mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
130 lines
5.2 KiB
Plaintext
130 lines
5.2 KiB
Plaintext
##
|
|
# 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
|
|
'''
|
|
|
|
import re
|
|
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.'
|
|
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'}
|
|
compress_news_images = False
|
|
scale_news_images = True
|
|
resolve_internal_links = True
|
|
extra_css = """
|
|
body{font-family: "PT Serif", serif}
|
|
img{margin-bottom: 0.8em; display: block}
|
|
.quotebx{font-size: x-large; font-weight: bold; margin-right: 2em; margin-left: 2em}
|
|
.article-title,h2,h3{font-family: "Lato Black", sans-serif}
|
|
.strap{font-family: "Lato Light", sans-serif}
|
|
.quote{font-family: "Lato Black", sans-serif}
|
|
.box-out{font-family: "Lato Regular", sans-serif}
|
|
.wp-caption-text{font-family: "Lato Bold", sans-serif; font-size:x-small;}
|
|
"""
|
|
|
|
keep_only_tags = [
|
|
classes('article-header article__content')
|
|
]
|
|
|
|
remove_tags = [
|
|
classes('social__button-container')
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', attrs={'data-src': True}):
|
|
img['src'] = img['data-src']
|
|
for img in soup.findAll('img', attrs={'data-srcset': True}):
|
|
img['src'] = img['data-srcset'].split(',')[-1].strip().split()[0]
|
|
img['width'] = img['height'] = ''
|
|
return soup
|
|
|
|
def get_article_url(self, article):
|
|
ans = BasicNewsRecipe.get_article_url(self, article)
|
|
return ans.partition('?')[0]
|
|
|
|
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'>Log out<' 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):
|
|
cover_url = None
|
|
soup = self.index_to_soup(
|
|
'https://www.newscientist.com/issue/current/')
|
|
cover_item = soup.find(
|
|
'img', attrs={'class': 'issue-new-magazine-cover'})
|
|
if cover_item:
|
|
cover_url = self.image_url_processor(None, cover_item['src'])
|
|
# Configure series and issue number
|
|
issue_nr = soup.find('div', attrs={'class': 'magnavissue'})
|
|
if issue_nr:
|
|
if issue_nr.string is not None:
|
|
non_decimal = re.compile(r'[^\d.]+')
|
|
nr = non_decimal.sub('', issue_nr.string)
|
|
self.conversion_options.update({'series': 'New Scientist'})
|
|
self.conversion_options.update({'series_index': nr})
|
|
return cover_url
|