calibre/recipes/lemonde_dip.recipe

78 lines
3.4 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
mondediplo.com
'''
import urllib
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class LeMondeDiplomatiqueEn(BasicNewsRecipe):
title = 'Le Monde diplomatique - English edition'
__author__ = 'Darko Miletic'
description = 'Real journalism making sense of the world around us'
publisher = 'Le Monde diplomatique'
category = 'news, politics, world'
no_stylesheets = True
oldest_article = 31
delay = 1
encoding = 'utf-8'
needs_subscription = True
masthead_url = 'http://mondediplo.com/squelettes/pics/logo-30.gif'
publication_type = 'magazine'
PREFIX = 'http://mondediplo.com/'
LOGIN = PREFIX + '2009/09/02congo'
INDEX = PREFIX + strftime('%Y/%m/')
use_embedded_content = False
language = 'en'
extra_css = ' body{font-family: "Luxi sans","Lucida sans","Lucida Grande",Lucida,"Lucida Sans Unicode",sans-serif} .surtitre{font-size: 1.2em; font-variant: small-caps; margin-bottom: 0.5em} .chapo{font-size: 1.2em; font-weight: bold; margin: 1em 0 0.5em} .texte{font-family: Georgia,"Times New Roman",serif} h1{color: #990000} .notes{border-top: 1px solid #CCCCCC; font-size: 0.9em; line-height: 1.4em} '
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
def get_browser(self):
br = BasicNewsRecipe.get_browser()
br.open(self.LOGIN)
if self.username is not None and self.password is not None:
data = urllib.urlencode({ 'login':self.username
,'pass':self.password
,'enter':'enter'
})
br.open(self.LOGIN,data)
return br
keep_only_tags =[
dict(name='div', attrs={'id':'contenu'})
, dict(name='div',attrs={'class':'notes surlignable'})
]
remove_tags = [dict(name=['object','link','script','iframe','base'])]
remove_attributes = ['height','width']
def parse_index(self):
articles = []
soup = self.index_to_soup(self.INDEX)
cnt = soup.find('div',attrs={'class':'som_num'})
for item in cnt.findAll('li'):
description = ''
feed_link = item.find('a')
desc = item.find('div',attrs={'class':'chapo'})
if desc:
description = desc.string
if feed_link and feed_link.has_key('href'):
url = self.PREFIX + feed_link['href'].partition('/../')[2]
title = self.tag_to_string(feed_link)
date = strftime(self.timefmt)
articles.append({
'title' :title
,'date' :date
,'url' :url
,'description':description
})
return [(self.title, articles)]