calibre/recipes/ars_technica.recipe
2020-05-09 21:55:39 +05:30

87 lines
3.6 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2008-2012, Darko Miletic <darko.miletic at gmail.com>'
'''
arstechnica.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 ArsTechnica(BasicNewsRecipe):
title = u'Ars Technica'
language = 'en'
__author__ = 'Darko Miletic, Sujata Raman, Alexis Rohou, Tom Sparks'
description = 'Ars Technica: Serving the technologist for 1.2 decades'
publisher = 'Conde Nast Publications'
oldest_article = 5
max_articles_per_feed = 100
no_stylesheets = True
encoding = 'utf-8'
use_embedded_content = False
remove_empty_feeds = True
extra_css = '''
body {font-family: Arial,sans-serif}
.heading{font-family: "Times New Roman",serif}
.byline{font-weight: bold; line-height: 1em; font-size: 0.625em; text-decoration: none}
img{display: block}
.caption-text{font-size:small; font-style:italic}
.caption-byline{font-size:small; font-style:italic; font-weight:bold}
.video, .page-numbers, .story-sidebar { display: none }
.image { display: block }
'''
keep_only_tags = [
dict(itemprop=['headline', 'description']),
classes('post-meta article-guts standalone'),
]
remove_tags = [
classes('site-header video corner-info article-expander left-column related-stories'),
dict(name=['object', 'link', 'embed', 'iframe', 'meta']),
dict(id=['social-left', 'article-footer-wrap']),
dict(name='nav', attrs={'class': 'subheading'}),
]
remove_attributes = ['lang', 'style']
# Feed are found here: http://arstechnica.com/rss-feeds/
feeds = [
('Ars Technica', 'http://feeds.arstechnica.com/arstechnica/index'),
('Features', 'http://feeds.arstechnica.com/arstechnica/features'),
('Technology Lab', 'http://feeds.arstechnica.com/arstechnica/technology-lab'),
('Gear &amp; Gadgets', 'http://feeds.arstechnica.com/arstechnica/gadgets'),
('Ministry of Innovation', 'http://feeds.arstechnica.com/arstechnica/business'),
('Risk Assessment', 'http://feeds.arstechnica.com/arstechnica/security'),
('Law &amp; Disorder', 'http://feeds.arstechnica.com/arstechnica/tech-policy'),
('Infinite Loop', 'http://feeds.arstechnica.com/arstechnica/apple'),
('Opposable Thumbs', 'http://feeds.arstechnica.com/arstechnica/gaming'),
('Scientific Method', 'http://feeds.arstechnica.com/arstechnica/science'),
('The Multiverse', 'http://feeds.arstechnica.com/arstechnica/multiverse'),
('Cars Technica', 'http://feeds.arstechnica.com/arstechnica/cars'),
('Staff', 'http://feeds.arstechnica.com/arstechnica/staff-blogs'),
('Open Source', 'http://feeds.arstechnica.com/arstechnica/open-source'),
('microsoft', 'http://feeds.arstechnica.com/arstechnica/microsoft'),
('software', 'http://feeds.arstechnica.com/arstechnica/software'),
('telecom', 'http://feeds.arstechnica.com/arstechnica/telecom'),
('Internet', 'http://feeds.arstechnica.com/arstechnica/web'),
]
recursions = 1
def is_link_wanted(self, url, tag):
return re.search(r'/[0-9]/$', url) is not None
def postprocess_html(self, soup, first_fetch):
if not first_fetch:
for x in soup.findAll(itemprop=['headline', 'description']):
x.extract()
for x in soup.findAll(**classes('post-meta')):
x.extract()
return soup