New recipe for Wikinews by Darko Miletic

src/calibre/web/feeds/recipes/__init__.py

@@ -33,7 +33,7 @@ recipe_modules = ['recipe_' + r for r in (
            'la_republica', 'physics_today', 'chicago_tribune', 'e_novine',
            'al_jazeera', 'winsupersite', 'borba', 'courrierinternational',
            'lamujerdemivida', 'soldiers', 'theonion', 'news_times',
-           'el_universal', 'mediapart',
+           'el_universal', 'mediapart', 'wikinews_en',
           )]
 
 import re, imp, inspect, time, os

src/calibre/web/feeds/recipes/recipe_wikinews_en.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env  python
+
+__license__   = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+en.wikinews.org
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class WikiNews(BasicNewsRecipe):
+    title                 = 'Wikinews'
+    __author__            = 'Darko Miletic'
+    description           = 'News from wikipedia'
+    category              = 'news, world'
+    oldest_article        = 7
+    max_articles_per_feed = 100
+    publisher             = 'Wiki'
+    no_stylesheets        = True
+    use_embedded_content  = False
+    encoding              = 'utf-8'
+    remove_javascript     = True
+    language              = _('English')
+    
+    html2lrf_options = [
+                          '--comment', description
+                        , '--category', category
+                        , '--publisher', publisher
+                        ]
+    
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"' 
+
+    keep_only_tags = [ 
+                        dict(name='h1', attrs={'id':'firstHeading'}) 
+                       ,dict(name='div', attrs={'id':'bodyContent'}) 
+                     ]
+    
+    remove_tags = [
+                    dict(name='link')
+                   ,dict(name='div',attrs={'id':['printfooter','catlinks','footer']})
+                   ,dict(name='div',attrs={'class':['thumb left','thumb right']})
+                  ]
+
+    remove_tags_after = dict(name='h2')
+                  
+    feeds = [(u'News', u'http://feeds.feedburner.com/WikinewsLatestNews')]
+
+    def get_article_url(self, article):
+        artl  = article.get('link',  None)
+        rest, sep, article_id  = artl.rpartition('/')
+        return 'http://en.wikinews.org/wiki/' + article_id
+            
+    def print_version(self, url):
+        rest, sep, article_id  = url.rpartition('/')
+        return 'http://en.wikinews.org/w/index.php?title=' + article_id + '&printable=yes'
+
+    def preprocess_html(self, soup):
+        mtag = '<meta http-equiv="Content-Language" content="en"/><meta http-equiv="Content-Type" content="text/html; charset=utf-8">'
+        soup.head.insert(0,mtag)
+        btag = soup.find('div',attrs={'id':'bodyContent'})
+        for item in btag.findAll('div'):
+            item.extract()        
+        for item in btag.findAll('h2'):
+            item.extract()        
+        for item in soup.findAll(style=True):
+            del item['style']
+        for item in soup.findAll(font=True):
+            del item['font']
+        return soup
+