Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Buenos Aires Economico. Fixes #1653092 [Updated recipe for Buenos Aires Economico](https://bugs.launchpad.net/calibre/+bug/1653092)

Browse Source
This commit is contained in:
Kovid Goyal 2016-12-30 08:31:37 +05:30
parent 94d7bce604
commit ef16647400
1 changed files with 22 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
recipes/buenosaireseconomico.recipe
View File

@ -1,9 +1,12 @@
#!/usr/bin/env python2
# -*- mode: python -*-
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2009-2011, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2009-2016, Darko Miletic <darko.miletic at gmail.com>'
'''
www.diariobae.com
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
@ -19,41 +22,32 @@ class BsAsEconomico(BasicNewsRecipe):
use_embedded_content = False
encoding = 'utf-8'
language = 'es_AR'
cover_url = strftime(
'http://www.diariobae.com/imgs_portadas/%Y%m%d_portadasBAE.jpg')
masthead_url = 'http://www.diariobae.com/img/logo_bae.png'
masthead_url = 'http://static.cronica.com.ar/FileAccessHandler.ashx?code=635959869637084622'
remove_empty_feeds = True
publication_type = 'newspaper'
extra_css = """
body{font-family: Georgia,"Times New Roman",Times,serif}
#titulo{font-size: x-large}
#epi{font-size: small; font-style: italic; font-weight: bold}
img{display: block; margin-top: 1em}
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
'comment' : description,
'tags' : category,
'publisher': publisher,
'language' : language
}
remove_tags_before = dict(attrs={'id': 'titulo'})
remove_tags_after = dict(attrs={'id': 'autor'})
keep_only_tags = [dict(name='div', attrs={'class':'post'})]
remove_tags = [
dict(name=['meta', 'base', 'iframe', 'link', 'lang']), dict(
attrs={'id': 'barra_tw'})
]
remove_attributes = ['data-count', 'data-via']
dict(name=['meta', 'base', 'iframe', 'link', 'lang'])
,dict(attrs={'class':'pdfprnt-bottom-right'})
]
feeds = [
feeds = [(u'Articles', u'http://www.diariobae.com/feed/getfeed')]
(u'Argentina', u'http://www.diariobae.com/rss/argentina.xml'),
(u'Valores', u'http://www.diariobae.com/rss/valores.xml'),
(u'Finanzas', u'http://www.diariobae.com/rss/finanzas.xml'),
(u'Negocios', u'http://www.diariobae.com/rss/negocios.xml'),
(u'Mundo', u'http://www.diariobae.com/rss/mundo.xml'),
(u'5 dias', u'http://www.diariobae.com/rss/5dias.xml'),
(u'Espectaculos', u'http://www.diariobae.com/rss/espectaculos.xml')
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup
def get_cover_url(self):
cover = None
soup = self.index_to_soup('http://www.diariobae.com/')
tag = soup.find('a', rel='lightbox[tapa]', href=True)
if tag:
cover = tag['href']
return cover