calibre/recipes/new_scientist.recipe
Kovid Goyal c41d85d207 ...
2016-01-01 09:27:00 +05:30

138 lines
6.2 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: 2008-2010, AprilHare, Darko Miletic <darko.miletic at gmail.com>
##
## Written: 2008
## Last Edited: Dec 2015
##
'''
01-19-2012: Added GrayScale Image conversion and Duplicant article removals
12-31-2015: Major rewrite due to massive changes in site structure
'''
__license__ = 'GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html'
__copyright__ = '2008-2015, AprilHare, Darko Miletic <darko.miletic at gmail.com>'
__version__ = 'v0.6.0'
__date__ = '2015-12-31'
__author__ = 'Darko Miletic'
'''
newscientist.com
'''
import re
from calibre.utils.magick import Image
from calibre.web.feeds.news import BasicNewsRecipe
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
masthead_url = 'http://www.newscientist.com/img/misc/ns_logo.jpg'
encoding = 'utf-8'
needs_subscription = 'optional'
remove_empty_feeds = True
ignore_duplicate_articles = {'url'}
compress_news_images = True
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;}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
preprocess_regexps = [(re.compile(r'</title>.*?</head>', re.DOTALL|re.IGNORECASE),lambda match: '</title></head>')]
keep_only_tags = [dict(attrs={'class':['article-header', 'article-content']})]
remove_tags_after = dict(name='p', attrs={'class':'print-headline'})
# Whether to convert images to grayscale for eInk readers.
Convert_Grayscale = False
def is_login_form(self, form):
return "action" in form.attrs and form.attrs['action'] == "/ns-login.php"
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open('http://www.newscientist.com/')
if self.username is not None and self.password is not None:
try:
br.open('https://www.newscientist.com/login/')
br.select_form(predicate=self.is_login_form)
br['log'] = self.username
br['pwd'] = self.password
br.submit()
except:
self.log.exception('Unable to locate login form! Switching to free mode.')
return br
remove_tags = [
dict(name=['link','base','meta','iframe','object','embed'])
,dict(attrs={'class':['ad-leaderboard', 'article-topics']})
,dict(attrs={'id':'mpu-mid-article'})
]
feeds = [
(u'Latest Headlines' , u'http://feeds.newscientist.com/science-news' )
,(u'Magazine' , u'http://feeds.newscientist.com/magazine' )
,(u'Health' , u'http://feeds.newscientist.com/health' )
,(u'Life' , u'http://feeds.newscientist.com/life' )
,(u'Space' , u'http://feeds.newscientist.com/space' )
,(u'Physics and Mathematics' , u'http://feeds.newscientist.com/physics-math' )
,(u'Environment' , u'http://feeds.newscientist.com/environment' )
,(u'Science in Society' , u'http://feeds.newscientist.com/science-in-society' )
,(u'Tech' , u'http://feeds.newscientist.com/tech' )
]
def get_article_url(self, article):
articleurl = BasicNewsRecipe.get_article_url(self, article)
urlverified = self.browser.open_novisit(articleurl).geturl() # resolve redirect.
if '?' in urlverified:
pleft, ppart, pright = urlverified.rpartition('?')
urlverified = pleft
return urlverified
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'])
return cover_url
# Converts images to Gray Scale
def postprocess_html(self, soup, first):
if self.Convert_Grayscale:
#process all the images
for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
iurl = tag['src']
img = Image()
img.open(iurl)
if img < 0:
raise RuntimeError('Out of memory')
img.type = "GrayscaleType"
img.save(iurl)
return soup