Add recipe for elperiodicomediterraneo.com

2025-06-23 15:30:45 -04:00 · 2019-03-07 12:52:25 +01:00 · 2019-03-07 12:52:25 +01:00 · 0dc35d543d
commit 0dc35d543d
parent 59ec0ad2a7
1 changed files with 102 additions and 0 deletions
--- a/recipes/mediterraneo.recipe
+++ b/recipes/mediterraneo.recipe
@ -0,0 +1,102 @@
+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+
+__license__ = 'GPL v3'
+__copyright__ = 'benages, based on elperidicodearagon.com by desUBIKado'
+__author__ = 'benages'
+__description__ = 'Daily newspaper from Castellón'
+__version__ = 'v0.10'
+__date__ = '07, March 2019'
+'''
+elperiodicomediterraneo.com
+'''
+from calibre.web.feeds.news import BasicNewsRecipe
+
+
+class elperiodicomediterraneo(BasicNewsRecipe):
+    title = u'El Periódico Mediterráneo'
+    __author__ = u'benages'
+    description = u'Noticias desde Castellón'
+    publisher = u'elperiodicomediterraneo.com'
+    category = u'news, politics, Spain, Castellón'
+    oldest_article = 1
+    delay = 1
+    max_articles_per_feed = 100
+    no_stylesheets = True
+    use_embedded_content = False
+    language = 'es'
+    masthead_url = 'http://pdf.elperiodicomediterraneo.com/img/logotipo.gif'
+    encoding = 'iso-8859-1'
+    remove_empty_feeds = True
+    remove_javascript = True
+
+    # The index of feeds is in https://www.elperiodicomediterraneo.com/info/rss.php
+    feeds = [
+        (u'Portada', u'https://est.zetaestaticos.com/mediterraneo/rss/portada_es.xml'),
+        (u'Ultima hora', u'https://est.zetaestaticos.com/mediterraneo/rss/ultimahora_es.xml'),
+        (u'Castell\xf3n', u'https://est.zetaestaticos.com/mediterraneo/rss/2_es.xml'),
+        (u'Vila-Real', u'https://est.zetaestaticos.com/mediterraneo/rss/102_es.xml'),
+        (u'Comarcas', u'https://est.zetaestaticos.com/mediterraneo/rss/10_es.xml'),
+        (u'Comunitat', u'https://est.zetaestaticos.com/mediterraneo/rss/230_es.xml'),
+        (u'Espa\xf1a', u'https://est.zetaestaticos.com/mediterraneo/rss/3_es.xml'),
+        (u'Opini\xf3n', u'https://est.zetaestaticos.com/mediterraneo/rss/103_es.xml'),
+        (u'Internacional', u'https://est.zetaestaticos.com/mediterraneo/rss/4_es.xml'),
+        (u'Econom\xeda', u'https://est.zetaestaticos.com/mediterraneo/rss/5_es.xml'),
+        (u'Deportes', u'https://est.zetaestaticos.com/mediterraneo/rss/7_es.xml'),
+        (u'Villarreal', u'https://est.zetaestaticos.com/mediterraneo/rss/288_es.xml'),
+        (u'Castell\xf3n CF', u'https://est.zetaestaticos.com/mediterraneo/rss/319_es.xml'),        
+        (u'Sucesos', u'https://est.zetaestaticos.com/mediterraneo/rss/105_es.xml'),
+        (u'Sociedad', u'https://est.zetaestaticos.com/mediterraneo/rss/106_es.xml'),
+        (u'Espectaculos', u'https://est.zetaestaticos.com/mediterraneo/rss/107_es.xml'),
+        (u'Televisi\xf3n', u'https://est.zetaestaticos.com/mediterraneo/rss/324_es.xml'),
+    ]
+
+    remove_tags_before = dict(name='div', attrs={'class': 'Pagina'})
+    remove_tags_after = dict(name='div', attrs={'class': 'ComentariosNew'})
+
+    keep_only_tags = [dict(name='div', attrs={'class': 'Pagina'})]
+
+    remove_tags = [
+        dict(
+            name='nav',
+            attrs={'class': ['Compartir', 'HerramientasConversacion Herramientas']}
+        ),
+        dict(name='h5', attrs={'class': ['CintilloBox']}),
+        dict(
+            name='div',
+            attrs={
+                'class': [
+                    'BoxMenu BoxMenuConFoto', 'BxGalerias', 'ConStick',
+                    'HerramientasComentarioNew Herramientas', 'NumeroComentarioNew'
+                ]
+            }
+        ),
+        dict(
+            name='div',
+            attrs={
+                'class': [
+                    'BoxPestanas', 'Box', 'ColumnaDerecha',
+                    'NoticiasRelacionadasDeNoticia',
+                    'CintilloNoticiasRelacionadasDeNoticia'
+                ]
+            }
+        ),
+        dict(name='a', attrs={'class': ['IrA BotonLink']})
+    ]
+
+    # Recuperamos la portada de papel (la imagen format=1 tiene mayor resolucion)
+
+    def get_cover_url(self):
+        index = 'http://pdf.elperiodicomediterraneo.com/edicion.php'
+        soup = self.index_to_soup(index)
+        for image in soup.findAll('img', src=True):
+            if image['src'].startswith('/funciones/img-public.php?key='):
+                return 'http://pdf.elperiodicomediterraneo.com' + image['src']
+        return None
+
+    extra_css = '''
+                    h1 {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:28px;}
+                    h2 {font-family:Arial,Helvetica,sans-serif; font-style:italic;font-size:14px;color:#4D4D4D;}
+                    h3 {font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:18px;}
+                '''
+