mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
111 lines
4.8 KiB
Plaintext
111 lines
4.8 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
|
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
|
|
|
|
|
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']), dict(attrs={'class': ['post-meta', 'article-guts', 'standalone']})
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name=['object', 'link', 'embed', 'iframe', 'meta']),
|
|
dict(attrs={'class': ['video', 'corner-info', 'article-expander']}),
|
|
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 & 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 & 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'),
|
|
]
|
|
|
|
def append_page(self, soup, appendtag, position):
|
|
pager = soup.find(attrs={'class': 'numbers'})
|
|
if pager:
|
|
nexttag = pager.find(attrs={'class': 'next'})
|
|
if nexttag:
|
|
nurl = nexttag.parent['href']
|
|
rawc = self.index_to_soup(nurl, True)
|
|
soup2 = BeautifulSoup(rawc, fromEncoding=self.encoding)
|
|
texttag = soup2.find(attrs={'class': 'article-guts'})
|
|
if texttag is not None:
|
|
newpos = len(texttag.contents)
|
|
soup = self.append_page(soup2, texttag, newpos)
|
|
texttag.extract()
|
|
pager.extract()
|
|
appendtag.insert(position, texttag)
|
|
soup = BeautifulSoup(soup.renderContents().decode('utf-8'))
|
|
return soup
|
|
|
|
def preprocess_html(self, soup):
|
|
soup = self.append_page(soup, soup.body, 3)
|
|
for item in soup.findAll('a'):
|
|
limg = item.find('img')
|
|
if item.string is not None:
|
|
str = item.string
|
|
item.replaceWith(str)
|
|
else:
|
|
if limg:
|
|
item.name = 'div'
|
|
item.attrs.clear()
|
|
else:
|
|
str = self.tag_to_string(item)
|
|
item.replaceWith(str)
|
|
for div in soup.findAll('div', attrs={'class':'image', 'style':lambda x: x and 'background-image' in x}):
|
|
url = re.search(r'''url\(['"]?([^'")]+)''', div['style'])
|
|
if url is not None:
|
|
div.name = 'img'
|
|
div['src'] = url.group(1)
|
|
div['style'] = ''
|
|
return soup
|
|
|
|
def preprocess_raw_html(self, raw, url):
|
|
return '<html><head>' + raw[raw.find('</head>'):]
|