mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
108 lines
4.3 KiB
Plaintext
108 lines
4.3 KiB
Plaintext
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2010-2017, Bobby Steel <bob at xdca.com>, Darko Miletic'
|
|
'''
|
|
www.thetimes.co.uk
|
|
'''
|
|
import urllib
|
|
import html5lib
|
|
from lxml import html
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
def classes(classes):
|
|
q = frozenset(classes.split(' '))
|
|
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
|
|
|
|
|
|
class TimesOnline(BasicNewsRecipe):
|
|
title = 'The Times & Sunday Times (UK)'
|
|
__author__ = 'Bobby Steel'
|
|
description = 'news from United Kingdom and World'
|
|
language = 'en_GB'
|
|
publisher = 'Times Newspapers Ltd'
|
|
category = 'news, politics, UK'
|
|
excludeSections = ['Puzzles']
|
|
oldest_article = 1
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
encoding = 'utf-8'
|
|
delay = 1
|
|
needs_subscription = True
|
|
publication_type = 'newspaper'
|
|
INDEX = 'http://www.thetimes.co.uk/'
|
|
PREFIX = u'http://www.thetimes.co.uk'
|
|
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.thetimes.co.uk/')
|
|
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 = [
|
|
{'name': ['object', 'link', 'iframe', 'base', 'meta', 'script']},
|
|
{'attrs': {'class': ['tools comments-parent','u-hide','RelatedLinks','Tooltip','Toolbar Toolbar--bottom',
|
|
'Comments Article-container','ArticlePager','Media-caption']}},
|
|
{'attrs': {'class': lambda x: x and 'Toolbar' in x}}
|
|
]
|
|
remove_attributes = ['lang']
|
|
keep_only_tags = [
|
|
dict(attrs={'class': 'Article Article--default'}
|
|
), dict(attrs={'class': 'f-author'}), dict(attrs={'id': 'bodycopy'})
|
|
]
|
|
remove_tags_after = dict(attrs={'class': 'Article-content'})
|
|
|
|
feeds = [
|
|
(u'All News', u'http://www.thetimes.co.uk/')
|
|
]
|
|
|
|
def preprocess_raw_html(self, raw, url):
|
|
return html.tostring(html5lib.parse(raw, treebuilder='lxml', namespaceHTMLElements=False), method='html', encoding=unicode)
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return self.adeify_images(soup)
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup(self.INDEX)
|
|
totalfeeds = []
|
|
current_section = []
|
|
div = []
|
|
for div in soup.findAll('section', attrs={'data-text': True}):
|
|
current_articles = []
|
|
self.log('in section: ', div['data-text'])
|
|
current_section = div['data-text']
|
|
if current_section not in self.excludeSections:
|
|
for article in div.findAll('div', attrs={'class': 'Item-content'}):
|
|
h3 = article.find('h3')
|
|
if h3 is not None:
|
|
title = self.tag_to_string(h3)
|
|
aurl = h3.find('a')
|
|
if aurl is not None:
|
|
url = aurl['href']
|
|
if url.startswith('/'):
|
|
url = 'http://www.thetimes.co.uk' + url
|
|
desc = title
|
|
self.log('section: ', current_section, 'title: ', title, 'url: ', url, 'desc: ', desc, '\n')
|
|
current_articles.append({'title': title, 'url': url, 'description': desc})
|
|
if current_articles:
|
|
totalfeeds.append((current_section, current_articles))
|
|
return totalfeeds
|