From 07db492808c5fba756271fdcfe203750d27d312b Mon Sep 17 00:00:00 2001
From: unkn0w7n <51942695+unkn0w7n@users.noreply.github.com>
Date: Sat, 10 May 2025 14:21:38 +0530
Subject: [PATCH] Update business_standard_print.recipe

---
 recipes/business_standard_print.recipe | 51 +++++++++++++++++++++-----
 1 file changed, 42 insertions(+), 9 deletions(-)

diff --git a/recipes/business_standard_print.recipe b/recipes/business_standard_print.recipe
index 439284b28d..10fe56a0e2 100644
--- a/recipes/business_standard_print.recipe
+++ b/recipes/business_standard_print.recipe
@@ -38,15 +38,19 @@ class BusinessStandardPrint(BasicNewsRecipe):
     recipe_specific_options = {
         'date': {
             'short': 'The date of the print edition to download (DD-MM-YYYY format)',
-            'long': 'For example, 20-09-2023'
+            'long': 'For example, 20-09-2023',
         }
     }
 
     def get_cover_url(self):
         d = self.recipe_specific_options.get('date')
         if not (d and isinstance(d, str)):
-            soup = self.index_to_soup('https://www.magzter.com/IN/Business-Standard-Private-Ltd/Business-Standard/Newspaper/')
-            for citem in soup.findAll('meta', content=lambda s: s and s.endswith('view/3.jpg')):
+            soup = self.index_to_soup(
+                'https://www.magzter.com/IN/Business-Standard-Private-Ltd/Business-Standard/Newspaper/'
+            )
+            for citem in soup.findAll(
+                'meta', content=lambda s: s and s.endswith('view/3.jpg')
+            ):
                 return citem['content']
 
     def parse_index(self):
@@ -81,7 +85,7 @@ class BusinessStandardPrint(BasicNewsRecipe):
                 desc = article['sub_heading']
                 url = 'https://www.business-standard.com' + article['article_url']
                 self.log('\t', title, '\n\t', desc, '\n\t\t', url)
-                articles.append({'title': title, 'description':desc, 'url': url})
+                articles.append({'title': title, 'description': desc, 'url': url})
             if articles:
                 feeds.append((section, articles))
         return feeds
@@ -105,33 +109,59 @@ class BusinessStandardPrint(BasicNewsRecipe):
         cat = subhead = lede = auth = caption = ''
 
         if 'defaultArticleCat' in data and data['defaultArticleCat'] is not None:
-            if 'h1_tag' in data['defaultArticleCat'] and data['defaultArticleCat']['h1_tag'] is not None:
+            if (
+                'h1_tag' in data['defaultArticleCat']
+                and data['defaultArticleCat']['h1_tag'] is not None
+            ):
                 cat = '<div class="cat">' + data['defaultArticleCat']['h1_tag'] + '</div>'
 
         if 'metaDescription' in data and data['metaDescription'] is not None:
             subhead = '<p class="sub">' + data['metaDescription'] + '</p>'
             self.art_desc = data['metaDescription']
 
-        date = (datetime.fromtimestamp(int(data['publishDate']))).strftime('%b %d, %Y | %I:%M %p')
+        date = (datetime.fromtimestamp(int(data['publishDate']))).strftime(
+            '%b %d, %Y | %I:%M %p'
+        )
 
         authors = []
         if 'articleMappedMultipleAuthors' in data:
             for aut in data['articleMappedMultipleAuthors']:
                 authors.append(data['articleMappedMultipleAuthors'][str(aut)])
-        auth = '<div><p class="auth">' + ', '.join(authors) + ' | ' + data['placeName'] + ' | ' + date + '</p></div>'
+        auth = (
+            '<div><p class="auth">'
+            + ', '.join(authors)
+            + ' | '
+            + data['placeName']
+            + ' | '
+            + date
+            + '</p></div>'
+        )
 
         if 'featuredImageObj' in data:
             if 'url' in data['featuredImageObj']:
                 if img_url is not None:
                     lede = '<p class="cap"><img src="{}">'.format(img_url)
                 else:
-                    lede = '<p class="cap"><img src="{}">'.format(data['featuredImageObj']['url'])
+                    lede = '<p class="cap"><img src="{}">'.format(
+                        data['featuredImageObj']['url']
+                    )
             if 'alt_text' in data['featuredImageObj']:
                 caption = '<span>' + data['featuredImageObj']['alt_text'] + '</span></p>'
 
         body = data['htmlContent']
 
-        return '<html><body>' + cat + title + subhead + auth + lede + caption + '<div><br>' + body + '</div></body></html>'
+        return (
+            '<html><body>'
+            + cat
+            + title
+            + subhead
+            + auth
+            + lede
+            + caption
+            + '<div><br>'
+            + body
+            + '</div></body></html>'
+        )
 
     def preprocess_html(self, soup):
         for img in soup.findAll('img'):
@@ -141,4 +171,7 @@ class BusinessStandardPrint(BasicNewsRecipe):
         for attr in self.remove_attributes:
             for x in soup.findAll(attrs={attr: True}):
                 del x[attr]
+        for br in soup.findAll('small', attrs={'class': 'brtag'}):
+            br.name = 'br'
+            br.clear()
         return soup