Update Live Mint

recipes/livemint.recipe

@@ -1,4 +1,6 @@
-from calibre.web.feeds.news import BasicNewsRecipe
+#!/usr/bin/env  python
+
+from calibre.web.feeds.news import BasicNewsRecipe, classes
 
 
 class LiveMint(BasicNewsRecipe):
@@ -7,26 +9,45 @@ class LiveMint(BasicNewsRecipe):
     __author__ = 'Krittika Goyal'
     oldest_article = 1  # days
     max_articles_per_feed = 50
+    encoding = 'utf-8'
     use_embedded_content = False
-
     no_stylesheets = True
-    auto_cleanup = True
-    feeds = [
-        ('Companies','https://www.livemint.com/rss/companies'),
-        ('Opinion','https://www.livemint.com/rss/opinion'),
-        ('Money','https://www.livemint.com/rss/money'),
-        ('Politics','https://www.livemint.com/rss/politics'),
-        ('Science','https://www.livemint.com/rss/science'),
-        ('Industry','https://www.livemint.com/rss/industry'),
-        ('Lounge','https://www.livemint.com/rss/lounge'),
-        ('Education','https://www.livemint.com/rss/education'),
-        ('Sports','https://www.livemint.com/rss/sports'),
-        ('Technology','https://www.livemint.com/rss/technology'),
-        ('News','https://www.livemint.com/rss/news'),
-        ('Mutual Funds','https://www.livemint.com/rss/Mutual Funds'),
-        ('Markets','https://www.livemint.com/rss/markets'),
-        ('AI','https://www.livemint.com/rss/AI'),
-        ('Insurance','https://www.livemint.com/rss/insurance'),
-        ('Budget','https://www.livemint.com/rss/budget'),
-        ('Elections','https://www.livemint.com/rss/elections'),
+    remove_attributes = ['style', 'height', 'width']
+
+    keep_only_tags = [
+        dict(name='h1'),
+        dict(name='picture'),
+        dict(name='figcaption'),
+        classes('articleInfo FirstEle summary highlights paywall'),
     ]
+    remove_tags = [
+        classes(
+            'trendingSimilarHeight moreNews mobAppDownload label msgError msgOk'
+        )
+    ]
+
+    feeds = [
+        ('Companies', 'https://www.livemint.com/rss/companies'),
+        ('Opinion', 'https://www.livemint.com/rss/opinion'),
+        ('Money', 'https://www.livemint.com/rss/money'),
+        ('Economy', 'https://www.livemint.com/rss/economy/'),
+        ('Politics', 'https://www.livemint.com/rss/politics'),
+        ('Science', 'https://www.livemint.com/rss/science'),
+        ('Industry', 'https://www.livemint.com/rss/industry'),
+        ('Lounge', 'https://www.livemint.com/rss/lounge'),
+        ('Education', 'https://www.livemint.com/rss/education'),
+        ('Sports', 'https://www.livemint.com/rss/sports'),
+        ('Technology', 'https://www.livemint.com/rss/technology'),
+        ('News', 'https://www.livemint.com/rss/news'),
+        ('Mutual Funds', 'https://www.livemint.com/rss/Mutual Funds'),
+        ('Markets', 'https://www.livemint.com/rss/markets'),
+        ('AI', 'https://www.livemint.com/rss/AI'),
+        ('Insurance', 'https://www.livemint.com/rss/insurance'),
+        ('Budget', 'https://www.livemint.com/rss/budget'),
+        ('Elections', 'https://www.livemint.com/rss/elections'),
+    ]
+
+    def preprocess_html(self, soup):
+        for img in soup.findAll('img', attrs={'data-src': True}):
+            img['src'] = img['data-src']
+        return soup