mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
55 lines
1.6 KiB
Python
55 lines
1.6 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
www.tiempo.hn
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import Tag
|
|
|
|
|
|
def new_tag(soup, name, attrs=()):
|
|
impl = getattr(soup, 'new_tag', None)
|
|
if impl is not None:
|
|
return impl(name, attrs=dict(attrs))
|
|
return Tag(soup, name, attrs=attrs or None)
|
|
|
|
|
|
class ElTiempoHn(BasicNewsRecipe):
|
|
title = 'El Tiempo - Honduras'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Noticias de Honduras y mundo'
|
|
publisher = 'El Tiempo'
|
|
category = 'news, politics, Honduras'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
use_embedded_content = False
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
encoding = 'utf-8'
|
|
language = 'es_HN'
|
|
|
|
lang = 'es-HN'
|
|
direction = 'ltr'
|
|
|
|
remove_tags = [dict(name=['form', 'object', 'embed', 'base'])]
|
|
|
|
keep_only_tags = [dict(name='td', attrs={'id': 'mainbodycont'})]
|
|
|
|
feeds = [(u'Noticias', u'http://www.tiempo.hn/index.php?format=feed&type=rss')]
|
|
|
|
def preprocess_html(self, soup):
|
|
soup.html['lang'] = self.lang
|
|
soup.html['dir'] = self.direction
|
|
mlang = new_tag(soup, 'meta', [
|
|
("http-equiv", "Content-Language"), ("content", self.lang)])
|
|
mcharset = new_tag(soup, 'meta', [
|
|
("http-equiv", "Content-Type"), ("content", "text/html; charset=utf-8")])
|
|
soup.head.insert(0, mlang)
|
|
soup.head.insert(1, mcharset)
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return self.adeify_images(soup)
|