El Pais Semanal and Axxon by Darko MIletic

This commit is contained in:
Kovid Goyal 2010-04-12 08:18:47 +05:30
parent 64f20d1a22
commit f437ddeca7
3 changed files with 120 additions and 0 deletions

Binary file not shown.

After

Width:  |  Height:  |  Size: 759 B

View File

@ -0,0 +1,64 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
axxon.com.ar
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class Axxon_news(BasicNewsRecipe):
title = 'Revista Axxon'
__author__ = 'Darko Miletic'
description = 'Axxon, Ciencia Ficcion en Bits'
publisher = 'Revista Axxon - Ciencia Ficcion'
category = 'SF, Argentina'
oldest_article = 31
delay = 1
max_articles_per_feed = 100
no_stylesheets = False
use_embedded_content = False
language = 'es'
encoding = 'utf-8'
publication_type = 'magazine'
INDEX = 'http://axxon.com.ar/rev/'
extra_css = ' body{font-family: Verdana,Arial,sans-serif} .editorial{font-family: serif} .posttitle{font-family: "Trebuchet MS","Lucida Grande",Verdana,Arial,sans-serif} .cuento{font-family: "Times New Roman", serif} .biografia{color: red; font-weight: bold; font-family: Verdana,Geneva,Arial,Helvetica,sans-serif} '
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'class':'post'})]
remove_tags = [dict(name=['object','link','iframe','embed','img'])]
remove_tags_after = [dict(attrs={'class':['editorial','correo','biografia','articulo']})]
remove_attributes = ['width','height','font','border','align']
def parse_index(self):
articles = []
soup = self.index_to_soup(self.INDEX)
for item in soup.findAll('strong'):
description = ''
title_prefix = ''
feed_link = item.find('a')
if feed_link and feed_link.has_key('href') and feed_link['href'].startswith('?p='):
url = self.INDEX + feed_link['href']
title = title_prefix + self.tag_to_string(feed_link)
date = strftime(self.timefmt)
articles.append({
'title' :title
,'date' :date
,'url' :url
,'description':description
})
return [(soup.head.title.string, articles)]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return self.adeify_images(soup)

View File

@ -0,0 +1,56 @@
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
www.elpais.com/suple/eps/
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class ElPaisSemanal(BasicNewsRecipe):
title = 'El Pais semanal'
__author__ = 'Darko Miletic'
description = 'Revista semanal de diario El Pais'
publisher = 'EL PAIS S.L.'
category = 'news, politics, Spain'
no_stylesheets = True
encoding = 'cp1252'
use_embedded_content = False
language = 'es'
publication_type = 'magazine'
masthead_url = 'http://www.elpais.com/im/tit_logo_int.gif'
index = 'http://www.elpais.com/suple/eps/'
extra_css = ' p{text-align: justify} body{ text-align: left; font-family: Georgia,"Times New Roman",Times,serif } h2{font-family: Arial,Helvetica,sans-serif} img{margin-bottom: 0.4em} '
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags=[dict(attrs={'class':['cabecera_noticia','contenido_noticia']})]
remove_attributes=['width','height']
remove_tags=[dict(name='link')]
def parse_index(self):
articles = []
soup = self.index_to_soup(self.index)
for item in soup.findAll('a',attrs={'class':['g19i003','g17r003','g17i003']}):
description = ''
title_prefix = ''
feed_link = item
if item.has_key('href'):
url = 'http://www.elpais.com' + item['href'].rpartition('/')[0]
title = title_prefix + self.tag_to_string(feed_link)
date = strftime(self.timefmt)
articles.append({
'title' :title
,'date' :date
,'url' :url
,'description':description
})
return [(soup.head.title.string, articles)]
def print_version(self, url):
return url + '?print=1'