Implement #4141 (RIA Novosti in english and spanish)

resources/recipes/rian_eng.recipe

@@ -0,0 +1,42 @@
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+en.rian.ru
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Ria_eng(BasicNewsRecipe):
+    title                 = 'Ria Novosti'
+    __author__            = 'Darko Miletic'
+    description           = 'News from Russia in English'
+    language              = 'en'
+    publisher             = 'en.rian.ru'
+    category              = 'news, politics, Russia'
+    oldest_article        = 3
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'utf-8'
+
+    conversion_options = {
+                          'comment'          : description
+                        , 'tags'             : category
+                        , 'publisher'        : publisher
+                        , 'language'         : language
+                        }
+
+
+    keep_only_tags = [dict(name='div', attrs={'class':'article'})]
+
+    remove_tags = [
+                     dict(name=['object','link','iframe','base'])
+                    ,dict(name='div',attrs={'class':['related','mmban','view-story']})
+                    ,dict(name='span',attrs={'class':'copyright'})
+                  ]
+    remove_tags_after = dict(name='div',attrs={'class':'text'})
+
+
+    feeds = [(u'Online news', u'http://en.rian.ru/export/rss2/archive/index.xml')]
+

resources/recipes/rian_spa.recipe

@@ -0,0 +1,41 @@
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+sp.rian.ru
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Ria_eng(BasicNewsRecipe):
+    title                 = 'Ria Novosti'
+    __author__            = 'Darko Miletic'
+    description           = 'Noticias desde Russia en Castellano'
+    language              = 'es'
+    publisher             = 'sp.rian.ru'
+    category              = 'news, politics, Russia'
+    oldest_article        = 3
+    max_articles_per_feed = 100
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'utf-8'
+
+    conversion_options = {
+                          'comment'          : description
+                        , 'tags'             : category
+                        , 'publisher'        : publisher
+                        , 'language'         : language
+                        }
+
+
+    keep_only_tags = [dict(name='div', attrs={'class':'articletxt'})]
+    remove_tags = [dict(name=['object','link','iframe','base'])]
+    remove_tags_after = dict(name='div',attrs={'class':'text'})
+
+
+    feeds = [(u'Noticias', u'http://sp.rian.ru/export/rss2/index.xml')]
+
+    def print_version(self, url):
+        return url.replace('.html','-print.html')
+
+

src/calibre/ebooks/pml/pmlml.py

@@ -14,7 +14,6 @@ from calibre.ebooks.oeb.base import XHTML, XHTML_NS, barename, namespace
 from calibre.ebooks.oeb.stylizer import Stylizer
 from calibre.ebooks.pdb.ereader import image_name
 from calibre.ebooks.pml import unipmlcode
-from calibre import entity_to_unicode
 
 TAG_MAP = {
     'b'       : 'B',
@@ -158,12 +157,6 @@ class PMLMLizer(object):
         text = text.replace(u'\xc2', '')
         text = text.replace(u'\xa0', ' ')
 
-        # Turn all html entities into unicode. This should not be necessary as
-        # lxml should have already done this but we want to be sure it happens.
-        for entity in set(re.findall('&.+?;', text)):
-            mo = re.search('(%s)' % entity[1:-1], text)
-            text = text.replace(entity, entity_to_unicode(mo))
-
         # Turn all characters that cannot be represented by themself into their
         # PML code equivelent
         text = re.sub('[^\x00-\x7f]', lambda x: unipmlcode(x.group()), text)