La Jornada by rogeliodh

2025-07-09 03:04:10 -04:00 · 2010-08-19 21:07:54 -06:00 · 2010-08-19 21:07:54 -06:00 · e947f60154
commit e947f60154
parent f61c197194
1 changed files with 120 additions and 0 deletions
--- a/resources/recipes/la_jornada.recipe
+++ b/resources/recipes/la_jornada.recipe
@ -0,0 +1,120 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2010, Rogelio Dominguez <rogelio.dominguez at gmail.com>'
+'''
+www.jornada.unam.mx
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.ebooks.BeautifulSoup import BeautifulStoneSoup
+
+import re
+
+class LaJornada(BasicNewsRecipe):
+    title          = u'La Jornada'
+    language       = 'es'
+    oldest_article = 1
+    __author__ = 'rogeliodh'
+    max_articles_per_feed = 100
+    remove_tags    = [dict(name='div', attrs={'class':['go gui','go gui top','comment-cont',]})]
+    remove_tags_before = dict(id='article-cont')
+    remove_tags_after = dict(id='article-cont')
+    no_stylesheets = True
+    extra_css      = ' .series{ \
+                               border-bottom: 1px solid #626366; \
+                               font-weight: bold; \
+                               } \
+                       .sumario{ \
+                               font-weight: bold; \
+                               margin-top: 2em; \
+                               text-align: center \
+                               } \
+                       p.sumario{ \
+                               text-align: center \
+                               } \
+                       .sumarios{font-weight: bold} \
+                       .cabeza{	font-size: 1.5em} \
+                       .pie-foto { \
+                               text-align: justify; \
+                               font-size: 0.8em; \
+                               text-align: justify; \
+                               } \
+                        .pie-foto .credito { \
+                               font-weight: bold; \
+                               display: block \
+                               } \
+                       .credito-autor{ \
+                               margin-top: 1.5em; \
+                               padding-left: 0.6em; \
+                               border-bottom: 1px solid #626366; \
+                               font-variant: small-caps; \
+                               font-weight: bold \
+                               } \
+                       .credito-articulo{ \
+                               margin-top: 1.5em; \
+                               padding-left: 0.6em; \
+                               border-bottom: 1px solid #626366; \
+                               font-variant: small-caps; \
+                               font-weight: bold \
+                               } \
+                       .credito-titulo{text-align: right} \
+                       .hemero { \
+                               text-align: right; \
+                               font-size: 0.9em; \
+                               margin-bottom: 8px; \
+                               } \
+                       .loc    { \
+                               font-weight: bold; \
+                               } \
+                       .carton  { \
+                               text-align: center; \
+                               } \
+                       .credit { \
+                               font-weight: bold; \
+                               } \
+                              '
+
+    preprocess_regexps = [
+                         # Remove capitalized initial letter on some articles (editorial)
+    		       	 (re.compile(r'<div class="inicial">(.*)</div><p class="s-s">', re.DOTALL|re.IGNORECASE),
+        		  lambda match: match.group(1)),
+                         # Cartons section uses a class instead of a div to identify the main content. Change it.
+    		       	 (re.compile(r'class="carton"', re.DOTALL|re.IGNORECASE),
+        		  lambda match: 'id="article-cont" class="carton"'),
+                         # Remove <link rel="alternate"> as calibre has a bug (to report)
+    		       	 (re.compile(r'<link rel="alternate".*?/>', re.DOTALL|re.IGNORECASE),
+        		  lambda match: ''),
+        		 ]
+
+    INDEX          = 'http://www.jornada.unam.mx/rss/edicion.xml'
+    feeds          = [
+                     (u'Opinion','http://www.jornada.unam.mx/rss/opinion.xml'),
+                     (u'Cartones','http://www.jornada.unam.mx/rss/cartones.xml'),
+                     (u'Política','http://www.jornada.unam.mx/rss/politica.xml'),
+                     (u'Economía','http://www.jornada.unam.mx/rss/economia.xml'),
+                     (u'Mundo','http://www.jornada.unam.mx/rss/mundo.xml'),
+                     (u'Estados','http://www.jornada.unam.mx/rss/estados.xml'),
+                     (u'Capital','http://www.jornada.unam.mx/rss/capital.xml'),
+                     (u'Sociedad','http://www.jornada.unam.mx/rss/sociedad.xml'),
+                     (u'Ciencias','http://www.jornada.unam.mx/rss/ciencias.xml'),
+                     (u'Cultura','http://www.jornada.unam.mx/rss/cultura.xml'),
+                     (u'Gastronomia','http://www.jornada.unam.mx/rss/gastronomia.xml'),
+                     (u'Espectáculos','http://www.jornada.unam.mx/rss/espectaculos.xml'),
+                     (u'Deportes','http://www.jornada.unam.mx/rss/deportes.xml'),
+                     ]
+
+    def get_cover_url(self):
+        '''
+        Cover URL is http://www.jornada.unam.mx/YYYY/MM/DD/portada.pdf
+        '''
+        cover_url = None
+        soup = self.index_to_soup(self.INDEX)
+        soupstone = BeautifulStoneSoup(str(soup))
+        urlbase = str(soupstone('link')[0])
+        r= re.compile(r'.*http://www.jornada.unam.mx/([0-9]{4})/([0-9]{2})/([0-9]{2})', re.DOTALL|re.IGNORECASE)
+        m = r.match(urlbase)
+        if m:
+              cover_url = 'http://www.jornada.unam.mx/' + m.groups()[0] + '/' + m.groups()[1] + '/' + m.groups()[2] + '/portada.pdf'
+
+        return cover_url