MIT Technology Magazine by rty

resources/recipes/alternet.recipe

@@ -15,7 +15,7 @@ class Alternet(BasicNewsRecipe):
 	(u'Top Ten Campaigns', u'http://feeds.feedblitz.com/alternet_top_10_campaigns'),
 	(u'Special Coverage Areas', u'http://feeds.feedblitz.com/alternet_coverage')
 	]
-
+    remove_attributes = ['width', 'align','cellspacing']
     remove_javascript = True
     use_embedded_content   = False
     no_stylesheets = True

resources/recipes/technology_review.recipe

@@ -0,0 +1,44 @@
+import string
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class TechnologyReview(BasicNewsRecipe):
+    title          = u'Technology Review'
+    __author__ = 'rty'
+    description = 'MIT Technology Magazine'
+    publisher = 'Technology Review Inc.'
+    category = 'Technology, Innovation, R&D'
+    oldest_article = 14
+    max_articles_per_feed = 100
+    No_stylesheets = True
+    extra_css = """
+    .ArticleBody {font: normal; text-align: justify}
+    .headline {font: bold x-large}
+    .subheadline {font: italic large}
+    """
+    feeds = [
+	(u'Computing', u'http://feeds.technologyreview.com/technology_review_Computing'),
+	(u'Web', u'http://feeds.technologyreview.com/technology_review_Web'),
+	(u'Communications', u'http://feeds.technologyreview.com/technology_review_Communications'),
+	(u'Energy', u'http://feeds.technologyreview.com/technology_review_Energy'),
+	(u'Materials', u'http://feeds.technologyreview.com/technology_review_Materials'),
+	(u'Biomedicine', u'http://feeds.technologyreview.com/technology_review_Biotech'),
+	(u'Business', u'http://feeds.technologyreview.com/technology_review_Biztech')
+	]
+    remove_attributes = ['width', 'align','cellspacing']
+
+    remove_tags = [
+                    dict(name='div', attrs={'id':['CloseLink','footerAdDiv','copyright']}),
+                         ]
+    remove_tags_after = [dict(name='div', attrs={'id':'copyright'})]
+
+    def get_article_url(self, article):
+        return article.get('guid', article.get('id', None))
+
+
+    def print_version(self, url):
+        baseurl='http://www.technologyreview.com/printer_friendly_article.aspx?id='
+        split1 = string.split(url,"/")
+        xxx=split1 [4]
+        split2= string.split(xxx,"/")
+        s =  baseurl + split2[0]
+        return s