mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
76 lines
2.4 KiB
Python
76 lines
2.4 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
www.latribuna.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 LaTribuna(BasicNewsRecipe):
|
|
title = 'La Tribuna - Honduras'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Noticias de Honduras y mundo'
|
|
publisher = 'La Tribuna'
|
|
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'
|
|
|
|
html2lrf_options = [
|
|
'--comment', description, '--category', category, '--publisher', publisher
|
|
]
|
|
|
|
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + \
|
|
'"\npretty_print=True\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} "'
|
|
|
|
remove_tags = [dict(name=['form', 'object', 'embed'])]
|
|
|
|
keep_only_tags = [
|
|
dict(name='p', attrs={'id': ['BlogTitle', 'BlogDate']}), dict(
|
|
name='div', attrs={'id': 'BlogContent'})
|
|
]
|
|
|
|
feeds = [(u'Noticias', u'http://www.latribuna.hn/web2.0/?feed=rss')]
|
|
|
|
def print_version(self, url):
|
|
return url + '&print=1'
|
|
|
|
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 soup
|
|
|
|
def get_cover_url(self):
|
|
cover_url = None
|
|
soup = self.index_to_soup('http://www.latribuna.hn/web2.0/')
|
|
cover_item = soup.find('div', attrs={'class': 'portada_impresa'})
|
|
if cover_item:
|
|
cover_url = cover_item.a.img['src']
|
|
return cover_url
|