Various Spanish news sources by Gustavo Azambuja

resources/recipes/180.recipe

@@ -0,0 +1,50 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+180.com.uy
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Noticias(BasicNewsRecipe):
+    title                 = '180.com.uy'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Noticias de Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 5
+    encoding = 'utf-8'
+    remove_javascript = True
+    no_stylesheets = True
+
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    keep_only_tags = [dict(name='div', attrs={'class':'tef-md tef-md-seccion-sociedad'})]
+    remove_tags = [
+             dict(name=['object','link'])
+                  ]
+
+    remove_attributes = ['width','height', 'style', 'font', 'color']
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+           (u'Titulares', u'http://www.180.com.uy/feed.php')
+        ]
+
+    def get_cover_url(self):
+		return 'http://www.180.com.uy/tplef/img/logo.gif'
+
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+

resources/recipes/bitacora.recipe

@@ -0,0 +1,58 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+bitacora.com.uy
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class General(BasicNewsRecipe):
+    title                 = 'bitacora.com.uy'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Noticias de Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 5
+    encoding = 'iso-8859-1'
+    remove_javascript = True
+    no_stylesheets = True
+
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    keep_only_tags = [dict(id=['txt'])]
+    remove_tags = [
+             dict(name='div', attrs={'class':'tablafoot'}),
+             dict(name=['object','h4']),
+             dict(name=['object','link'])
+                  ]
+
+    remove_attributes = ['width','height', 'style', 'font', 'color']
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+           (u'Titulares', u'http://www.bitacora.com.uy/anxml.cgi?15')
+        ]
+
+    def get_cover_url(self):
+	cover_url = None
+	index = 'http://www.bitacora.com.uy'
+	soup = self.index_to_soup(index)
+	link_item = soup.find('img',attrs={'class':'imgtapa'})
+	if link_item:
+		cover_url = "http://www.bitacora.com.uy/"+link_item['src']
+	return cover_url
+
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+

resources/recipes/cosmopolitan.recipe

@@ -0,0 +1,69 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+Muy Interesante
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class General(BasicNewsRecipe):
+    title                 = 'Cosmopolitan'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Revista Cosmopolitan, Edicion Espanola'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 1
+    encoding = 'utf8'
+    remove_javascript = True
+    no_stylesheets = True
+    conversion_options = {'linearize_tables': True}
+
+    oldest_article        = 180
+    max_articles_per_feed = 100
+    keep_only_tags = [
+             dict(id=['contenido']),
+             dict(name='td', attrs={'class':['contentheading', 'txt_articulo']})
+                     ]
+    remove_tags = [
+             dict(name='div', attrs={'class':['breadcrumb', 'bloque1', 'article', 'bajo_title', 'tags_articles', 'otrosenlaces_title', 'otrosenlaces_parent', 'compartir']}),
+             dict(name='div', attrs={'id':'comment'}),
+             dict(name='table', attrs={'class':'pagenav'}),
+             dict(name=['object','link'])
+                  ]
+    remove_attributes = ['width','height', 'style', 'font', 'color']
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                img {float:left; clear:both; margin:10px}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+                  (u'Articulos', u'http://feeds.feedburner.com/cosmohispano/FSSt')
+    ]
+
+    def preprocess_html(self, soup):
+        attribs = [  'style','font','valign'
+                    ,'colspan','width','height'
+                    ,'rowspan','summary','align'
+                    ,'cellspacing','cellpadding'
+                    ,'frames','rules','border'
+                  ]
+        for item in soup.body.findAll(name=['table','td','tr','th','caption','thead','tfoot','tbody','colgroup','col']):
+            item.name = 'div'
+            for attrib in attribs:
+                if item.has_key(attrib):
+                   del item[attrib]
+        return soup
+
+    def get_cover_url(self):
+		index = 'http://www.cosmohispano.com/revista'
+		soup = self.index_to_soup(index)
+		link_item = soup.find('img',attrs={'class':'img_portada'})
+		if link_item:
+			cover_url = "http://www.cosmohispano.com"+link_item['src']
+		return cover_url

resources/recipes/el_pais_uy.recipe

@@ -0,0 +1,67 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+http://www.elpais.com.uy/
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class General(BasicNewsRecipe):
+    title                 = 'Diario El Pais'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Noticias | Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 2
+    encoding = 'iso-8859-1'
+    remove_javascript = True
+    no_stylesheets = True
+
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    keep_only_tags = [
+                      dict(name='h1'),
+                      dict(name='div', attrs={'id':'Contenido'})
+                      ]
+    remove_tags = [
+				 dict(name='div', attrs={'class':['date_text', 'comments', 'form_section', 'share_it']}),
+				 dict(name='div', attrs={'id':['relatedPosts', 'spacer', 'banner_izquierda', 'right_container']}),
+				 dict(name='p', attrs={'class':'FacebookLikeButton'}),
+				 dict(name=['object','form']),
+				 dict(name=['object','table']) ]
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+           (u'Ultimo Momento', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=umomento'),
+           (u'Editorial', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=editorial'),
+           (u'Nacional', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=nacional'),
+           (u'Internacional', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=internacional'),
+           (u'Espectaculos', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=espectaculos'),
+           (u'Deportes', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=deportes'),
+           (u'Ciudades', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=ciudades'),
+           (u'Economia', u'http://www.elpais.com.uy/formatos/rss/index.asp?seccion=economia') 
+        ]
+
+    def get_cover_url(self):
+		cover_url = None
+		index = 'http://www.elpais.com.uy'
+		soup = self.index_to_soup(index)
+		link_item = soup.find('div',attrs={'class':'boxmedio box257'})
+		print link_item
+		if link_item:
+			cover_url = 'http://www.elpais.com.uy'+link_item.img['src']
+		return cover_url
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+

resources/recipes/freeway.recipe

@@ -0,0 +1,100 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+http://freeway.com.uy
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class General(BasicNewsRecipe):
+    title                 = 'freeway.com.uy'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Revista Freeway, Montevideo, Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 1
+    encoding = 'utf8'
+    remove_javascript = True
+    no_stylesheets = True
+    conversion_options = {'linearize_tables': True}
+
+    oldest_article        = 180
+    max_articles_per_feed = 100
+    keep_only_tags = [
+             dict(id=['contenido']),
+             dict(name='a', attrs={'class':'titulo_art_ppal'}),
+             dict(name='img', attrs={'class':'recuadro'}),
+             dict(name='td', attrs={'class':'txt_art_ppal'})
+                     ]
+    remove_tags = [
+             dict(name=['object','link'])
+                  ]
+    remove_attributes = ['width','height', 'style', 'font', 'color']
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                img {float:left; clear:both; margin:10px}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+
+    def parse_index(self):
+            feeds = []
+            for title, url in [('Articulos', 'http://freeway.com.uy/revista/')]:
+               articles = self.art_parse_section(url)
+               if articles:
+                   feeds.append((title, articles))
+            return feeds
+
+    def art_parse_section(self, url):
+            soup = self.index_to_soup(url)
+            div = soup.find(attrs={'id': 'tbl_1'})
+
+            current_articles = []
+            for tag in div.findAllNext(attrs = {'class': 'ancho_articulos'}):
+                if tag.get('class') == 'link-list-heading':
+                    break
+                for td in tag.findAll('td'):
+                    a = td.find('a', attrs= {'class': 'titulo_articulos'})
+                    if a is None:
+                        continue
+                    title = self.tag_to_string(a)
+                    url = a.get('href', False)
+                    if not url or not title:
+                        continue
+                    if url.startswith('/'):
+                         url = 'http://freeway.com.uy'+url
+                    p = td.find('p', attrs= {'class': 'txt_articulos'})
+                    description = self.tag_to_string(p)
+                    self.log('\t\tFound article:', title)
+                    self.log('\t\t\t', url)
+                    self.log('\t\t\t', description)
+                    current_articles.append({'title': title, 'url': url, 'description':description, 'date':''})
+
+            return current_articles
+
+    def preprocess_html(self, soup):
+        attribs = [  'style','font','valign'
+                    ,'colspan','width','height'
+                    ,'rowspan','summary','align'
+                    ,'cellspacing','cellpadding'
+                    ,'frames','rules','border'
+                  ]
+        for item in soup.body.findAll(name=['table','td','tr','th','caption','thead','tfoot','tbody','colgroup','col']):
+            item.name = 'div'
+            for attrib in attribs:
+                if item.has_key(attrib):
+                   del item[attrib]
+        return soup
+
+    def get_cover_url(self):
+		#index = 'http://www.cosmohispano.com/revista'
+		#soup = self.index_to_soup(index)
+		#link_item = soup.find('img',attrs={'class':'img_portada'})
+		#if link_item:
+		#	cover_url = "http://www.cosmohispano.com"+link_item['src']
+		return 'http://freeway.com.uy/_upload/_n_foto_grande/noticia_1792_tapanoviembre2010.jpg'

resources/recipes/la_diaria.recipe

@@ -0,0 +1,48 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+ladiaria.com.uy
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class General(BasicNewsRecipe):
+    title                 = 'La Diaria'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Noticias de Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 5
+    encoding = 'utf8'
+    remove_javascript = True
+    no_stylesheets = True
+
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    keep_only_tags = [dict(id=['article'])]
+    remove_tags = [
+             dict(name='div', attrs={'class':['byline', 'hr', 'titlebar', 'volver-arriba-right']}),
+             dict(name='div', attrs={'id':'discussion'}),
+             dict(name=['object','link'])
+                  ]
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+           (u'Articulos', u'http://ladiaria.com/feeds/articulos')
+        ]
+
+    def get_cover_url(self):
+        return 'http://ladiaria.com/edicion/imagenportada/'
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup

resources/recipes/la_razon_bo.recipe

@@ -8,7 +8,7 @@ from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
 
 class LaRazon_Bol(BasicNewsRecipe):
-    title                 = 'La Razón - Bolivia'
+    title                 = u'La Razón - Bolivia'
     __author__            = 'Darko Miletic'
     description           = 'El diario nacional de Bolivia'
     publisher             = 'Praxsis S.R.L.'

resources/recipes/montevideo_com.recipe

@@ -0,0 +1,56 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+http://www.montevideo.com.uy
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Noticias(BasicNewsRecipe):
+    title                 = 'Montevideo COMM'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Noticias de Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 5
+    encoding = 'utf-8'
+    remove_javascript = True
+    no_stylesheets = True
+
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    keep_only_tags = [dict(id=['txt'])]
+    remove_tags = [
+             dict(name=['object','link'])
+                  ]
+
+    remove_attributes = ['width','height', 'style', 'font', 'color']
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+           (u'Destacados', u'http://www.montevideo.com.uy/anxml.aspx?58'),
+           (u'Noticias', u'http://www.montevideo.com.uy/anxml.aspx?59'),
+           (u'Tecnologia', u'http://www.montevideo.com.uy/anxml.aspx?133'),
+           (u'Tiempo Libre', u'http://www.montevideo.com.uy/anxml.aspx?60'),
+           # (u'Deportes', u'http://www.montevideo.com.uy/anxml.aspx?968'),
+           # (u'Pantallazo', u'http://www.montevideo.com.uy/anxml.aspx?1022'),
+           (u'Gastronomia', u'http://www.montevideo.com.uy/anxml.aspx?1023')
+        ]
+
+    def get_cover_url(self):
+		return 'http://sphotos.ak.fbcdn.net/hphotos-ak-snc1/hs276.snc1/10319_147339559330_147337559330_2625816_6636564_n.jpg'
+
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup
+

resources/recipes/observa_digital.recipe

@@ -0,0 +1,63 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+observa.com.uy
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Noticias(BasicNewsRecipe):
+    title                 = 'Observa Digital'
+    __author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+    description           = 'Noticias desde Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 5
+    encoding = 'utf8'
+    remove_javascript = True
+    no_stylesheets = True
+
+    oldest_article        = 2
+    max_articles_per_feed = 100
+    keep_only_tags = [dict(id=['contenido'])]
+    remove_tags = [
+             dict(name='div', attrs={'id':'contenedorVinculadas'}),
+             dict(name='p', attrs={'id':'nota_firma'}),
+             dict(name=['object','link'])
+                  ]
+
+    remove_attributes = ['width','height', 'style', 'font', 'color']
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+           (u'Actualidad', u'http://www.observa.com.uy/RSS/actualidad.xml'),
+           (u'Deportes', u'http://www.observa.com.uy/RSS/deportes.xml'),
+           (u'Vida', u'http://www.observa.com.uy/RSS/vida.xml'),
+           (u'Ciencia y Tecnologia', u'http://www.observa.com.uy/RSS/ciencia.xml')
+        ]
+
+    def get_cover_url(self):
+		cover_url = None
+		index = 'http://www.elobservador.com.uy/elobservador/nav_portada.asp?suplemento=dia'
+		soup = self.index_to_soup(index)
+		link_item = soup.find('img',attrs={'usemap':'#mapeo_imagenes'})
+		if link_item:
+			cover_url = 'http://www.elobservador.com.uy'+link_item['src'].strip()
+
+		print cover_url
+
+		return cover_url
+
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup

resources/recipes/revista_bla.recipe

@@ -0,0 +1,54 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
+'''
+http://www.revistabla.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Noticias(BasicNewsRecipe):
+    title                 = 'Revista Bla'
+    __author__            = 'Gustavo Azambuja'
+    description           = 'Moda | Uruguay'
+    language       = 'es'
+    timefmt        = '[%a, %d %b, %Y]'
+    use_embedded_content  = False
+    recursion             = 5
+    encoding = 'utf8'
+    remove_javascript = True
+    no_stylesheets = True
+
+    oldest_article        = 20
+    max_articles_per_feed = 100
+    keep_only_tags = [dict(id=['body_container'])]
+    remove_tags = [
+				 dict(name='div', attrs={'class':['date_text', 'comments', 'form_section', 'share_it']}),
+				 dict(name='div', attrs={'id':['relatedPosts', 'spacer', 'banner_izquierda', 'right_container']}),
+				 dict(name='p', attrs={'class':'FacebookLikeButton'}),
+				 dict(name=['object','link']) ]
+
+    extra_css = '''
+                h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+                h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+                h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+                p {font-family:Arial,Helvetica,sans-serif;}
+                '''
+    feeds = [
+           (u'Articulos', u'http://www.revistabla.com/feed/')
+        ]
+
+    def get_cover_url(self):
+	cover_url = None
+	index = 'http://www.revistabla.com'
+	soup = self.index_to_soup(index)
+	link_item = soup.find('div',attrs={'class':'header_right'})
+	if link_item:
+		cover_url = link_item.img['src']
+	return cover_url
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        return soup

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

@@ -61,6 +61,11 @@ def serialize_recipe(urn, recipe_class):
 
 def serialize_collection(mapping_of_recipe_classes):
     collection = E.recipe_collection()
+    '''for u, x in mapping_of_recipe_classes.items():
+        print 11111, u, repr(x.title)
+        if isinstance(x.title, str):
+            x.title.decode('ascii')
+    '''
     for urn in sorted(mapping_of_recipe_classes.keys(),
             key=lambda key: getattr(mapping_of_recipe_classes[key], 'title',
                 'zzz')):