Recipe for La Prensa by Darko Miletic

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

@@ -23,6 +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',
           )]
 
 import re, imp, inspect, time, os

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

@@ -0,0 +1,50 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
+'''
+laprensa.com.ar
+'''
+import urllib
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class LaPrensa(BasicNewsRecipe):
+    title                 = 'La Prensa'
+    __author__            = 'Darko Miletic'
+    description           = 'Informacion Libre las 24 horas'    
+    oldest_article        = 7
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'cp1252'
+    cover_url             = 'http://www.laprensa.com.ar/imgs/logo.gif'
+
+    html2lrf_options = [
+                          '--comment'       , description
+                        , '--category'      , 'news, Argentina'
+                        , '--publisher'     , title
+                        ]
+                            
+    feeds = [ 
+              (u'Politica'    , u'http://www.laprensa.com.ar/Rss.aspx?Rss=4' )
+             ,(u'Economia'    , u'http://www.laprensa.com.ar/Rss.aspx?Rss=5' )
+             ,(u'Opinion'     , u'http://www.laprensa.com.ar/Rss.aspx?Rss=6' )
+             ,(u'El Mundo'    , u'http://www.laprensa.com.ar/Rss.aspx?Rss=7' )
+             ,(u'Actualidad'  , u'http://www.laprensa.com.ar/Rss.aspx?Rss=8' )
+             ,(u'Deportes'    , u'http://www.laprensa.com.ar/Rss.aspx?Rss=9' )
+             ,(u'Espectaculos', u'http://www.laprensa.com.ar/Rss.aspx?Rss=10')
+            ]
+
+    def print_version(self, url):
+        return url.replace('.note.aspx','.NotePrint.note.aspx')
+
+    def get_article_url(self, article):
+        raw = article.get('link',  None).encode('utf8')
+        final = urllib.quote(raw,':/') 
+        return final
+
+    def preprocess_html(self, soup):
+        del soup.body['onload']
+        return soup
+    

src/calibre/web/fetch/simple.py

@@ -398,7 +398,7 @@ class RecursiveFetcher(object, LoggingInterface):
                     _fname = basename(iurl)
                     if not isinstance(_fname, unicode):
                         _fname.decode('latin1', 'replace')
-                    _fname.encode('ascii', 'replace').replace('%', '').replace(os.sep, '')
+                    _fname = _fname.encode('ascii', 'replace').replace('%', '').replace(os.sep, '')
                     res = os.path.join(linkdiskpath, _fname)
                     self.downloaded_paths.append(res)
                     self.filemap[nurl] = res