| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
__license__ = 'GPL v3' |
| 4 |
__copyright__ = '2010-2012, Darko Miletic <darko.miletic at gmail.com>, Rogelio DomÃnguez <[email protected]>' |
| 5 |
''' |
| 6 |
www.jornada.com.mx |
| 7 |
''' |
| 8 |
|
| 9 |
import re |
| 10 |
|
| 11 |
try: |
| 12 |
from urllib.parse import urlencode |
| 13 |
except ImportError: |
| 14 |
from urllib import urlencode |
| 15 |
try: |
| 16 |
from urllib.parse import parse_qs, urlparse, urlunparse |
| 17 |
except ImportError: |
| 18 |
from urlparse import parse_qs, urlparse, urlunparse |
| 19 |
from calibre import strftime |
| 20 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 21 |
|
| 22 |
|
| 23 |
class LaJornada_mx(BasicNewsRecipe): |
| 24 |
title = 'La Jornada (Mexico)' |
| 25 |
__author__ = 'Darko Miletic/Rogelio DomÃnguez' |
| 26 |
description = 'Noticias del diario mexicano La Jornada' |
| 27 |
publisher = 'DEMOS, Desarrollo de Medios, S.A. de C.V.' |
| 28 |
category = 'news, Mexico' |
| 29 |
oldest_article = 2 |
| 30 |
max_articles_per_feed = 200 |
| 31 |
no_stylesheets = True |
| 32 |
encoding = 'utf8' |
| 33 |
use_embedded_content = False |
| 34 |
language = 'es_MX' |
| 35 |
remove_empty_feeds = True |
| 36 |
cover_url = strftime('http://www.jornada.com.mx/%Y/%m/%d/portada.pdf') |
| 37 |
masthead_url = 'http://www.jornada.com.mx/v7.0/imagenes/la-jornada-trans.png' |
| 38 |
publication_type = 'newspaper' |
| 39 |
extra_css = ''' |
| 40 |
body{font-family: "Times New Roman",serif } |
| 41 |
.cabeza{font-size: xx-large; font-weight: bold } |
| 42 |
.documentFirstHeading{font-size: xx-large; font-weight: bold } |
| 43 |
.credito-articulo{font-variant: small-caps; font-weight: bold } |
| 44 |
.foto{text-align: center} |
| 45 |
.pie-foto{font-size: 0.9em} |
| 46 |
.credito{font-weight: bold; margin-left: 1em} |
| 47 |
.credito-autor{font-variant: small-caps; font-weight: bold } |
| 48 |
.credito-titulo{text-align: right} |
| 49 |
.hemero{text-align: right; font-size: 0.9em; margin-bottom: 0.5em } |
| 50 |
.loc{font-weight: bold} |
| 51 |
.carton{text-align: center} |
| 52 |
.credit{font-weight: bold} |
| 53 |
.sumario{font-weight: bold; text-align: center} |
| 54 |
.text{margin-top: 1.4em} |
| 55 |
p.inicial{display: inline; font-size: xx-large; font-weight: bold} |
| 56 |
p.s-s{display: inline; text-indent: 0} |
| 57 |
''' |
| 58 |
|
| 59 |
conversion_options = {'comment': description, 'tags': category, 'publisher': publisher, 'language': language} |
| 60 |
|
| 61 |
recipe_specific_options = { |
| 62 |
'days': { |
| 63 |
'short': 'Oldest article to download from this news source. In days ', |
| 64 |
'long': 'For example, 0.5, gives you articles from the past 12 hours', |
| 65 |
'default': str(oldest_article), |
| 66 |
} |
| 67 |
} |
| 68 |
|
| 69 |
def __init__(self, *args, **kwargs): |
| 70 |
BasicNewsRecipe.__init__(self, *args, **kwargs) |
| 71 |
d = self.recipe_specific_options.get('days') |
| 72 |
if d and isinstance(d, str): |
| 73 |
self.oldest_article = float(d) |
| 74 |
|
| 75 |
preprocess_regexps = [ |
| 76 |
( |
| 77 |
re.compile(r'<div class="inicial">(.*)</div><p class="s-s">', re.DOTALL | re.IGNORECASE), |
| 78 |
lambda match: '<p class="inicial">' + match.group(1) + '</p><p class="s-s">', |
| 79 |
) |
| 80 |
] |
| 81 |
|
| 82 |
keep_only_tags = [ |
| 83 |
dict(name='div', attrs={'class': ['documentContent', 'cabeza', 'sumarios', 'credito-articulo', 'text', 'carton']}), |
| 84 |
dict(name='div', attrs={'id': 'renderComments'}), |
| 85 |
] |
| 86 |
remove_tags = [dict(name='div', attrs={'class': ['buttonbar', 'comment-cont']})] |
| 87 |
|
| 88 |
feeds = [ |
| 89 |
('Opinion', 'http://www.jornada.com.mx/rss/opinion.xml'), |
| 90 |
('Cartones', 'http://www.jornada.com.mx/rss/cartones.xml'), |
| 91 |
('Politica', 'http://www.jornada.com.mx/rss/politica.xml'), |
| 92 |
('Economia', 'http://www.jornada.com.mx/rss/economia.xml'), |
| 93 |
('Mundo', 'http://www.jornada.com.mx/rss/mundo.xml'), |
| 94 |
('Estados', 'http://www.jornada.com.mx/rss/estados.xml'), |
| 95 |
('Capital', 'http://www.jornada.com.mx/rss/capital.xml'), |
| 96 |
('Sociedad y justicia', 'http://www.jornada.com.mx/rss/sociedad.xml'), |
| 97 |
('Ciencias', 'http://www.jornada.com.mx/rss/ciencias.xml'), |
| 98 |
('Cultura', 'http://www.jornada.com.mx/rss/cultura.xml'), |
| 99 |
('Gastronomia', 'http://www.jornada.com.mx/rss/gastronomia.xml'), |
| 100 |
('Espectaculos', 'http://www.jornada.com.mx/rss/espectaculos.xml'), |
| 101 |
('Deportes', 'http://www.jornada.com.mx/rss/deportes.xml'), |
| 102 |
('Ultimas noticias', 'http://www.jornada.com.mx/ultimas/news/RSS'), |
| 103 |
] |
| 104 |
|
| 105 |
def preprocess_html(self, soup): |
| 106 |
for item in soup.findAll(style=True): |
| 107 |
del item['style'] |
| 108 |
return soup |
| 109 |
|
| 110 |
def get_article_url(self, article): |
| 111 |
# Get link to original article URL |
| 112 |
rurl = article.get('guid', None) |
| 113 |
if not rurl: |
| 114 |
# Use the "link" attribute as failover |
| 115 |
return article.get('link', None) |
| 116 |
# Remove "partner" query param |
| 117 |
u = urlparse(rurl) |
| 118 |
query = parse_qs(u.query) |
| 119 |
query.pop('partner', None) |
| 120 |
u = u._replace(query=urlencode(query, True)) |
| 121 |
return urlunparse(u) |