mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
107 lines
5.0 KiB
Plaintext
107 lines
5.0 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2008-2012, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
arstechnica.com
|
|
'''
|
|
|
|
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'
|
|
category = 'news, IT, technology'
|
|
oldest_article = 5
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
encoding = 'utf-8'
|
|
use_embedded_content = False
|
|
remove_empty_feeds = True
|
|
publication_type = 'newsportal'
|
|
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}
|
|
'''
|
|
|
|
conversion_options = {
|
|
'comments' : description
|
|
,'tags' : category
|
|
,'language' : language
|
|
,'publisher' : publisher
|
|
}
|
|
|
|
keep_only_tags = [
|
|
dict(attrs={'class':'standalone'})
|
|
,dict(attrs={'id':'article-guts'})
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name=['object','link','embed','iframe','meta'])
|
|
,dict(attrs={'class':'corner-info'})
|
|
,dict(attrs={'id': 'article-footer-wrap'})
|
|
,dict(attrs={'class': 'article-expander'})
|
|
,dict(name='nav',attrs={'class': 'subheading'})
|
|
]
|
|
remove_attributes = ['lang']
|
|
|
|
feeds = [
|
|
|
|
(u'Ars Features (All our long-form feature articles)' , u'http://feeds.arstechnica.com/arstechnica/features')
|
|
, (u'Technology Lab (Information Technology)' , u'http://feeds.arstechnica.com/arstechnica/technology-lab/')
|
|
,(u'Ministry of Innovation (Business of Technology)' , u'http://feeds.arstechnica.com/arstechnica/business')
|
|
,(u'Staff Blogs (From the Minds of Ars)' , u'http://feeds.arstechnica.com/arstechnica/staff-blogs')
|
|
,(u'Infinite Loop (Apple content)' , u'http://feeds.arstechnica.com/arstechnica/apple/')
|
|
,(u'Opposable Thumbs (Gaming content)' , u'http://feeds.arstechnica.com/arstechnica/gaming/')
|
|
,(u'Gear and Gadgets' , u'http://feeds.arstechnica.com/arstechnica/gadgets/')
|
|
,(u'Uptime (IT content)' , u'http://feeds.arstechnica.com/arstechnica/business/')
|
|
,(u'Open Ended (Open Source content)' , u'http://feeds.arstechnica.com/arstechnica/open-source/')
|
|
,(u'One Microsoft Way' , u'http://feeds.arstechnica.com/arstechnica/microsoft/')
|
|
,(u'Scientific method (Science content)' , u'http://feeds.arstechnica.com/arstechnica/science/')
|
|
,(u'Law & Disorder (Tech policy content)' , u'http://feeds.arstechnica.com/arstechnica/tech-policy/')
|
|
,(u'Risk Assessment (Security content)' , u'http://feeds.arstechnica.com/arstechnica/security/')
|
|
]
|
|
|
|
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={'id':'article-guts'})
|
|
newpos = len(texttag.contents)
|
|
self.append_page(soup2,texttag,newpos)
|
|
texttag.extract()
|
|
pager.extract()
|
|
appendtag.insert(position,texttag)
|
|
|
|
def preprocess_html(self, 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 = []
|
|
else:
|
|
str = self.tag_to_string(item)
|
|
item.replaceWith(str)
|
|
for item in soup.findAll('img'):
|
|
if 'alt' not in item:
|
|
item['alt'] = 'image'
|
|
return soup
|
|
|
|
def preprocess_raw_html(self, raw, url):
|
|
return '<html><head>'+raw[raw.find('</head>'):]
|