Recipes for Critica de la Argentina and El Cronista by Darko Miletic

src/calibre/web/feeds/recipes/__init__.py

@@ -23,7 +23,7 @@ recipe_modules = ['recipe_' + r for r in (
            'spiegel_int', 'themarketticker', 'tomshardware', 'xkcd', 'ftd', 'zdnet',
            'joelonsoftware', 'telepolis', 'common_dreams', 'nin', 'tomshardware_de',
            'pagina12', 'infobae', 'ambito', 'elargentino', 'sueddeutsche', 'the_age',
-           'laprensa', 'amspec', 'freakonomics',
+           'laprensa', 'amspec', 'freakonomics', 'criticadigital', 'elcronista',
           )]
 
 import re, imp, inspect, time, os

src/calibre/web/feeds/recipes/recipe_criticadigital.py

@@ -0,0 +1,60 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+'''
+criticadigital.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class CriticaDigital(BasicNewsRecipe):
+    title                 = 'Critica de la Argentina'
+    __author__            = 'Darko Miletic'
+    description           = 'Noticias de Argentina'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'cp1252'
+
+    html2lrf_options = [
+                          '--comment'       , description
+                        , '--category'      , 'news, Argentina'
+                        , '--publisher'     , title
+                        ]
+    
+    keep_only_tags = [
+                        dict(name='div', attrs={'class':'bloqueTitulosNoticia'})
+                       ,dict(name='div', attrs={'id':'c453-1'                 })
+                     ]
+    
+    remove_tags = [
+                     dict(name='div', attrs={'class':'box300'       })
+                    ,dict(name='div', style=True                     )
+                    ,dict(name='div', attrs={'class':'titcomentario'})
+                    ,dict(name='div', attrs={'class':'comentario'   })
+                    ,dict(name='div', attrs={'class':'paginador'    })
+                  ]
+                  
+    feeds = [
+               (u'Politica', u'http://www.criticadigital.com/herramientas/rss.php?ch=politica'        )
+              ,(u'Economia', u'http://www.criticadigital.com/herramientas/rss.php?ch=economia'        )
+              ,(u'Deportes', u'http://www.criticadigital.com/herramientas/rss.php?ch=deportes'        )
+              ,(u'Espectaculos', u'http://www.criticadigital.com/herramientas/rss.php?ch=espectaculos')
+              ,(u'Mundo', u'http://www.criticadigital.com/herramientas/rss.php?ch=mundo'              )
+              ,(u'Policiales', u'http://www.criticadigital.com/herramientas/rss.php?ch=policiales'    )
+              ,(u'Sociedad', u'http://www.criticadigital.com/herramientas/rss.php?ch=sociedad'        )
+              ,(u'Salud', u'http://www.criticadigital.com/herramientas/rss.php?ch=salud'              )
+              ,(u'Tecnologia', u'http://www.criticadigital.com/herramientas/rss.php?ch=tecnologia'    )
+              ,(u'Santa Fe', u'http://www.criticadigital.com/herramientas/rss.php?ch=santa_fe'        )
+            ]
+
+    def get_cover_url(self):
+        cover_url = None
+        index = 'http://www.criticadigital.com/impresa/'
+        soup = self.index_to_soup(index)
+        link_item = soup.find('div',attrs={'class':'tapa'})
+        if link_item:
+           cover_url = index + link_item.img['src']
+        return cover_url

src/calibre/web/feeds/recipes/recipe_elcronista.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+'''
+cronista.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class ElCronista(BasicNewsRecipe):
+    title                 = 'El Cronista'
+    __author__            = 'Darko Miletic'
+    description           = 'Noticias de Argentina'
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'cp1252'
+
+    html2lrf_options = [
+                          '--comment'       , description
+                        , '--category'      , 'news, Argentina'
+                        , '--publisher'     , title
+                        ]
+    
+    keep_only_tags = [
+                        dict(name='table', attrs={'width':'100%'             })
+                       ,dict(name='h1'   , attrs={'class':'Arialgris16normal'})
+                     ]
+
+    remove_tags = [dict(name='a', attrs={'class':'Arialazul12'})]
+                     
+    feeds = [
+               (u'Economia'                , u'http://www.cronista.com/adjuntos/8/rss/Economia_EI.xml'             )
+              ,(u'Negocios'                , u'http://www.cronista.com/adjuntos/8/rss/negocios_EI.xml'             )
+              ,(u'Ultimo momento'          , u'http://www.cronista.com/adjuntos/8/rss/ultimo_momento.xml'          )
+              ,(u'Finanzas y Mercados'     , u'http://www.cronista.com/adjuntos/8/rss/Finanzas_Mercados_EI.xml'    )
+              ,(u'Financial Times'         , u'http://www.cronista.com/adjuntos/8/rss/FT_EI.xml'                   )
+              ,(u'Opinion edicion impresa' , u'http://www.cronista.com/adjuntos/8/rss/opinion_edicion_impresa.xml' )
+              ,(u'Socialmente Responsables', u'http://www.cronista.com/adjuntos/8/rss/Socialmente_Responsables.xml')
+              ,(u'Asuntos Legales'         , u'http://www.cronista.com/adjuntos/8/rss/asuntoslegales.xml'          )
+              ,(u'IT Business'             , u'http://www.cronista.com/adjuntos/8/rss/itbusiness.xml'              )
+              ,(u'Management y RR.HH.'     , u'http://www.cronista.com/adjuntos/8/rss/management.xml'              )
+              ,(u'Inversiones Personales'  , u'http://www.cronista.com/adjuntos/8/rss/inversionespersonales.xml'   )
+            ]
+
+    def print_version(self, url):
+        main, sep, rest = url.partition('.com/notas/')
+        article_id, lsep, rrest = rest.partition('-')
+        return 'http://www.cronista.com/interior/index.php?p=imprimir_nota&idNota=' + article_id
+
+    def preprocess_html(self, soup):
+        mtag = '<meta http-equiv="Content-Type" content="text/html; charset=utf-8">'
+        soup.head.insert(0,mtag)
+        soup.head.base.extract()
+        htext = soup.find('h1',attrs={'class':'Arialgris16normal'})
+        htext.name = 'p'
+        soup.prettify()
+        return soup
+
+    def get_cover_url(self):
+        cover_url = None
+        index = 'http://www.cronista.com/contenidos/'
+        soup = self.index_to_soup(index + 'ee.html')
+        link_item = soup.find('a',attrs={'href':"javascript:Close()"})
+        if link_item:
+           cover_url = index + link_item.img['src']
+        return cover_url
+