update Indian Express

recipes/indian_express.recipe

@@ -3,15 +3,16 @@ from calibre.web.feeds.news import BasicNewsRecipe
 
 def classes(classes):
     q = frozenset(classes.split(' '))
-    return dict(attrs={
+    return dict(
-        'class': lambda x: x and frozenset(x.split()).intersection(q)})
+        attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}
+    )
 
 
 class IndianExpress(BasicNewsRecipe):
     title = u'Indian Express'
     language = 'en_IN'
     __author__ = 'Krittika Goyal'
-    oldest_article = 1  # days
+    oldest_article = 1.15  # days
     max_articles_per_feed = 25
     encoding = 'utf-8'
     masthead_url = 'https://indianexpress.com/wp-content/themes/indianexpress/images/indian-express-logo-n.svg'
@@ -20,49 +21,97 @@ class IndianExpress(BasicNewsRecipe):
     use_embedded_content = False
     remove_attributes = ['style', 'height', 'width']
     ignore_duplicate_articles = {'url'}
-    extra_css = '#storycenterbyline {font-size:small};'
+    extra_css = '''
+        #storycenterbyline {font-size:small;}
+        #img-cap {font-size:small;}
+    '''
+    resolve_internal_links = True
+    remove_empty_feeds = True
 
-    keep_only_tags = [
+    keep_only_tags = [classes('heading-part full-details')]
-        classes('heading-part full-details')
-    ]
     remove_tags = [
         dict(name='div', attrs={'id': 'ie_story_comments'}),
-        dict(name='img', attrs={'src':'https://images.indianexpress.com/2021/06/explained-button-300-ie.jpeg'}),
+        dict(
-        dict(name='a', attrs={'href':'https://indianexpress.com/section/explained/?utm_source=newbanner'}),
+            name='img',
-        dict(name='img', attrs={'src':'https://images.indianexpress.com/2021/06/opinion-button-300-ie.jpeg'}),
+            attrs={
-        dict(name='a', attrs={'href':'https://indianexpress.com/section/opinion/?utm_source=newbanner'}),
+                'src':
+                'https://images.indianexpress.com/2021/06/explained-button-300-ie.jpeg'
+            }
+        ),
+        dict(
+            name='a',
+            attrs={
+                'href':
+                'https://indianexpress.com/section/explained/?utm_source=newbanner'
+            }
+        ),
+        dict(
+            name='img',
+            attrs={
+                'src':
+                'https://images.indianexpress.com/2021/06/opinion-button-300-ie.jpeg'
+            }
+        ),
+        dict(
+            name='a',
+            attrs={
+                'href':
+                'https://indianexpress.com/section/opinion/?utm_source=newbanner'
+            }
+        ),
         classes(
             'share-social appstext ie-int-campign-ad ie-breadcrumb custom_read_button unitimg copyright'
             ' storytags pdsc-related-modify news-guard premium-story append_social_share'
+            ' digital-subscriber-only h-text-widget'
         )
     ]
+
     feeds = [
         ('Front Page', 'https://indianexpress.com/print/front-page/feed/'),
-        ('Op-Ed', 'http://indianexpress.com/section/opinion/feed/'),
-        ('Science & Technology', 'http://indianexpress.com/section/technology/feed/'),
-        ('Movie Reviews', 'https://indianexpress.com/section/entertainment/movie-review/feed/'),
-        ('Sunday Eye', 'https://indianexpress.com/print/eye/feed/'),
-        ('Explained', 'https://indianexpress.com/section/explained/feed/'),
-        ('Delhi Confidential', 'https://indianexpress.com/section/delhi-confidential/feed'),
-        ('Economy', 'https://indianexpress.com/print/economy/feed'),
-        ('Express Network', 'https://indianexpress.com/print/express-network/'),
-        ('Research', 'https://indianexpress.com/section/research/feed/'),
-        ('UPSC-CSE Key','https://indianexpress.com/section/upsc-current-affairs/feed/'),
-        ('World','https://indianexpress.com/section/world/feed/'),
-        ('Business', 'https://indianexpress.com/section/business/feed/'),
-        ('Political Pulse', 'https://indianexpress.com/section/political-pulse/feed'),
         ('India', 'https://indianexpress.com/section/india/feed/'),
+        ('Express Network', 'https://indianexpress.com/print/express-network/feed/'),
+        (
+            'Delhi Confidential',
+            'https://indianexpress.com/section/delhi-confidential/feed/'
+        ),
+        ('Op-Ed', 'http://indianexpress.com/section/opinion/feed/'),
+        ('Explained', 'https://indianexpress.com/section/explained/feed/'),
+        (
+            'UPSC-CSE Key',
+            'https://indianexpress.com/section/upsc-current-affairs/feed/'
+        ),
+        ('Research', 'https://indianexpress.com/section/research/feed/'),
+        ('Economy', 'https://indianexpress.com/print/economy/feed/'),
         ('Business', 'https://indianexpress.com/section/business/feed/'),
-        ('Education', 'https://indianexpress.com/section/education/feed/'),
+        ('World', 'https://indianexpress.com/section/world/feed/'),
+        (
+            'Movie Reviews',
+            'https://indianexpress.com/section/entertainment/movie-review/feed/'
+        ),
+        ('Sunday Eye', 'https://indianexpress.com/print/eye/feed/'),
+        # ('Science & Technology', 'http://indianexpress.com/section/technology/feed/'),
+        # ('Political Pulse', 'https://indianexpress.com/section/political-pulse/feed'),
+        # ('Education', 'https://indianexpress.com/section/education/feed/'),
         # Want to add more? go-to:https://indianexpress.com/syndication/
     ]
 
     def get_cover_url(self):
-        soup = self.index_to_soup('https://www.magzter.com/IN/The-Indian-Express-Ltd./The-Indian-Express-Mumbai/Newspaper/')
+        soup = self.index_to_soup(
-        for citem in soup.findAll('meta', content=lambda s: s and s.endswith('view/3.jpg')):
+            'https://www.magzter.com/IN/The-Indian-Express-Ltd./The-Indian-Express-Mumbai/Newspaper/'
+        )
+        for citem in soup.findAll(
+            'meta', content=lambda s: s and s.endswith('view/3.jpg')
+        ):
             return citem['content']
 
     def preprocess_html(self, soup):
+        h2 = soup.findAll('h2')
+        for sub in h2:
+            sub.name = 'h4'
+        for span in soup.findAll(
+            'span', attrs={'class': ['ie-custom-caption', 'custom-caption']}
+        ):
+            span['id'] = 'img-cap'
         for img in soup.findAll('img'):
             noscript = img.findParent('noscript')
             if noscript is not None: