Merge from trunk

resources/recipes/adevarul.recipe

@@ -32,16 +32,25 @@ class Adevarul(BasicNewsRecipe):
                          }
 
     keep_only_tags = [  dict(name='div', attrs={'class':'article_header'})
-                       ,dict(name='div', attrs={'class':'bd'})
+                       ,dict(name='div', attrs={'class':'bb-tu first-t bb-article-body'})
                      ]
 
 
-    remove_tags = [  dict(name='div', attrs={'class':'bb-wg-article_related_attachements'})
+    remove_tags = [ 
+					 dict(name='li', attrs={'class':'author'})
+					,dict(name='li', attrs={'class':'date'})
+					,dict(name='li', attrs={'class':'comments'})
+					,dict(name='div', attrs={'class':'bb-wg-article_related_attachements'})
                     ,dict(name='div', attrs={'class':'bb-md bb-md-article_comments'})
-                ,dict(name='form', attrs={'id':'bb-comment-create-form'})
+                    ,dict(name='form', attrs={'id':'bb-comment-create-form'})
-              ]
+				    ,dict(name='div', attrs={'id':'mediatag'})
+					,dict(name='div', attrs={'id':'ft'})	
+					,dict(name='div', attrs={'id':'comment_wrapper'})
+                 ]
 
-    remove_tags_after = [ dict(name='form', attrs={'id':'bb-comment-create-form'}) ]
+    remove_tags_after = [ 
+							dict(name='div', attrs={'id':'comment_wrapper'}),											
+						]
 
     feeds = [ (u'\u0218tiri', u'http://www.adevarul.ro/rss/latest') ]
 

resources/recipes/gsp.recipe

@@ -1,20 +1,43 @@
+# -*- coding: utf-8 -*-
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = u'2011, Silviu Cotoar\u0103'
+'''
+gsp.ro
+'''
+
 from calibre.web.feeds.news import BasicNewsRecipe
 
-class AdvancedUserRecipe1286351181(BasicNewsRecipe):
+class GSP(BasicNewsRecipe):
-    title          = u'gsp.ro'
+    title                 = u'Gazeta Sporturilor'
-    __author__   = 'bucsie'
+    language              = 'ro'
-    oldest_article = 2
+    __author__            = u'Silviu Cotoar\u0103'
+    description           = u'Gazeta Sporturilor'
+    publisher             = u'Gazeta Sporturilor'
+    category              = 'Ziare,Sport,Stiri,Romania'
+    oldest_article        = 5
     max_articles_per_feed = 100
-    language='ro'
+    no_stylesheets        = True
-    cover_url ='http://www.gsp.ro/images/sigla_rosu.jpg'
+    use_embedded_content  = False
+    encoding              = 'utf-8'
+    remove_javascript     = True
+    cover_url             = 'http://www.gsp.ro/images/logo.jpg'
 
-    remove_tags = [
+    conversion_options = {
-                       dict(name='div', attrs={'class':['related_articles', 'articol_noteaza straight_line dotted_line_top', 'comentarii','mai_multe_articole']}),
+                             'comments'   : description
-                       dict(name='div', attrs={'id':'icons'})
+                            ,'tags'       : category
-                        ]
+                            ,'language'   : language
-    remove_tags_after = dict(name='div', attrs={'id':'adoceanintactrovccmgpmnyt'})
+							,'publisher'  : publisher
+                         }
 
-    feeds          = [(u'toate stirile', u'http://www.gsp.ro/index.php?section=section&screen=rss')]
+    keep_only_tags = [  dict(name='h1', attrs={'class':'serif title_2'})
+                       ,dict(name='div', attrs={'id':'only_text'})
+					   ,dict(name='span', attrs={'class':'block poza_principala'})
+                     ]
+					 
+    feeds = [ (u'\u0218tiri', u'http://www.gsp.ro/rss.xml') ]
+
+    def preprocess_html(self, soup):
+        return self.adeify_images(soup)
 
-    def print_version(self, url):
-         return 'http://www1.gsp.ro/print/' + url[(url.rindex('/')+1):]

resources/recipes/nytimes.recipe

@@ -89,7 +89,7 @@ class NYTimes(BasicNewsRecipe):
     if headlinesOnly:
         title='New York Times Headlines'
         description = 'Headlines from the New York Times. Needs a subscription from http://www.nytimes.com'
-        needs_subscription = True
+        needs_subscription = 'optional'
     elif webEdition:
         title='New York Times (Web)'
         description = 'New York Times on the Web'

resources/template-functions.json

@@ -15,6 +15,7 @@
     "template": "def evaluate(self, formatter, kwargs, mi, locals, template):\n    template = template.replace('[[', '{').replace(']]', '}')\n    return formatter.__class__().safe_format(template, kwargs, 'TEMPLATE', mi)\n", 
     "print": "def evaluate(self, formatter, kwargs, mi, locals, *args):\n    print args\n    return None\n", 
     "titlecase": "def evaluate(self, formatter, kwargs, mi, locals, val):\n    return titlecase(val)\n", 
+    "sublist": "def evaluate(self, formatter, kwargs, mi, locals, val, start_index, end_index, sep):\n    if not val:\n        return ''\n    si = int(start_index)\n    ei = int(end_index)\n    val = val.split(sep)\n    try:\n        if ei == 0:\n            return sep.join(val[si:])\n        else:\n            return sep.join(val[si:ei])\n    except:\n        return ''\n", 
     "test": "def evaluate(self, formatter, kwargs, mi, locals, val, value_if_set, value_not_set):\n    if val:\n        return value_if_set\n    else:\n        return value_not_set\n", 
     "eval": "def evaluate(self, formatter, kwargs, mi, locals, template):\n    from formatter import eval_formatter\n    template = template.replace('[[', '{').replace(']]', '}')\n    return eval_formatter.safe_format(template, locals, 'EVAL', None)\n", 
     "multiply": "def evaluate(self, formatter, kwargs, mi, locals, x, y):\n    x = float(x if x else 0)\n    y = float(y if y else 0)\n    return unicode(x * y)\n",