mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
65 lines
2.7 KiB
Plaintext
65 lines
2.7 KiB
Plaintext
__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_AR'
|
|
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)
|
|
|