From 62bf0ab006f78ecc4a7fc5387c110decd817ec98 Mon Sep 17 00:00:00 2001
From: unkn0w7n <51942695+unkn0w7n@users.noreply.github.com>
Date: Thu, 19 Sep 2024 09:18:58 +0530
Subject: [PATCH] Update SciAm

---
 recipes/nytfeeds.recipe            | 10 ++++++----
 recipes/scientific_american.recipe |  4 ++--
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/recipes/nytfeeds.recipe b/recipes/nytfeeds.recipe
index 5e09f0a5b6..c803ae7ec8 100644
--- a/recipes/nytfeeds.recipe
+++ b/recipes/nytfeeds.recipe
@@ -33,9 +33,11 @@ def parse_img_grid(g):
 def parse_byline(byl):
     for b in byl.get('bylines', {}):
         yield '<div>' + b['renderedRepresentation'] + '</div>'
+    yield '<div><b><i>'
     for rl in byl.get('role', {}):
         if ''.join(parse_cnt(rl)).strip():
-            yield '<div><i>' + ''.join(parse_cnt(rl)) + '</i></div>'
+            yield ''.join(parse_cnt(rl))
+    yield '</i></b></div>'
 
 def iso_date(x):
     dt = datetime.fromisoformat(x[:-1]) + timedelta(seconds=time.timezone)
@@ -47,7 +49,7 @@ def parse_header(h):
     if h.get('headline'):
         yield ''.join(parse_types(h['headline']))
     if h.get('summary'):
-        yield '<p class="sub">' +  ''.join(parse_types(h['summary'])) + '</p>'
+        yield '<p><i>' +  ''.join(parse_types(h['summary'])) + '</i></p>'
     if h.get('ledeMedia'):
         yield ''.join(parse_types(h['ledeMedia']))
     if h.get('byline'):
@@ -201,7 +203,6 @@ class nytFeeds(BasicNewsRecipe):
         .byl, .time { font-size:small; color:#202020; }
         .cap { font-size:small; text-align:center; }
         .cred { font-style:italic; font-size:small; }
-        .sub { font-style:italic; }
         em, blockquote { color: #202020; }
         .sc { font-variant: small-caps; }
         .lbl { font-size:small; color:#404040; }
@@ -263,5 +264,6 @@ class nytFeeds(BasicNewsRecipe):
 
     def get_article_url(self, article):
         url = BasicNewsRecipe.get_article_url(self, article)
-        if not re.search(r'/video/|live|/athletic/', url):
+        # you can remove '|/espanol/' from code below to include spanish articles.
+        if not re.search(r'/video/|live|/athletic/|/espanol/', url):
             return url
diff --git a/recipes/scientific_american.recipe b/recipes/scientific_american.recipe
index a5bbd7d609..10ffc5bb1d 100644
--- a/recipes/scientific_american.recipe
+++ b/recipes/scientific_american.recipe
@@ -36,7 +36,7 @@ class ScientificAmerican(BasicNewsRecipe):
 
     keep_only_tags = [
         prefixed_classes(
-            'article_hed- article_dek- article_authors- lead_image- article__content- bio-'
+            'article_hed- article_dek- article_authors- lead_image- article__body- bio-'
         ),
     ]
     remove_tags = [
@@ -45,7 +45,7 @@ class ScientificAmerican(BasicNewsRecipe):
 
     def preprocess_html(self, soup):
         for fig in soup.findAll('figcaption'):
-            for p in fig.findAll('p'):
+            for p in fig.findAll(['p', 'div']):
                 p.name = 'span'
         return soup