News24 and Nuus24 by Nicki de Wet

recipes/news24.recipe

@@ -0,0 +1,53 @@
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class AdvancedUserRecipe1375900744(BasicNewsRecipe):
+    title                 = u'News24'
+    description           = "News24."
+    __author__            = 'Nicki de Wet'
+    publisher             = 'Media24'
+    category              = 'news, politics, South Africa'
+    oldest_article        = 3
+    max_articles_per_feed = 20
+    no_stylesheets        = True
+    encoding              = 'utf8'
+    use_embedded_content  = False
+    auto_cleanup          = False
+    language              = 'en_ZA'
+    remove_empty_feeds    = True
+    publication_type      = 'newsportal'
+    masthead_url          = 'http://www.24.com/images/widgethead_news.png'
+    extra_css             = """
+                                body{font-family: Arial,Helvetica,sans-serif }
+                                img{display: block}
+                            """
+
+    conversion_options = {
+                          'comment'   : description
+                        , 'tags'      : category
+                        , 'publisher' : publisher
+                        , 'language'  : language
+                        }
+
+    remove_tags = [
+        dict(name=['object','embed','iframe','table','meta','link']),
+        dict(attrs={
+                'class':['TwitterfacebookLink','superSportArticleBlock',
+                         'videoHighlights', 'facebookComments','share',
+                         'item_block','kalahari_product left', 'block red',
+                         'credit']}),
+        dict(attrs={'id':['comments_wrap', 'article_toolbox_bot',
+                          'inside_news','sponsored-links', 'lnkGalleries',
+                          'relatedlinks_box', 'lnkUserGalleries',
+                          'lnkNewsGalleries', 'relatedlinks',
+                          'divRelatedLinks']})]
+
+    keep_only_tags = [
+        dict(attrs={'class':['left col633', 'article col626',
+                             'columnWrapperLeft', 'articlecolumn',
+                             'article_img', 'picture_caption', 'DiveTable']})]
+
+    feeds          = [
+        (u'Top Stories', u'http://feeds.news24.com/articles/news24/TopStories/rss'),
+        (u'South Africa', u'http://feeds.news24.com/articles/news24/SouthAfrica/rss'),
+        (u'World', u'http://feeds.news24.com/articles/news24/World/rss'),
+        (u'Sport', u'http://feeds.24.com/articles/sport/featured/topstories/rss')]

recipes/nuus24.recipe

@@ -0,0 +1,57 @@
+import re
+from calibre import strftime
+from calibre.web.feeds.recipes import BasicNewsRecipe
+
+class Nuus24(BasicNewsRecipe):
+
+    title       = 'Nuus24'
+    __author__  = 'Nicki de Wet'
+    encoding              = 'utf-8'
+    description = 'Daaglikse Afrikaanse Nuus via Nuus24'
+    language = 'af'
+    publisher             = 'Media24'
+    timefmt = ' [%a, %d %b, %Y]'
+    masthead_url = 'http://afrikaans.news24.com/images/nuus.jpg'
+    max_articles_per_feed = 25
+    remove_tags_before = dict(id='TheFeed')
+    remove_tags_after  = dict(id='TheFeed')
+    remove_tags = [dict(
+        attrs={
+            'class':[
+                'personal-bar row-fluid', 'navbar main-menu-fixed',
+                'breaking-news-wrapper', 'row-fluid comments-bg',
+                'unstyled actions', 'modal-body', 'modal-header', 'desktop']}),
+        dict(id=['weather-forecast', 'topics', 'side-widgets', 'footer-container', 'sb-container', 'myModal']),
+        dict(name=['script', 'noscript', 'style'])]
+
+    keep_only_tags = [dict(attrs={'class':['span8 border-right']}),
+                                                dict(name=['article', 'section']),
+                                                dict(id=['img-wrapper'])]
+    extra_css = """ div.carousel-inner{ overflow:hidden;display: block;height:300px;} img{display: block} """
+    no_stylesheets = True
+
+    def parse_index(self):
+        soup = self.index_to_soup('http://afrikaans.news24.com/Index.aspx')
+
+        def feed_title(div):
+            return ''.join(div.findAll(text=True, recursive=False)).strip()
+
+        articles = {}
+        key = None
+        key = 'Nuus in Afrikaans'
+        articles[key] = []
+        ans= []
+
+        for anchor in soup.findAll(True,
+            attrs={'id':['lnkLink']}):
+            url = re.sub(r'\?.*', '', anchor['href'])
+            title = self.tag_to_string(anchor, use_alt=True).strip()
+            print title
+            description = ''
+            pubdate = strftime('%a, %d %b')
+            articles[key].append(
+                    dict(title=title, url=url, date=pubdate,
+                                    description=description,
+                                    content=''))
+        ans = [(key, articles[key])]
+        return ans