mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
129 lines
5.2 KiB
Plaintext
129 lines
5.2 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
arstechnica.com
|
|
'''
|
|
|
|
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
|
|
|
|
class ArsTechnica(BasicNewsRecipe):
|
|
title = u'Ars Technica'
|
|
language = 'en'
|
|
__author__ = 'Darko Miletic, Sujata Raman, Alexis Rohou'
|
|
description = 'The art of technology'
|
|
publisher = 'Ars Technica'
|
|
category = 'news, IT, technology'
|
|
oldest_article = 5
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
encoding = 'utf-8'
|
|
use_embedded_content = False
|
|
extra_css = '''
|
|
body {font-family: Arial,Helvetica,sans-serif}
|
|
.title{text-align: left}
|
|
.byline{font-weight: bold; line-height: 1em; font-size: 0.625em; text-decoration: none}
|
|
.news-item-figure-caption-text{font-size:small; font-style:italic}
|
|
.news-item-figure-caption-byline{font-size:small; font-style:italic; font-weight:bold}
|
|
'''
|
|
ignoreEtcArticles = True # Etc feed items can be ignored, as they're not real stories
|
|
|
|
conversion_options = {
|
|
'comments' : description
|
|
,'tags' : category
|
|
,'language' : language
|
|
,'publisher' : publisher
|
|
}
|
|
|
|
|
|
#preprocess_regexps = [
|
|
# (re.compile(r'<div class="news-item-figure', re.DOTALL|re.IGNORECASE),lambda match: '<div class="news-item-figure"')
|
|
# ,(re.compile(r'</title>.*?</head>', re.DOTALL|re.IGNORECASE),lambda match: '</title></head>')
|
|
# ]
|
|
|
|
keep_only_tags = [dict(name='div', attrs={'id':['story','etc-story']})]
|
|
|
|
remove_tags = [
|
|
dict(name=['object','link','embed'])
|
|
,dict(name='div', attrs={'class':'read-more-link'})
|
|
]
|
|
#remove_attributes=['width','height']
|
|
|
|
feeds = [
|
|
(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'Chipster (Hardware content)' , u'http://feeds.arstechnica.com/arstechnica/hardware/' )
|
|
,(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'Nobel Intent (Science content)' , u'http://feeds.arstechnica.com/arstechnica/science/' )
|
|
,(u'Law & Disorder (Tech policy content)' , u'http://feeds.arstechnica.com/arstechnica/tech-policy/')
|
|
]
|
|
|
|
# This deals with multi-page stories
|
|
def append_page(self, soup, appendtag, position):
|
|
pager = soup.find('div',attrs={'class':'pager'})
|
|
if pager:
|
|
for atag in pager.findAll('a',href=True):
|
|
str = self.tag_to_string(atag)
|
|
if str.startswith('Next'):
|
|
nurl = 'http://arstechnica.com' + atag['href']
|
|
rawc = self.index_to_soup(nurl,True)
|
|
soup2 = BeautifulSoup(rawc, fromEncoding=self.encoding)
|
|
|
|
readmoretag = soup2.find('div', attrs={'class':'read-more-link'})
|
|
if readmoretag:
|
|
readmoretag.extract()
|
|
texttag = soup2.find('div', attrs={'class':'body'})
|
|
for it in texttag.findAll(style=True):
|
|
del it['style']
|
|
|
|
newpos = len(texttag.contents)
|
|
self.append_page(soup2,texttag,newpos)
|
|
texttag.extract()
|
|
pager.extract()
|
|
appendtag.insert(position,texttag)
|
|
|
|
|
|
def preprocess_html(self, soup):
|
|
# Adds line breaks near the byline (not sure why this is needed)
|
|
ftag = soup.find('div', attrs={'class':'byline'})
|
|
if ftag:
|
|
brtag = Tag(soup,'br')
|
|
brtag2 = Tag(soup,'br')
|
|
ftag.insert(4,brtag)
|
|
ftag.insert(5,brtag2)
|
|
|
|
# Remove style items
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
|
|
# Remove id
|
|
for item in soup.findAll(id=True):
|
|
del item['id']
|
|
|
|
# For some reason, links to authors don't have the domainname
|
|
a_author = soup.find('a',{'href':re.compile("^/author")})
|
|
if a_author:
|
|
a_author['href'] = 'http://arstechnica.com'+a_author['href']
|
|
|
|
# within div class news-item-figure, we need to grab images
|
|
|
|
# Deal with multi-page stories
|
|
self.append_page(soup, soup.body, 3)
|
|
|
|
return soup
|
|
|
|
def get_article_url(self, article):
|
|
# If the article title starts with Etc:, don't return it
|
|
if self.ignoreEtcArticles:
|
|
article_title = article.get('title',None)
|
|
if re.match('Etc: ',article_title) is not None:
|
|
return None
|
|
|
|
# The actual article is in a guid tag
|
|
return article.get('guid', None).rpartition('?')[0]
|
|
|