mirror of
git://github.com/kovidgoyal/calibre.git
synced 2025-12-06 08:15:41 +01:00
b54734383d
old domain still works but it will probably stop working any day, so better to use the new one
106 lines
4.6 KiB
Text
106 lines
4.6 KiB
Text
__license__ = 'GPL v3'
|
|
__copyright__ = '2010-2012, Darko Miletic <darko.miletic at gmail.com>, Rogelio Domínguez <rogelio.dominguez@gmail.com>'
|
|
'''
|
|
www.jornada.com.mx
|
|
'''
|
|
|
|
import re
|
|
try:
|
|
from urllib.parse import urlencode
|
|
except ImportError:
|
|
from urllib import urlencode
|
|
try:
|
|
from urllib.parse import urlparse, urlunparse, parse_qs
|
|
except ImportError:
|
|
from urlparse import urlparse, urlunparse, parse_qs
|
|
from calibre import strftime
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class LaJornada_mx(BasicNewsRecipe):
|
|
title = 'La Jornada (Mexico)'
|
|
__author__ = 'Darko Miletic/Rogelio Domínguez'
|
|
description = 'Noticias del diario mexicano La Jornada'
|
|
publisher = 'DEMOS, Desarrollo de Medios, S.A. de C.V.'
|
|
category = 'news, Mexico'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 200
|
|
no_stylesheets = True
|
|
encoding = 'utf8'
|
|
use_embedded_content = False
|
|
language = 'es_MX'
|
|
remove_empty_feeds = True
|
|
cover_url = strftime("http://www.jornada.com.mx/%Y/%m/%d/portada.pdf")
|
|
masthead_url = 'http://www.jornada.com.mx/v7.0/imagenes/la-jornada-trans.png'
|
|
publication_type = 'newspaper'
|
|
extra_css = """
|
|
body{font-family: "Times New Roman",serif }
|
|
.cabeza{font-size: xx-large; font-weight: bold }
|
|
.documentFirstHeading{font-size: xx-large; font-weight: bold }
|
|
.credito-articulo{font-variant: small-caps; font-weight: bold }
|
|
.foto{text-align: center}
|
|
.pie-foto{font-size: 0.9em}
|
|
.credito{font-weight: bold; margin-left: 1em}
|
|
.credito-autor{font-variant: small-caps; font-weight: bold }
|
|
.credito-titulo{text-align: right}
|
|
.hemero{text-align: right; font-size: 0.9em; margin-bottom: 0.5em }
|
|
.loc{font-weight: bold}
|
|
.carton{text-align: center}
|
|
.credit{font-weight: bold}
|
|
.sumario{font-weight: bold; text-align: center}
|
|
.text{margin-top: 1.4em}
|
|
p.inicial{display: inline; font-size: xx-large; font-weight: bold}
|
|
p.s-s{display: inline; text-indent: 0}
|
|
"""
|
|
|
|
conversion_options = {
|
|
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
|
|
}
|
|
|
|
preprocess_regexps = [
|
|
(re.compile(r'<div class="inicial">(.*)</div><p class="s-s">', re.DOTALL | re.IGNORECASE),
|
|
lambda match: '<p class="inicial">' + match.group(1) + '</p><p class="s-s">')
|
|
]
|
|
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'class': ['documentContent', 'cabeza', 'sumarios',
|
|
'credito-articulo', 'text', 'carton']}), dict(name='div', attrs={'id': 'renderComments'})
|
|
]
|
|
remove_tags = [
|
|
dict(name='div', attrs={'class': ['buttonbar', 'comment-cont']})]
|
|
|
|
feeds = [
|
|
|
|
(u'Opinion', u'http://www.jornada.com.mx/rss/opinion.xml'),
|
|
(u'Cartones', u'http://www.jornada.com.mx/rss/cartones.xml'),
|
|
(u'Politica', u'http://www.jornada.com.mx/rss/politica.xml'),
|
|
(u'Economia', u'http://www.jornada.com.mx/rss/economia.xml'),
|
|
(u'Mundo', u'http://www.jornada.com.mx/rss/mundo.xml'),
|
|
(u'Estados', u'http://www.jornada.com.mx/rss/estados.xml'),
|
|
(u'Capital', u'http://www.jornada.com.mx/rss/capital.xml'),
|
|
(u'Sociedad y justicia', u'http://www.jornada.com.mx/rss/sociedad.xml'),
|
|
(u'Ciencias', u'http://www.jornada.com.mx/rss/ciencias.xml'),
|
|
(u'Cultura', u'http://www.jornada.com.mx/rss/cultura.xml'),
|
|
(u'Gastronomia', u'http://www.jornada.com.mx/rss/gastronomia.xml'),
|
|
(u'Espectaculos', u'http://www.jornada.com.mx/rss/espectaculos.xml'),
|
|
(u'Deportes', u'http://www.jornada.com.mx/rss/deportes.xml'),
|
|
(u'Ultimas noticias', u'http://www.jornada.com.mx/ultimas/news/RSS')
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return soup
|
|
|
|
def get_article_url(self, article):
|
|
# Get link to original article URL
|
|
rurl = article.get('guid', None)
|
|
if not rurl:
|
|
# Use the "link" attribute as failover
|
|
return article.get('link', None)
|
|
# Remove "partner" query param
|
|
u = urlparse(rurl)
|
|
query = parse_qs(u.query)
|
|
query.pop('partner', None)
|
|
u = u._replace(query=urlencode(query, True))
|
|
return urlunparse(u)
|