Merge branch 'master' of https://github.com/unkn0w7n/calibre

recipes/hindu.recipe

@@ -40,7 +40,7 @@ class TheHindu(BasicNewsRecipe):
                      'erode, hyderabad, international, kochi, kolkata,\n'
                      'kozhikode, madurai, mangalore, mumbai, thiruvananthapuram, '
                      'tiruchirapalli, vijayawada, visakhapatnam'),
-            'default': 'international'
+            'default': 'chennai'
         },
         'date': {
             'short': 'The date of the edition to download (YYYY-MM-DD format)',
@@ -68,7 +68,7 @@ class TheHindu(BasicNewsRecipe):
         return soup
 
     def parse_index(self):
-        local_edition = 'th_international'
+        local_edition = 'th_chennai'
         d = self.recipe_specific_options.get('location')
         if d and isinstance(d, str):
             local_edition = 'th_' + d

recipes/hindufeeds.recipe

@@ -4,7 +4,7 @@ from calibre.web.feeds.news import BasicNewsRecipe, classes
 
 
 class TheHindufeeds(BasicNewsRecipe):
-    title = 'The Hindu (Feeds)'
+    title = 'The Hindu News'
     __author__ = 'unkn0wn'
     description = 'The Hindu, based on RSS feeds.'
     language = 'en_IN'
@@ -20,6 +20,7 @@ class TheHindufeeds(BasicNewsRecipe):
         .caption {font-size:small; text-align:center;}
         .author, .dateLine, .publish-time {font-size:small; font-weight:bold;}
         .subhead, .subhead_lead, .bold {font-weight:bold;}
+        .update-publish-time, .publish-time-new {font-size:small; }
         img {display:block; margin:0 auto;}
         .italic {font-style:italic; color:#202020;}
     '''
@@ -28,7 +29,7 @@ class TheHindufeeds(BasicNewsRecipe):
         'days': {
             'short': 'Oldest article to download from this news source. In days ',
             'long': 'For example, 0.5, gives you articles from the past 12 hours',
-            'default': str(oldest_article)
+            'default': str(oldest_article),
         }
     }
 
@@ -40,33 +41,35 @@ class TheHindufeeds(BasicNewsRecipe):
 
     ignore_duplicate_articles = {'url'}
 
-    keep_only_tags = [
+    keep_only_tags = [classes('article-section')]
-        classes('article-section')
-    ]
 
     remove_tags = [
         dict(name='button'),
-        dict(attrs={'target':'_self'}),
+        dict(attrs={'target': '_self'}),
         classes(
-            'hide-mobile comments-shares share-page editiondetails breadcrumb'
+            'hide-mobile comments-shares share-page editiondetails '
-            ' related-topics related-stories also-read premium-label'
+            'breadcrumb related-stories-inline related-topics related-stories '
-        )
+            'also-read premium-label article-ad'
+        ),
     ]
 
     def preprocess_html(self, soup):
-        for cap in soup.findAll('p', attrs={'class':'caption'}):
+        for cap in soup.findAll('p', attrs={'class': 'caption'}):
             cap.name = 'figcaption'
-        for img in soup.findAll('img', attrs={'data-original':True}):
+        for img in soup.findAll('img', attrs={'data-original': True}):
             if img['data-original'].endswith('1x1_spacer.png'):
                 source = img.findPrevious('source', srcset=True)
                 img.extract()
                 if source:
-                    source['src'] = source['srcset'].replace('_320','_1200')
+                    source['src'] = source['srcset'].replace('_320', '_1200')
                     source.name = 'img'
             else:
                 img['src'] = img['data-original']
-        for img in soup.findAll('img', attrs={'data-src-template':True}):
+        for img in soup.findAll('img', attrs={'data-src-template': True}):
             img['src'] = img['data-src-template']
+        if h2 := soup.find(**classes('sub-title')):
+            h2.name = 'p'
+            h2['class'] = 'italic'
         return soup
 
     def postprocess_html(self, soup, first_fetch):
@@ -76,15 +79,15 @@ class TheHindufeeds(BasicNewsRecipe):
 
     def get_cover_url(self):
         soup = self.index_to_soup('https://www.thehindu.com/todays-paper/')
-        if cover := soup.find(attrs={'class':'hindu-ad'}):
+        if cover := soup.find(attrs={'class': 'hindu-ad'}):
             return cover.img['src']
 
     # https://www.thehindu.com/rssfeeds/
     feeds = [
+        ('Opinion', 'https://www.thehindu.com/opinion/feeder/default.rss'),
         ('India', 'https://www.thehindu.com/news/national/feeder/default.rss'),
         ('States', 'https://www.thehindu.com/news/states/feeder/default.rss'),
         # ('Cities', 'https://www.thehindu.com/news/cities/feeder/default.rss'),
-        ('Opinion', 'https://www.thehindu.com/opinion/feeder/default.rss'),
         ('Business', 'https://www.thehindu.com/business/feeder/default.rss'),
         ('World', 'https://www.thehindu.com/news/international/feeder/default.rss'),
         # ('Sport', 'https://www.thehindu.com/sport/feeder/default.rss'),
@@ -92,5 +95,5 @@ class TheHindufeeds(BasicNewsRecipe):
         # ('Crossword', 'https://crossword.thehindu.com/?utm_source=thehindu&utm_medium=mainmenufeeder/default.rss'),
         ('Science', 'https://www.thehindu.com/sci-tech/science/feeder/default.rss'),
         ('Life and Style', 'https://www.thehindu.com/life-and-style/feeder/default.rss'),
-        ('thRead', 'https://www.thehindu.com/thread/feeder/default.rss')
+        ('thRead', 'https://www.thehindu.com/thread/feeder/default.rss'),
     ]