New recipes for CNET News, Business Week Magazine and Dilbert

This commit is contained in:
Kovid Goyal 2009-12-25 23:48:43 -07:00
parent cba96c724e
commit ea124d6afa
7 changed files with 135 additions and 3 deletions

View File

@ -4,11 +4,18 @@
# for important features/bug fixes.
# Also, each release can have new and improved recipes.
- version: 0.6.29
date: 2009-12-25
- version: 0.6.30
date: 2009-12-26
new features:
- title: "Update graphical toolkit to Qt 4.6 for better integration with Windows 7 and OS X Snow Leopard."
description: >
"The library calibre uses to draw its user interface, Qt, has been updated in all binary builds to
version 4.6. This provides better support for Windows 7 and OS X Snow Leopard,a s well as various
speed ups in the user interface and e-book viewer rendering. Note that calibre will still run with
Qt 4.5"
- title: "Device drivers: Support for device specific icons"
- title: "Add menu options to delete specific formats/covers from the library"
@ -23,7 +30,7 @@
- title: "Nook driver: Upload covers when sending to device. Also add Output Profile for the Nook"
- title: "Double clicking on row numbers will now open the book in the viewer"
- title: "Clicking on row numbers in the book list will now open the book in the viewer"
tickets: [4266]
- title: "Driver for the Boox reader"
@ -61,6 +68,15 @@
new recipes:
- title: Business Week Magazine
author: Darko Mieltic
- title: CNET News
author: Darko Miletic
- title: Dilbert
author: Darko Miletic
- title: Le Temps
author: Sujata Raman

Binary file not shown.

After

Width:  |  Height:  |  Size: 446 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 892 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 657 B

View File

@ -0,0 +1,38 @@
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
http://www.businessweek.com/magazine/news/articles/business_news.htm
'''
from calibre.web.feeds.news import BasicNewsRecipe
class BWmagazine(BasicNewsRecipe):
title = 'BusinessWeek Magazine'
__author__ = 'Darko Miletic'
description = 'Stay up to date with BusinessWeek magazine articles. Read news on international business, personal finances & the economy in the BusinessWeek online magazine.'
publisher = 'BusinessWeek'
category = 'news, finances, politics, USA'
oldest_article = 50
max_articles_per_feed = 100
no_stylesheets = True
encoding = 'utf-8'
use_embedded_content = False
language = 'en'
cover_url = 'http://images.businessweek.com/mz/covers/current_120x160.jpg'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = dict(name='div', attrs={'id':'storyBody'})
feeds = [(u'Articles', u'http://rss.businessweek.com/bw_rss/magazine')]
def print_version(self, url):
rurl = url.rpartition('?')[0]
return rurl.replace('.com/magazine/','.com/print/magazine/')

View File

@ -0,0 +1,37 @@
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
news.cnet.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class CnetNews(BasicNewsRecipe):
title = 'CNET News'
__author__ = 'Darko Miletic'
description = 'Tech news and business reports by CNET News. Focused on information technology, core topics include computers, hardware, software, networking, and Internet media.'
publisher = 'CNET'
category = 'news, IT, USA'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
encoding = 'cp1252'
use_embedded_content = False
language = 'en'
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
remove_tags = [
dict(name='div', attrs={'id':'tweetmemeAndFacebook'})
,dict(name='ul', attrs={'class':'contentTools'})
]
keep_only_tags = dict(name='div', attrs={'class':'txtWrap'})
feeds = [(u'News', u'http://news.cnet.com/2547-1_3-0-20.xml')]

View File

@ -0,0 +1,41 @@
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
http://www.dilbert.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class DosisDiarias(BasicNewsRecipe):
title = 'Dilbert'
__author__ = 'Darko Miletic'
description = 'Dilbert'
oldest_article = 5
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = True
encoding = 'utf-8'
publisher = 'UNITED FEATURE SYNDICATE, INC.'
category = 'comic'
language = 'en'
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
}
feeds = [(u'Dilbert', u'http://feeds.dilbert.com/DilbertDailyStrip' )]
def get_article_url(self, article):
return article.get('feedburner_origlink', None)
def preprocess_html(self, soup):
for tag in soup.findAll(name='a'):
if tag['href'].find('http://feedads') >= 0:
tag.extract()
return soup