Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

New recipe for MSNBC by Darko Miletic

Browse Source
This commit is contained in:
Kovid Goyal 2010-01-15 12:05:13 -07:00
parent 52907e1bde
commit 26dc5a8f2f
2 changed files with 58 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
resources/images/msnbc.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 3.3 KiB

58
resources/recipes/msnbc.recipe Normal file
View File

@ -0,0 +1,58 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
msnbc.msn.com
'''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
class MsNBC(BasicNewsRecipe):
title = 'msnbc.com'
__author__ = 'Darko Miletic'
description = 'A Fuller Spectrum of News'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf8'
publisher = 'msnbc.com'
category = 'news, USA, world'
language = 'en'
extra_css = ' body{ font-family: sans-serif } .head{font-family: serif; font-size: xx-large; font-weight: bold; color: #CC0000} .abstract{font-weight: bold} .source{font-size: small} .updateTime{font-size: small} '
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher': publisher
}
preprocess_regexps = [
(re.compile(r'</style></head>', re.DOTALL|re.IGNORECASE),lambda match: '</style>')
,(re.compile(r'<div class="head">', re.DOTALL|re.IGNORECASE),lambda match: '</head><body><div class="head">'),
]
remove_tags_before = dict(name='div', attrs={'class':'head'})
remove_tags_after = dict(name='div', attrs={'class':'copyright'})
remove_tags = [dict(name=['iframe','object','link','script','form'])]
feeds = [
(u'US News' , u'http://rss.msnbc.msn.com/id/3032524/device/rss/rss.xml' )
,(u'World News' , u'http://rss.msnbc.msn.com/id/3032506/device/rss/rss.xml' )
,(u'Politics' , u'http://rss.msnbc.msn.com/id/3032552/device/rss/rss.xml' )
,(u'Business' , u'http://rss.msnbc.msn.com/id/3032071/device/rss/rss.xml' )
,(u'Sports' , u'http://rss.nbcsports.msnbc.com/id/3032112/device/rss/rss.xml')
,(u'Entertainment' , u'http://rss.msnbc.msn.com/id/3032083/device/rss/rss.xml' )
,(u'Health' , u'http://rss.msnbc.msn.com/id/3088327/device/rss/rss.xml' )
,(u'Tech & Science', u'http://rss.msnbc.msn.com/id/3032117/device/rss/rss.xml' )
]
def print_version(self, url):
return url + 'print/1/displaymode/1098/'
def preprocess_html(self, soup):
for item in soup.head.findAll('div'):
item.extract()
return soup