = 'The Sunday 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
|
|
publication_type = 'newspaper'
|
|
masthead_url = 'http://www.thesundaytimes.co.uk/sto/public/images/logos/logo-home.gif'
|
|
INDEX = 'http://www.thesundaytimes.co.uk'
|
|
PREFIX = u'http://www.thesundaytimes.co.uk/sto/'
|
|
extra_css = """
|
|
.author-name,.authorName{font-style: italic}
|
|
.published-date,.multi-position-photo-text{font-family: Arial,Helvetica,sans-serif;
|
|
font-size: small; color: gray;
|
|
display:block; margin-bottom: 0.5em}
|
|
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.thesundaytimes.co.uk/sto/')
|
|
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': 'tools comments-parent'})
|
|
]
|
|
remove_attributes = ['lang']
|
|
keep_only_tags = [
|
|
dict(attrs={'class': 'standard-content'}
|
|
), dict(attrs={'class': 'f-author'}), dict(attrs={'id': 'bodycopy'})
|
|
]
|
|
remove_tags_after = dict(attrs={'class': 'tools_border'})
|
|
|
|
feeds = [
|
|
|
|
(u'UK News', PREFIX + u'news/uk_news/'),
|
|
(u'World', PREFIX + u'news/world_news/'),
|
|
(u'Politics', PREFIX + u'news/Politics/'),
|
|
(u'Focus', PREFIX + u'news/focus/'),
|
|
(u'Insight', PREFIX + u'news/insight/'),
|
|
(u'Ireland', PREFIX + u'news/ireland/'),
|
|
(u'Columns', PREFIX + u'comment/columns/'),
|
|
(u'Arts', PREFIX + u'culture/arts/'),
|
|
(u'Books', PREFIX + u'culture/books/'),
|
|
(u'Film and TV', PREFIX + u'culture/film_and_tv/'),
|
|
(u'Sport', PREFIX + u'sport/'),
|
|
(u'Business', PREFIX + u'business'),
|
|
(u'Money', PREFIX + u'business/money/'),
|
|
(u'Style', PREFIX + u'style/'),
|
|
(u'Travel', PREFIX + u'travel/'),
|
|
(u'Clarkson', PREFIX + u'ingear/clarkson/'),
|
|
(u'Cars', PREFIX + u'ingear/cars/'),
|
|
(u'Bikes', PREFIX + u'ingear/2_Wheels/'),
|
|
(u'Tech', PREFIX + u'ingear/Tech___Games/'),
|
|
(u'Magazine', PREFIX + u'Magazine/')
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return self.adeify_images(soup)
|
|
|
|
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 atag in soup.findAll('a', href=True):
|
|
parentName = atag.parent.name
|
|
title = self.tag_to_string(atag).strip()
|
|
if (parentName == 'h2' or parentName == 'h3') and title is not None and title != '':
|
|
url = self.INDEX + atag['href']
|
|
articles.append({
|
|
'title': title, 'date': '', 'url': url, 'description': ''
|
|
})
|
|
totalfeeds.append((feedtitle, articles))
|
|
return totalfeeds
|