tportal.h by DM. Fixes #8552 (New recipe for daily tportal)

resources/recipes/dailytportal.recipe

@@ -0,0 +1,66 @@
+__license__   = 'GPL v3'
+__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
+'''
+daily.tportal.hr
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Pagina12(BasicNewsRecipe):
+    title                 = 'Daily tportal.h'
+    __author__            = 'Darko Miletic'
+    description           = 'News from Croatia'
+    publisher             = 'tportal.hr'
+    category              = 'news, politics, Croatia'
+    oldest_article        = 2
+    max_articles_per_feed = 200
+    no_stylesheets        = True
+    encoding              = 'utf-8'
+    use_embedded_content  = False
+    language              = 'en_HR'
+    remove_empty_feeds    = True
+    publication_type      = 'newsportal'
+    extra_css             = """
+                               body{font-family: Verdana,sans-serif }
+                               img{margin-bottom: 0.4em; display:block}
+                               h1,h2{color: #2D648A; font-family: Georgia,serif}
+                               .artAbstract{font-size: 1.2em; font-family: Georgia,serif}
+                            """
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_tags = [
+                     dict(name=['meta','link','embed','object','iframe','base'])
+                    ,dict(name='div', attrs={'class':'artInfo'})
+                  ]
+    remove_attributes=['lang']
+
+    keep_only_tags=dict(attrs={'class':'articleDetails'})
+
+    feeds = [(u'News', u'http://daily.tportal.hr/rss/dailynaslovnicarss.xml')]
+
+    def preprocess_html(self, soup):
+        for item in soup.findAll(style=True):
+            del item['style']
+        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
+

src/calibre/utils/localization.py

@@ -105,6 +105,7 @@ _extra_lang_codes = {
         'en_TH' : _('English (Thailand)'),
         'en_CY' : _('English (Cyprus)'),
         'en_PK' : _('English (Pakistan)'),
+        'en_HR' : _('English (Croatia)'),
         'en_IL' : _('English (Israel)'),
         'en_SG' : _('English (Singapore)'),
         'en_YE' : _('English (Yemen)'),