Merge from trunk

resources/recipes/cotidianul.recipe

@@ -0,0 +1,69 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+cotidianul.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Cotidianul(BasicNewsRecipe):
+    title                 = u'Cotidianul'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u''
+    publisher             = u'Cotidianul'
+    oldest_article        = 25
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Stiri'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.cotidianul.ro/images/cotidianul.png'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    extra_css = '''
+                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+                    h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+                    .byline {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
+                    .date {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
+                    p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .copyright {font-family:Arial,Helvetica,sans-serif;font-size:xx-small;text-align:center}
+                    .story{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .entry-asset asset hentry{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .pagebody{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .maincontentcontainer{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .story-body{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+                '''
+
+    keep_only_tags = [
+                          dict(name='div', attrs={'class':'titlu'})
+                        , dict(name='div', attrs={'class':'gallery clearfix'})
+                        , dict(name='div', attrs={'align':'justify'})
+                     ]
+
+    remove_tags = [
+                          dict(name='div', attrs={'class':['space']})
+                        , dict(name='div', attrs={'id':['title_desc']})
+                  ]
+
+    remove_tags_after = [
+                              dict(name='div', attrs={'class':['space']})
+                            , dict(name='span', attrs={'class':['date']})
+                        ]
+
+    feeds          = [
+                        (u'Feeds', u'http://www.cotidianul.ro/rssfeed/ToateStirile.xml')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/ele.recipe

@@ -0,0 +1,58 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+ele.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Ele(BasicNewsRecipe):
+    title                 = u'Ele'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'Dezv\u0103luie ceea ce e\u015fti'
+    publisher             = u'Ele'
+    oldest_article        = 25
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Femei'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.tripmedia.ro/tripadmin/photos/logo_ele_mare.jpg'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    extra_css = '''
+                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+                    h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+                    .byline {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
+                    .date {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
+                    p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .copyright {font-family:Arial,Helvetica,sans-serif;font-size:xx-small;text-align:center}
+                    .story{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .entry-asset asset hentry{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .pagebody{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .maincontentcontainer{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .story-body{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+                '''
+
+    keep_only_tags = [
+                          dict(name='h1', attrs={'class':'article_title'})
+                        , dict(name='div', attrs={'class':'article_text'})
+                     ]
+
+    feeds          = [
+                        (u'Feeds', u'http://www.ele.ro/rss_must_read')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/felicia.recipe

@@ -0,0 +1,48 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+revistafelicia.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Felicia(BasicNewsRecipe):
+    title                 = u'Revista Felicia'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'O revist\u0103 pentru sufletul t\u0103u'
+    publisher             = u'Revista Felicia'
+    oldest_article        = 25
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Reviste'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.3waves.net/uploads/image/logo-revista-felicia_03.jpg'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+                          dict(name='div', attrs={'class':'header'})
+                        , dict(name='div', attrs={'id':'contentArticol'})
+                     ]
+
+    remove_tags = [
+                      dict(name='img',attrs={'src':['http://www.revistafelicia.ro/templates/default/images/hdr_ultimul_nr.jpg']})
+                    , dict(name='div',attrs={'class':['content']})
+                  ]
+
+    feeds          = [
+                        (u'Feeds', u'http://www.revistafelicia.ro/rss')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/financiarul.recipe

@@ -0,0 +1,55 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+financiarul.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Financiarul(BasicNewsRecipe):
+    title                 = u'Financiarul'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'FIN.ro'
+    publisher             = u'Financiarul'
+    oldest_article        = 25
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Stiri'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.financiarul.com/templates/default/images/logo.png'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+                        dict(name='div', attrs={'class':'col2ContentLeftL'})
+                     ]
+
+    remove_tags = [
+                    dict(name='div',attrs={'class':['infoArticol']})
+                  , dict(name='ul', attrs={'class':'navSectiuni'})
+                  , dict(name='div', attrs={'class':'separator separatorTop'})
+                  , dict(name='div', attrs={'class':'infoArticol infoArticolBottom'})
+                  , dict(name='ul', attrs={'class':['related']})
+                  , dict(name='div', attrs={'class':['slot panel300 panelGri300 panelGri300s panelGri300sm']})
+                  ]
+
+    remove_tags_after = [
+                            dict(name='ul', attrs={'class':['related']})
+                        ]
+
+    feeds          = [
+                        (u'Feeds', u'http://www.financiarul.com/rss')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/imperatortravel.recipe

@@ -0,0 +1,68 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+imperatortravel.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Imperatortravel(BasicNewsRecipe):
+    title                 = u'Imperator Travel'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'C\u0103l\u0103torii'
+    publisher             = u'Imperator Travel'
+    oldest_article        = 25
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Stiri,Turism,Calatorii'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.imperatortravel.ro/images/header-1.jpg'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    extra_css = '''
+                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+                    h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+                    .byline {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
+                    .date {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
+                    p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .copyright {font-family:Arial,Helvetica,sans-serif;font-size:xx-small;text-align:center}
+                    .story{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .entry-asset asset hentry{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .pagebody{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .maincontentcontainer{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .story-body{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+                '''
+
+    keep_only_tags = [
+                          dict(name='div', attrs={'class':'article first_main_article'})
+                     ]
+
+    remove_tags = [
+                          dict(name='div', attrs={'class':['meta']})
+                        , dict(name='body', attrs={'class':['transparent_widget ff3 win  Locale_en_US']})
+                        , dict(name='div', attrs={'class':['connect_widget']})
+                        , dict(name='ul', attrs={'class':['similar-posts']})
+                  ]
+
+    remove_tags_after = [
+                            dict(name='ul', attrs={'class':['similar-posts']})
+                        ]
+
+    feeds          = [
+                        (u'Feeds', u'http://feeds.feedburner.com/ImperatorTravels')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/lanacion.recipe

@@ -1,5 +1,5 @@
 __license__   = 'GPL v3'
-__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
+__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
 '''
 lanacion.com.ar
 '''
@@ -19,9 +19,10 @@ class Lanacion(BasicNewsRecipe):
     language              = 'es_AR'
     publication_type      = 'newspaper'
     remove_empty_feeds    = True
-    masthead_url          = 'http://www.lanacion.com.ar/imgs/layout/logos/ln341x47.gif'
+    masthead_url          = 'http://www.lanacion.com.ar/_ui/desktop/imgs/layout/logos/ln341x47.gif'
-    extra_css             = """ h1{font-family: Georgia,serif}
+    extra_css             = """
-                                h2{color: #626262}
+                                h1{font-family: Georgia,serif}
+                                h2{color: #626262; font-weight: normal; font-size: 1.1em}
                                 body{font-family: Arial,sans-serif}
                                 img{margin-top: 0.5em; margin-bottom: 0.2em; display: block}
                                 .notaFecha{color: #808080}
@@ -37,47 +38,78 @@ class Lanacion(BasicNewsRecipe):
                         , 'language' : language
                         }
 
-    keep_only_tags = [dict(name='div', attrs={'class':['nota floatFix','topNota','nota','post']})]
+    keep_only_tags = [dict(name='div', attrs={'id':'content'})]
+    
     remove_tags = [
                      dict(name='div' , attrs={'class':'notaComentario floatFix noprint' })
                     ,dict(name='ul'  , attrs={'class':['cajaHerramientas cajaTop noprint','herramientas noprint']})
-                    ,dict(name='div' , attrs={'class':['cajaHerramientas noprint','cajaHerramientas floatFix']   })
+                    ,dict(name='div' , attrs={'class':['titulosMultimedia','herramientas noprint','cajaHerramientas noprint','cajaHerramientas floatFix']   })
-                    ,dict(attrs={'class':['titulosMultimedia','derecha','techo color','encuesta','izquierda compartir','floatFix','videoCentro']})
+                    ,dict(attrs={'class':['izquierda','espacio17','espacio10','espacio20','floatFix ultimasNoticias','relacionadas','titulosMultimedia','derecha','techo color','encuesta','izquierda compartir','floatFix','videoCentro']})
                     ,dict(name=['iframe','embed','object','form','base','hr','meta','link','input'])
                   ]
+                  
     remove_tags_after = dict(attrs={'class':['tags','nota-destacado']})
     remove_attributes = ['height','width','visible','onclick','data-count','name']
 
     feeds          = [
-                         (u'Ultimas noticias'     , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?origen=2'         )
+                         (u'Ultimas Noticias'     , u'http://servicios.lanacion.com.ar/herramientas/rss/origen=2'         )
-                        ,(u'Politica'             , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=30'  )
+                        ,(u'Politica'             , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=30'  )
-                        ,(u'Economia'             , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=272' )
+                        ,(u'Deportes'             , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=131' )
-                        ,(u'Deportes'             , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=131' )
+                        ,(u'Economia'             , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=272' )
-                        ,(u'Informacion General'  , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=21'  )
+                        ,(u'Informacion General'  , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=21'  )
-                        ,(u'Cultura'              , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=1'   )
+                        ,(u'Cultura'              , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=1'   )
-                        ,(u'Opinion'              , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=28'  )
+                        ,(u'Opinion'              , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=28'  )                        
-                        ,(u'Espectaculos'         , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=120' )
+                        ,(u'Espectaculos'         , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=120' )
-                        ,(u'Exterior'             , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=7'   )
+                        ,(u'Exterior'             , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=7'   )
-                        ,(u'Ciencia&Salud'        , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=498' )
+                        ,(u'Ciencia&Salud'        , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=498' )
-                        ,(u'Revista'              , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=494' )
+                        ,(u'Revista'              , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=494' )
-                        ,(u'Enfoques'             , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=421' )
+                        ,(u'Enfoques'             , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=421' )
-                        ,(u'Comercio Exterior'    , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=347' )
+                        ,(u'Comercio Exterior'    , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=347' )
-                        ,(u'Tecnologia'           , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=432' )
+                        ,(u'Tecnologia'           , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=432' )
-                        ,(u'Arquitectura'         , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=366' )
+                        ,(u'Arquitectura'         , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=366' )
-                        ,(u'Turismo'              , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=504' )
+                        ,(u'Turismo'              , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=504' )
-                        ,(u'Al volante'           , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=371' )
+                        ,(u'Al volante'           , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=371' )
-                        ,(u'El Campo'             , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=337' )
+                        ,(u'El Campo'             , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=337' )
-                        ,(u'Moda y Belleza'       , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=1312' )
+                        ,(u'Moda y Belleza'       , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=1312')
-                        ,(u'Inmuebles Comerciales', u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=1363' )
+                        ,(u'Inmuebles Comerciales', u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=1363')
-                        ,(u'Countries'            , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=1348' )
+                        ,(u'Countries'            , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=1348')
-                        ,(u'adnCultura'            , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=6734' )
+                        ,(u'adnCultura'           , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=6734')
-                        ,(u'The Wall Street Journal Americas', u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=6373' )
+                        ,(u'The WSJ Americas'     , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=6373')
-                        ,(u'Estilo de vida'            , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=7353' )
+                        ,(u'Comunidad'            , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=1344')
-                        ,(u'Management'            , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=7380' )
+                        ,(u'Management'           , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=7380')
-                        ,(u'Bicentenario'            , u'http://www.lanacion.com.ar/herramientas/rss/index.asp?categoria_id=7276' )
+                        ,(u'Bicentenario'         , u'http://servicios.lanacion.com.ar/herramientas/rss/categoria_id=7276')
                      ]
 
+                     
+    def get_browser(self):
+        br = BasicNewsRecipe.get_browser()
+        br.set_debug_redirects(True)
+        br.set_debug_responses(True)
+        br.set_debug_http(True)
+        return br
+
+    def get_article_url(self, article):
+        link = BasicNewsRecipe.get_article_url(self,article)
+        if link.startswith('http://blogs.lanacion') and not link.endswith('/'):
+           return None
+        return link
+        
     def preprocess_html(self, soup):
         for item in soup.findAll(style=True):
             del item['style']
-        return self.adeify_images(soup)
+        for item in soup.findAll('a'):
+            limg = item.find('img')
+            if item.string is not None:
+               str = item.string
+               item.replaceWith(str)
+            else:
+               if limg:
+                  item.name = 'div'
+                  item.attrs = []
+               else:
+                   str = self.tag_to_string(item)
+                   item.replaceWith(str)
+        for item in soup.findAll('img'):
+            if not item.has_key('alt'):
+               item['alt'] = 'image'            
+        return soup

resources/recipes/monden.recipe

@@ -0,0 +1,66 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+monden.info
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Monden(BasicNewsRecipe):
+    title                 = u'Monden'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'Arti\u015fti, interviuri, concerte.. MUZIC\u0102'
+    publisher             = u'Monden'
+    oldest_article        = 25
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Stiri,Muzica'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.monden.info/wp-content/uploads/2009/04/mondeninfo-logo.jpg'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+
+    extra_css = '''
+                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+                    h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+                    .byline {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
+                    .date {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
+                    p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .copyright {font-family:Arial,Helvetica,sans-serif;font-size:xx-small;text-align:center}
+                    .story{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .entry-asset asset hentry{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .pagebody{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .maincontentcontainer{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .story-body{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+                '''
+
+    keep_only_tags = [
+                          dict(name='div', attrs={'id':'content'})
+                     ]
+
+    remove_tags = [
+                          dict(name='div', attrs={'class':['postAuthor']})
+                        , dict(name='div', attrs={'class':['postLike']})
+                  ]
+
+    remove_tags_after = [
+                             dict(name='div', attrs={'class':['postLike']})
+                        ]
+
+    feeds          = [
+                        (u'Feeds', u'http://www.monden.info/feed/')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/oakland_north.recipe

@@ -0,0 +1,23 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+import re
+
+class AdvancedUserRecipe1299640653(BasicNewsRecipe):
+    title          = u'Oakland North'
+    oldest_article = 30
+    max_articles_per_feed = 100
+
+    language = 'en'
+    __author__ = 'noah'
+    description = 'Oakland North'
+    category = 'news'
+    no_stylesheets = True
+
+    masthead_url = 'http://oaklandnorth.net/wp-content/themes/oaklandnorth/images/masthead.png'
+
+    keep_only_tags    = [dict(name='div', attrs={'class':re.compile(r'\bpost\b(?!-)', re.IGNORECASE)})]
+
+    remove_tags_after = [dict(name='p', attrs={'class':'post-postscript'})]
+
+    remove_tags    = [dict(name='p', attrs={'class':'post-postscript'})]
+
+    feeds          = [(u'All Headlines', u'http://oaklandnorth.net/feed/')]

resources/recipes/promotor.recipe

@@ -0,0 +1,70 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+promotor.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Promotor(BasicNewsRecipe):
+    title                 = u'Promotor'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'Auto-moto'
+    publisher             = u'Promotor'
+    oldest_article        = 25
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Reviste,TV,Auto'
+    encoding              = 'utf-8'
+    cover_url             = 'http://www.promotor.ro/images/logo_promotor.gif'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                            ,'publisher'  : publisher
+                         }
+    extra_css = '''
+                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
+                    h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
+                    .byline {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
+                    .date {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;}
+                    p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .copyright {font-family:Arial,Helvetica,sans-serif;font-size:xx-small;text-align:center}
+                    .story{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .entry-asset asset hentry{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .pagebody{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .maincontentcontainer{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    .story-body{font-family:Arial,Helvetica,sans-serif;font-size:small;}
+                    body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
+                '''
+
+    keep_only_tags = [
+                          dict(name='div', attrs={'class':'casetatitluarticol'})
+                        , dict(name='div', attrs={'style':'width: 273px; height: 210px; overflow: hidden; margin: 0pt auto;'})
+                        , dict(name='div', attrs={'class':'textb'})
+                        , dict(name='div', attrs={'class':'contentarticol'})
+                     ]
+
+    remove_tags = [
+                      dict(name='td', attrs={'class':['connect_widget_vertical_center connect_widget_button_cell']})
+                    , dict(name='div', attrs={'class':['etichetagry']})
+                    , dict(name='span', attrs={'class':['textb']})
+                  ]
+
+    remove_tags_after = [
+                              dict(name='div', attrs={'class':['etichetagry']})
+                            , dict(name='span', attrs={'class':['textb']})
+                        ]
+
+    feeds          = [
+                        (u'Feeds', u'http://www.promotor.ro/rss')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

resources/recipes/timesnewroman.recipe

@@ -0,0 +1,52 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+timesnewroman.ro
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class TimesNewRoman(BasicNewsRecipe):
+    title                 = u'Times New Roman'
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'Cotidian independent de umor voluntar'
+    publisher             = u'Times New Roman'
+    oldest_article        = 25
+    language              = 'ro'
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    category              = 'Ziare,Reviste,Fun'
+    encoding              = 'utf-8'
+    cover_url         = 'http://www.timesnewroman.ro/templates/TNRV2/images/logo.gif'
+
+    conversion_options = {
+                             'comments'   : description
+                            ,'tags'       : category
+                            ,'language'   : language
+                ,'publisher'  : publisher
+                         }
+
+    keep_only_tags = [
+            dict(name='div', attrs={'id':'page'})
+                     ]
+
+    remove_tags = [
+                dict(name='p', attrs={'class':['articleinfo']})
+              , dict(name='div',attrs={'class':['vergefacebooklike']})
+                  , dict(name='div', attrs={'class':'cleared'})
+                  ]
+
+    remove_tags_after = [
+               dict(name='div', attrs={'class':'cleared'})
+                    ]
+
+    feeds          = [
+            (u'Feeds', u'http://www.timesnewroman.ro/index.php?format=feed&type=rss')
+                     ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)

src/calibre/devices/__init__.py

@@ -30,7 +30,6 @@ def strftime(epoch, zone=time.gmtime):
 def get_connected_device():
     from calibre.customize.ui import device_plugins
     from calibre.devices.scanner import DeviceScanner
-    import uuid
     dev = None
     scanner = DeviceScanner()
     scanner.scan()
@@ -48,7 +47,7 @@ def get_connected_device():
 
     for d in connected_devices:
         try:
-            d.open(str(uuid.uuid4()))
+            d.open()
         except:
             continue
         else:

src/calibre/devices/prs500/cli/main.py

@@ -6,7 +6,7 @@ Provides a command-line and optional graphical interface to the SONY Reader PRS-
 For usage information run the script.
 """
 
-import StringIO, sys, time, os, uuid
+import StringIO, sys, time, os
 from optparse import OptionParser
 
 from calibre import __version__, __appname__
@@ -213,7 +213,7 @@ def main():
 
     for d in connected_devices:
         try:
-            d.open(str(uuid.uuid4()))
+            d.open(None)
         except:
             continue
         else:

src/calibre/ebooks/__init__.py

@@ -25,7 +25,7 @@ class DRMError(ValueError):
 class ParserError(ValueError):
     pass
 
-BOOK_EXTENSIONS = ['lrf', 'rar', 'zip', 'rtf', 'lit', 'txt', 'txtz', 'htm', 'xhtm',
+BOOK_EXTENSIONS = ['lrf', 'rar', 'zip', 'rtf', 'lit', 'txt', 'txtz', 'text', 'htm', 'xhtm',
                    'html', 'xhtml', 'pdf', 'pdb', 'pdr', 'prc', 'mobi', 'azw', 'doc',
                    'epub', 'fb2', 'djvu', 'lrx', 'cbr', 'cbz', 'cbc', 'oebzip',
                    'rb', 'imp', 'odt', 'chm', 'tpz', 'azw1', 'pml', 'pmlz', 'mbp', 'tan', 'snb']

src/calibre/ebooks/oeb/transforms/structure.py

@@ -13,6 +13,7 @@ from urlparse import urlparse
 
 from calibre.ebooks.oeb.base import XPNSMAP, TOC, XHTML, xml2text
 from calibre.ebooks import ConversionError
+from calibre.utils.ordered_dict import OrderedDict
 
 def XPath(x):
     try:
@@ -95,10 +96,8 @@ class DetectStructure(object):
                     self.log.exception('Failed to mark chapter')
 
     def create_level_based_toc(self):
-        if self.opts.level1_toc is None:
+        if self.opts.level1_toc is not None:
-            return
+            self.add_leveled_toc_items()
-        for item in self.oeb.spine:
-            self.add_leveled_toc_items(item)
 
     def create_toc_from_chapters(self):
         counter = self.oeb.toc.next_play_order()
@@ -145,49 +144,57 @@ class DetectStructure(object):
         return text, href
 
 
-    def add_leveled_toc_items(self, item):
+    def add_leveled_toc_items(self):
-        level1 = XPath(self.opts.level1_toc)(item.data)
+        added = OrderedDict()
-        level1_order = []
+        added2 = OrderedDict()
-        document = item
-
         counter = 1
-        if level1:
+        for document in self.oeb.spine:
-            added = {}
+            previous_level1 = list(added.itervalues())[-1] if added else None
-            for elem in level1:
+            previous_level2 = list(added2.itervalues())[-1] if added2 else None
+
+            for elem in XPath(self.opts.level1_toc)(document.data):
                 text, _href = self.elem_to_link(document, elem, counter)
                 counter += 1
                 if text:
                     node = self.oeb.toc.add(text, _href,
                             play_order=self.oeb.toc.next_play_order())
-                    level1_order.append(node)
                     added[elem] = node
                     #node.add(_('Top'), _href)
-            if self.opts.level2_toc is not None:
+
-                added2 = {}
+            if self.opts.level2_toc is not None and added:
-                level2 = list(XPath(self.opts.level2_toc)(document.data))
+                for elem in XPath(self.opts.level2_toc)(document.data):
-                for elem in level2:
                     level1 = None
                     for item in document.data.iterdescendants():
-                        if item in added.keys():
+                        if item in added:
                             level1 = added[item]
-                        elif item == elem and level1 is not None:
+                        elif item == elem:
+                            if level1 is None:
+                                if previous_level1 is None:
+                                    break
+                                level1 = previous_level1
                             text, _href = self.elem_to_link(document, elem, counter)
                             counter += 1
                             if text:
                                 added2[elem] = level1.add(text, _href,
                                     play_order=self.oeb.toc.next_play_order())
-                if self.opts.level3_toc is not None:
+                            break
-                    level3 = list(XPath(self.opts.level3_toc)(document.data))
+
-                    for elem in level3:
+                if self.opts.level3_toc is not None and added2:
+                    for elem in XPath(self.opts.level3_toc)(document.data):
                         level2 = None
                         for item in document.data.iterdescendants():
-                            if item in added2.keys():
+                            if item in added2:
                                 level2 = added2[item]
-                            elif item == elem and level2 is not None:
+                            elif item == elem:
+                                if level2 is None:
+                                    if previous_level2 is None:
+                                        break
+                                    level2 = previous_level2
                                 text, _href = \
                                         self.elem_to_link(document, elem, counter)
                                 counter += 1
                                 if text:
                                     level2.add(text, _href,
-                                    play_order=self.oeb.toc.next_play_order())
+                                        play_order=self.oeb.toc.next_play_order())
+                                break
 

src/calibre/ebooks/rtf2xml/tokenize.py

@@ -46,7 +46,8 @@ class Tokenize:
 
     def __remove_uc_chars(self, startchar, token):
         for i in xrange(startchar, len(token)):
-            if token[i] == " ":
+            #handle the case of an uc char with a terminating blank before ansi char
+            if token[i] == " " and self.__uc_char:
                 continue
             elif self.__uc_char:
                 self.__uc_char -= 1

src/calibre/ebooks/txt/input.py

@@ -22,7 +22,7 @@ class TXTInput(InputFormatPlugin):
     name        = 'TXT Input'
     author      = 'John Schember'
     description = 'Convert TXT files to HTML'
-    file_types  = set(['txt', 'txtz'])
+    file_types  = set(['txt', 'txtz', 'text'])
 
     options = set([
         OptionRecommendation(name='paragraph_type', recommended_value='auto',

src/calibre/gui2/dialogs/choose_plugin_toolbars.py

@@ -0,0 +1,61 @@
+#!/usr/bin/env python
+# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
+
+from __future__ import (unicode_literals, division, absolute_import,
+                        print_function)
+
+__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
+__docformat__ = 'restructuredtext en'
+__license__   = 'GPL v3'
+
+
+from PyQt4.Qt import QDialog, QVBoxLayout, QLabel, QDialogButtonBox,  \
+            QListWidget, QAbstractItemView
+from PyQt4 import QtGui
+
+class ChoosePluginToolbarsDialog(QDialog):
+
+    def __init__(self, parent, plugin, locations):
+        QDialog.__init__(self, parent)
+        self.locations = locations
+
+        self.setWindowTitle(
+            _('Add "%s" to toolbars or menus')%plugin.name)
+
+        self._layout = QVBoxLayout(self)
+        self.setLayout(self._layout)
+
+        self._header_label = QLabel(
+                _('Select the toolbars and/or menus to add <b>%s</b> to:') %
+                plugin.name)
+        self._layout.addWidget(self._header_label)
+
+        self._locations_list = QListWidget(self)
+        self._locations_list.setSelectionMode(QAbstractItemView.MultiSelection)
+        sizePolicy = QtGui.QSizePolicy(QtGui.QSizePolicy.Preferred,
+                QtGui.QSizePolicy.Minimum)
+        sizePolicy.setHorizontalStretch(0)
+        sizePolicy.setVerticalStretch(0)
+        self._locations_list.setSizePolicy(sizePolicy)
+        for key, text in locations:
+            self._locations_list.addItem(text)
+        self._layout.addWidget(self._locations_list)
+
+        self._footer_label = QLabel(
+            _('You can also customise the plugin locations '
+              'using <b>Preferences -> Customise the toolbar</b>'))
+        self._layout.addWidget(self._footer_label)
+
+        button_box = QDialogButtonBox(QDialogButtonBox.Ok |
+                QDialogButtonBox.Cancel)
+        button_box.accepted.connect(self.accept)
+        button_box.rejected.connect(self.reject)
+        self._layout.addWidget(button_box)
+        self.resize(self.sizeHint())
+
+    def selected_locations(self):
+        selected = []
+        for row in self._locations_list.selectionModel().selectedRows():
+            selected.append(self.locations[row.row()])
+        return selected
+

src/calibre/gui2/preferences/plugins.py

@@ -16,9 +16,10 @@ from calibre.customize.ui import initialized_plugins, is_disabled, enable_plugin
                                  disable_plugin, plugin_customization, add_plugin, \
                                  remove_plugin
 from calibre.gui2 import NONE, error_dialog, info_dialog, choose_files, \
-        question_dialog
+        question_dialog, gprefs
 from calibre.utils.search_query_parser import SearchQueryParser
 from calibre.utils.icu import lower
+from calibre.utils.ordered_dict import OrderedDict
 
 class PluginModel(QAbstractItemModel, SearchQueryParser): # {{{
 
@@ -281,6 +282,7 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
             self._plugin_model.populate()
             self._plugin_model.reset()
             self.changed_signal.emit()
+            self.check_for_add_to_toolbars(plugin)
             info_dialog(self, _('Success'),
                     _('Plugin <b>{0}</b> successfully installed under <b>'
                         ' {1} plugins</b>. You may have to restart calibre '
@@ -342,6 +344,37 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form):
                          plugin.name + _(' cannot be removed. It is a '
                          'builtin plugin. Try disabling it instead.')).exec_()
 
+    def check_for_add_to_toolbars(self, plugin):
+        from calibre.gui2.preferences.toolbar import ConfigWidget
+        from calibre.customize import InterfaceActionBase
+
+        if not isinstance(plugin, InterfaceActionBase):
+            return
+
+        all_locations = OrderedDict(ConfigWidget.LOCATIONS)
+        plugin_action = plugin.load_actual_plugin(self.gui)
+        installed_actions = OrderedDict([
+            (key, list(gprefs.get('action-layout-'+key, [])))
+            for key in all_locations])
+
+        # If already installed in a GUI container, do nothing
+        for action_names in installed_actions.itervalues():
+            if plugin_action.name in action_names:
+                return
+
+        allowed_locations = [(key, text) for key, text in
+                all_locations.iteritems() if key
+                not in plugin_action.dont_add_to]
+        if not allowed_locations:
+            return # This plugin doesn't want to live in the GUI
+
+        from calibre.gui2.dialogs.choose_plugin_toolbars import ChoosePluginToolbarsDialog
+        d = ChoosePluginToolbarsDialog(self, plugin_action, allowed_locations)
+        if d.exec_() == d.Accepted:
+            for key, text in d.selected_locations():
+                installed_actions = list(gprefs.get('action-layout-'+key, []))
+                installed_actions.append(plugin_action.name)
+                gprefs['action-layout-'+key] = tuple(installed_actions)
 
 if __name__ == '__main__':
     from PyQt4.Qt import QApplication