Merge from trunk

resources/recipes/lanacion.recipe

@@ -9,17 +9,22 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class Lanacion(BasicNewsRecipe):
     title                 = 'La Nacion'
     __author__            = 'Darko Miletic'
-    description           = 'Noticias de Argentina y el resto del mundo'
+    description           = "lanacion.com - Informacion actualizada las 24 horas, con noticias de Argentina y del mundo"
     publisher             = 'La Nacion S.A.'
     category              = 'news, politics, Argentina'
-    oldest_article        = 2
+    oldest_article        = 1
     max_articles_per_feed = 100
     use_embedded_content  = False
     no_stylesheets        = True
     language              = 'es'
-    encoding              = 'cp1252'
+    publication_type      = 'newspaper'
+    remove_empty_feeds    = True    
     masthead_url          = 'http://www.lanacion.com.ar/imgs/layout/logos/ln341x47.gif'
-    extra_css             = ' h1{font-family: Georgia,serif} body{font-family: Arial,sans-serif} img{margin-top: 0.5em; margin-bottom: 0.2em} .notaEpigrafe{font-size: x-small} '
+    extra_css             = """ h1{font-family: Georgia,serif} 
+                                body{font-family: Arial,sans-serif} 
+                                img{margin-top: 0.5em; margin-bottom: 0.2em} 
+                                .notaEpigrafe{font-size: x-small} 
+                                .topNota h1{font-family: Arial,sans-serif} """
 
 
     conversion_options = {
@@ -29,19 +34,19 @@ class Lanacion(BasicNewsRecipe):
                         , 'language' : language
                         }
 
-    keep_only_tags = [dict(name='div', attrs={'class':'nota floatFix'})]
+    keep_only_tags = [dict(name='div', attrs={'class':['nota floatFix','topNota','nota','post']})]
     remove_tags = [
                      dict(name='div' , attrs={'class':'notaComentario floatFix noprint' })
-                    ,dict(name='ul'  , attrs={'class':'cajaHerramientas cajaTop noprint'})
+                    ,dict(name='ul'  , attrs={'class':['cajaHerramientas cajaTop noprint','herramientas noprint']})
                     ,dict(name='div' , attrs={'class':'cajaHerramientas noprint'        })
-                    ,dict(attrs={'class':['titulosMultimedia','derecha','techo color']})
+                    ,dict(attrs={'class':['titulosMultimedia','derecha','techo color','encuesta','izquierda compartir','floatFix']})
-                    ,dict(name=['iframe','embed','object'])
+                    ,dict(name=['iframe','embed','object','form','base','hr'])
                   ]
-    remove_attributes = ['height','width']
+    remove_tags_after = dict(attrs={'class':['tags','nota-destacado']})                
+    remove_attributes = ['height','width','visible']
 
     feeds          = [
                          (u'Ultimas noticias'     , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?origen=2'         )
-                        ,(u'Diario de hoy'        , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?origen=1'         )
                         ,(u'Politica'             , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=30'  )
                         ,(u'Economia'             , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=272' )
                         ,(u'Deportes'             , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=131' )
@@ -50,8 +55,23 @@ class Lanacion(BasicNewsRecipe):
                         ,(u'Opinion'              , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=28'  )
                         ,(u'Espectaculos'         , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=120' )
                         ,(u'Exterior'             , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=7'   )
-                        ,(u'Ciencia/Salud'        , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=498' )
+                        ,(u'Ciencia&Salud'        , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=498' )
                         ,(u'Revista'              , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=494' )
+                        ,(u'Enfoques'             , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=421' )
+                        ,(u'Comercio Exterior'    , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=347' )
+                        ,(u'Tecnologia'           , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=432' )
+                        ,(u'Arquitectura'         , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=366' )
+                        ,(u'Turismo'              , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=504' )
+                        ,(u'Al volante'           , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=371' )
+                        ,(u'El Campo'             , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=337' )
+                        ,(u'Moda y Belleza'       , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=1312' )
+                        ,(u'Inmuebles Comerciales', u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=1363' )
+                        ,(u'Countries'            , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=1348' )
+                        ,(u'adnCultura'            , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=6734' )
+                        ,(u'The Wall Street Journal Americas', u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=6373' )
+                        ,(u'Estilo de vida'            , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=7353' )
+                        ,(u'Management'            , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=7380' )
+                        ,(u'Bicentenario'            , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=7276' )
                      ]
 
     def preprocess_html(self, soup):

resources/recipes/novosti.recipe

@@ -11,7 +11,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class Novosti(BasicNewsRecipe):
     title                 = 'Vecernje Novosti'
     __author__            = 'Darko Miletic'
-    description           = 'Vesti'
+    description           = 'U početku su bile istinske večernje novine - pokrenute u vreme Tršćanske krize, Italijansko-jugoslovenskog konflikta oko grada Trsta - ali su brzo izrasle u dnevni informativno-politički list, koji već godinama ima najveći tiraž u Srbiji.'
     publisher             = 'Kompanija Novosti'
     category              = 'news, politics, Serbia'
     oldest_article        = 2
@@ -21,24 +21,22 @@ class Novosti(BasicNewsRecipe):
     encoding              = 'utf-8'
     language              = 'sr'
     publication_type      = 'newspaper'
-    extra_css             = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} .article_description,body{font-family: Tahoma,Arial,Helvetica,sans1,sans-serif} '
+    extra_css             = """ @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} 
+                                .article_description,body{font-family: Arial,Helvetica,sans1,sans-serif} 
+                                .author{font-size: small}
+                                .articleLead{font-size: large; font-weight: bold}
+                            """
 
     conversion_options = {
                           'comment'   : description
                         , 'tags'      : category
                         , 'publisher' : publisher
                         , 'language'  : language
-                        , 'linearize_tables' : True
                         }
 
     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
 
-    keep_only_tags     = [dict(name='div', attrs={'class':'jednaVest'})]
+    keep_only_tags     = [dict(attrs={'class':['articleTitle','author','articleLead','articleBody']})]
-    remove_tags        = [dict(name='div', attrs={'class':['info','info_bottom','clip_div']})]
+    remove_tags        = [dict(name=['embed','object','iframe','base'])]
 
-    feeds              = [(u'Vesti', u'http://www.novosti.rs/php/vesti/rss.php')]
+    feeds              = [(u'Vesti', u'http://www.novosti.rs/rss/rss-vesti')]
-
-    def preprocess_html(self, soup):
-        for item in soup.findAll(style=True):
-            del item['style']    
-        return self.adeify_images(soup)

src/calibre/__init__.py

@@ -413,15 +413,13 @@ def entity_to_unicode(match, exceptions=[], encoding='cp1252',
         return check("'")
     if ent == 'hellips':
         ent = 'hellip'
-    if ent.lower().startswith(u'#x'):
+    if ent.startswith('#'):
-        num = int(ent[2:], 16)
-        if encoding is None or num > 255:
-            return check(my_unichr(num))
-        return check(chr(num).decode(encoding))
-    if ent.startswith(u'#'):
         try:
+            if ent[1] in ('x', 'X'):
+                num = int(ent[2:], 16)
+            else:
                 num = int(ent[1:])
-        except ValueError:
+        except:
             return '&'+ent+';'
         if encoding is None or num > 255:
             return check(my_unichr(num))

src/calibre/customize/builtins.py

@@ -460,7 +460,7 @@ from calibre.devices.hanvon.driver import N516, EB511, ALEX, AZBOOKA, THEBOOK
 from calibre.devices.edge.driver import EDGE
 from calibre.devices.teclast.driver import TECLAST_K3, NEWSMY, IPAPYRUS
 from calibre.devices.sne.driver import SNE
-from calibre.devices.misc import PALMPRE, AVANT, SWEEX, PDNOVEL
+from calibre.devices.misc import PALMPRE, AVANT, SWEEX, PDNOVEL, PROMEDIA
 from calibre.devices.folder_device.driver import FOLDER_DEVICE_FOR_CONFIG
 from calibre.devices.kobo.driver import KOBO
 
@@ -564,6 +564,7 @@ plugins += [
     MENTOR,
     SWEEX,
     PDNOVEL,
+    PROMEDIA,
     ITUNES,
 ]
 plugins += [x for x in list(locals().values()) if isinstance(x, type) and \

src/calibre/devices/misc.py

@@ -96,3 +96,20 @@ class PDNOVEL(USBMS):
             with open('%s.jpg' % os.path.join(path, filename), 'wb') as coverfile:
                 coverfile.write(coverdata[2])
 
+class PROMEDIA(USBMS):
+
+    name = 'Promedia eBook Reader'
+    gui_name = 'Promedia'
+    description = _('Communicate with the Promedia eBook reader')
+    author = 'Kovid Goyal'
+    supported_platforms = ['windows', 'linux', 'osx']
+    FORMATS = ['epub', 'rtf', 'pdf']
+
+    VENDOR_ID   = [0x525]
+    PRODUCT_ID  = [0xa4a5]
+    BCD         = [0x319]
+
+    EBOOK_DIR_MAIN = 'calibre'
+    SUPPORTS_SUB_DIRS = True
+
+

src/calibre/gui2/layout.py

@@ -349,6 +349,7 @@ class ShareConnMenu(QMenu): # {{{
         for ac in self.email_actions:
             self.removeAction(ac)
         self.email_actions = []
+        self.memory = []
         opts = email_config().parse()
         if opts.accounts:
             self.email_to_menu = QMenu(_('Email to')+'...', self)
@@ -361,6 +362,7 @@ class ShareConnMenu(QMenu): # {{{
                 action2 = DeviceAction(dest, True, False, I('mail.svg'),
                         _('Email to')+' '+account+ _(' and delete from library'))
                 map(self.email_to_menu.addAction, (action1, action2))
+                map(self.memory.append, (action1, action2))
                 if default:
                     map(self.addAction, (action1, action2))
                     map(self.email_actions.append, (action1, action2))