calibre/recipes/new_scientist.recipe
2025-01-24 11:14:14 +01:00

131 lines
4.8 KiB
Python

##
# Title: New Scientist RSS recipe
# Contact: AprilHare, Darko Miletic <darko.miletic at gmail.com>
##
# License: GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html
# Copyright: 2008-2016, AprilHare, Darko Miletic <darko.miletic at gmail.com>
##
# Written: 2008
# Last Edited: Jan 2016
##
'''
01-19-2012: Added GrayScale Image conversion and Duplicant article removals
12-31-2015: Major rewrite due to massive changes in site structure
01-27-2016: Added support for series index and minor cleanup
'''
__license__ = 'GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html'
__copyright__ = '2008-2016, AprilHare, Darko Miletic <darko.miletic at gmail.com>'
__version__ = 'v0.6.1'
__date__ = '2016-01-27'
__author__ = 'Darko Miletic'
'''
newscientist.com
'''
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 NewScientist(BasicNewsRecipe):
title = 'New Scientist - Online News w. subscription'
description = 'Science news and science articles from New Scientist, based on feeds.'
language = 'en'
publisher = 'Reed Business Information Ltd.'
category = 'science news, science articles, science jobs, drugs, cancer, depression, computer software'
oldest_article = 15
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
needs_subscription = 'optional'
remove_empty_feeds = True
ignore_duplicate_articles = {'url'}
resolve_internal_links = True
remove_attributes = ['style', 'height', 'width']
masthead_url = 'https://cdn.shopify.com/s/files/1/0266/6843/3505/files/logo.svg?v=1629189295'
conversion_options = {
'comment': description,
'tags': category,
'publisher': publisher,
'language': language
}
extra_css = '''
img {display:block; margin:0 auto;}
.ArticleHeader__Category { font-size:small; color:#404040; }
.ArticleHeader__Author, .ArticleHeader__DateTimeWrapper { font-size:small; }
.ArticleHeader__Copy { font-style:italic; color:#202020; }
.ArticleImage { font-size:small; text-align:center; }
.ArticleImageCaption__Credit { font-size:smaller; }
'''
keep_only_tags = [
classes('ArticleHeader ArticleContent')
]
remove_tags = [
dict(name=['svg', 'button']),
classes('ArticleHeader__SocialWrapper AdvertWrapper ReadMoreWithImage ArticleTopics')
]
def preprocess_html(self, soup):
time = soup.find(**classes('ArticleHeader__DateTimeWrapper'))
if time:
time.name = 'div'
for img in soup.findAll('img', attrs={'data-src':True}):
img['src'] = img['data-src'].split('?')[0] + '?width=700'
for figc in soup.findAll('figcaption'):
for p in figc.findAll('p'):
p.name = 'div'
return soup
def get_article_url(self, article):
ans = BasicNewsRecipe.get_article_url(self, article)
return ans.partition('?')[0]
def print_version(self, url):
if '/video/' in url:
return None
return url
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
if self.username is not None and self.password is not None:
def is_login_form(form):
return 'action' in form.attrs and form.attrs['action'] == '/login/'
br.open('https://www.newscientist.com/login/')
br.select_form(predicate=is_login_form)
br['email'] = self.username
br['password'] = self.password
res = br.submit().read()
if b'>Your account<' not in res:
raise ValueError('Failed to log in to New Scientist, check your username and password')
return br
feeds = [
('News', 'https://www.newscientist.com/section/news/feed/'),
('Features', 'https://www.newscientist.com/section/features/feed/'),
('Physics', 'https://www.newscientist.com/subject/physics/feed/'),
('Technology', 'https://www.newscientist.com/subject/technology/feed/'),
('Space', 'https://www.newscientist.com/subject/space/feed/'),
('Life', 'https://www.newscientist.com/subject/life/feed/'),
('Earth', 'https://www.newscientist.com/subject/earth/feed/'),
('Health', 'https://www.newscientist.com/subject/health/feed/'),
('Humans', 'https://www.newscientist.com/subject/humans/feed/'),
]
def get_cover_url(self):
soup = self.index_to_soup('https://www.newscientist.com/issues/current/')
div = soup.find('div', attrs={'class':'ThisWeeksMagazineHero__CoverInfo'})
return div.find(**classes('ThisWeeksMagazineHero__ImageLink')).img['src']