Fix #803544 (Updated recipe for Buenos Aires Economico)

recipes/buenosaireseconomico.recipe

@@ -1,72 +1,60 @@
-#!/usr/bin/env  python
-
 __license__   = 'GPL v3'
-__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2009-2011, Darko Miletic <darko.miletic at gmail.com>'
 '''
-elargentino.com
+www.diariobae.com
 '''
-
+from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
 from calibre.ebooks.BeautifulSoup import Tag
 
 class BsAsEconomico(BasicNewsRecipe):
     title                 = 'Buenos Aires Economico'
     __author__            = 'Darko Miletic'
-    description           = 'Revista Argentina'
-    publisher             = 'ElArgentino.com'
+    description           = 'Diario BAE es el diario economico-politico con mas influencia en la Argentina. Fuente de empresarios y politicos del pais y el exterior. El pozo estaria aportando en periodos breves un volumen equivalente a 800m3 diarios. Pero todavia deben efectuarse otras perforaciones adicionales.'
+    publisher             = 'Diario BAE'
     category              = 'news, politics, economy, Argentina'
     oldest_article        = 2
     max_articles_per_feed = 100
     no_stylesheets        = True
     use_embedded_content  = False
     encoding              = 'utf-8'
-    language = 'es_AR'
+    language              = 'es_AR'
+    cover_url             = strftime('http://www.diariobae.com/imgs_portadas/%Y%m%d_portadasBAE.jpg')
+    masthead_url          = 'http://www.diariobae.com/img/logo_bae.png'
+    remove_empty_feeds    = True
+    publication_type      = 'newspaper'    
+    extra_css             = """ 
+                               body{font-family: Georgia,"Times New Roman",Times,serif}
+                               #titulo{font-size: x-large}
+                               #epi{font-size: small; font-style: italic; font-weight: bold}
+                               img{display: block; margin-top: 1em}
+                            """
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
 
-    lang                  = 'es-AR'
-    direction             = 'ltr'
-    INDEX                 = 'http://www.elargentino.com/medios/121/Buenos-Aires-Economico.html'
-    extra_css             = ' .titulo{font-size: x-large; font-weight: bold} .volantaImp{font-size: small; font-weight: bold} '
-
-    html2lrf_options = [
-                          '--comment'  , description
-                        , '--category' , category
-                        , '--publisher', publisher
+    remove_tags_before= dict(attrs={'id':'titulo'})
+    remove_tags_after = dict(attrs={'id':'autor' })
+    remove_tags       = [
+                            dict(name=['meta','base','iframe','link','lang'])
+                           ,dict(attrs={'id':'barra_tw'})
                         ]
-
-    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\noverride_css=" p {text-indent: 0cm; margin-top: 0em; margin-bottom: 0.5em} "'
-
-    keep_only_tags = [dict(name='div', attrs={'class':'ContainerPop'})]
-
-    remove_tags = [dict(name='link')]
-
-    feeds = [(u'Articulos', u'http://www.elargentino.com/Highlights.aspx?ParentType=Section&ParentId=121&Content-Type=text/xml&ChannelDesc=Buenos%20Aires%20Econ%C3%B3mico')]
-
-    def print_version(self, url):
-        main, sep, article_part = url.partition('/nota-')
-        article_id, rsep, rrest = article_part.partition('-')
-        return u'http://www.elargentino.com/Impresion.aspx?Id=' + article_id
+    remove_attributes = ['data-count','data-via']
+    
+    feeds = [
+               (u'Argentina'   , u'http://www.diariobae.com/rss/argentina.xml'   )
+              ,(u'Valores'     , u'http://www.diariobae.com/rss/valores.xml'     )
+              ,(u'Finanzas'    , u'http://www.diariobae.com/rss/finanzas.xml'    )
+              ,(u'Negocios'    , u'http://www.diariobae.com/rss/negocios.xml'    )
+              ,(u'Mundo'       , u'http://www.diariobae.com/rss/mundo.xml'       )
+              ,(u'5 dias'      , u'http://www.diariobae.com/rss/5dias.xml'       )
+              ,(u'Espectaculos', u'http://www.diariobae.com/rss/espectaculos.xml')
+            ]
 
     def preprocess_html(self, soup):
         for item in soup.findAll(style=True):
             del item['style']
-        soup.html['lang'] = self.lang
-        soup.html['dir' ] = self.direction
-        mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
-        mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=utf-8")])
-        soup.head.insert(0,mlang)
-        soup.head.insert(1,mcharset)
         return soup
-
-    def get_cover_url(self):
-        cover_url = None
-        soup = self.index_to_soup(self.INDEX)
-        cover_item = soup.find('div',attrs={'class':'colder'})
-        if cover_item:
-           clean_url = self.image_url_processor(None,cover_item.div.img['src'])
-           cover_url = 'http://www.elargentino.com' + clean_url + '&height=600'
-        return cover_url
-
-    def image_url_processor(self, baseurl, url):
-        base, sep, rest = url.rpartition('?Id=')
-        img, sep2, rrest = rest.partition('&')
-        return base + sep + img