calibre/recipes/straitstimes.recipe
2022-01-26 10:28:15 +05:30

59 lines
2.2 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.straitstimes.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class StraitsTimes(BasicNewsRecipe):
title = 'The Straits Times'
__author__ = 'Darko Miletic'
description = 'Singapore newspaper'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
publisher = 'Singapore Press Holdings Ltd.'
category = 'news, politics, singapore, asia'
language = 'en_SG'
conversion_options = {
'comments': description, 'tags': category, 'language': language, 'publisher': publisher
}
keep_only_tags = [
classes('node-header node-subheadline group-byline-info group-updated-timestamp group-image-frame field-name-body article-content-rawhtml')
]
remove_tags = [
classes('st_telegram_boilerplate dropdown-menu ads'),
dict(name='source'),
]
feeds = [
(u'World' , u'https://www.straitstimes.com/news/world/rss.xml')
,(u'Business' , u'https://www.straitstimes.com/news/business/rss.xml')
,(u'Life' , u'https://www.straitstimes.com/news/life/rss.xml')
,(u'Tech' , u'https://www.straitstimes.com/news/tech/rss.xml')
,(u'Opinion' , u'https://www.straitstimes.com/news/opinion/rss.xml')
,(u'Life' , u'https://www.straitstimes.com/news/life/rss.xml')
,(u'Singapore' , u'https://www.straitstimes.com/news/singapore/rss.xml')
,(u'Asia' , u'https://www.straitstimes.com/news/asia/rss.xml')
,(u'Multimedia' , u'https://www.straitstimes.com/news/multimedia/rss.xml')
,(u'Sport' , u'https://www.straitstimes.com/news/sport/rss.xml')
]
def preprocess_html(self, soup):
for img in soup.findAll('img', srcset=True):
img['src'] = img['srcset'].partition(' ')[0]
img['srcset'] = ''
return soup