From e8d08955d61c87b493feebd8eb7bd6f752e05280 Mon Sep 17 00:00:00 2001
From: unkn0w7n <51942695+unkn0w7n@users.noreply.github.com>
Date: Wed, 26 Jun 2024 18:54:39 +0530
Subject: [PATCH] Update WSJ

---
 recipes/wsj.recipe     | 21 ++++++++++++---------
 recipes/wsj_mag.recipe | 14 ++++++++------
 2 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/recipes/wsj.recipe b/recipes/wsj.recipe
index 958c041815..a0e2ac25e9 100644
--- a/recipes/wsj.recipe
+++ b/recipes/wsj.recipe
@@ -13,12 +13,16 @@ past_edition = None
 
 def media_bucket(x):
     if x.get('type', '') == 'image':
-        return '<img src="{}"><div class="figc">{}</div>\n'.format(
-            x['manifest-url'], x['caption'] + '<i> ' + x['credit'] + '</i>'
+        if x.get('subtype', '') == 'graphic':
+            return '<br><img src="{}"><div class="figc">{}</div>\n'.format(
+                x['manifest-url'], x['caption'] + '<i> ' + x['credit'] + '</i>'
+            )
+        return '<br><img src="{}"><div class="figc">{}</div>\n'.format(
+            x['manifest-url'].split('?')[0] + '?width=600', x['caption'] + '<i> ' + x['credit'] + '</i>'
         )
     if x.get('type', '') == 'video':
-        return '<a href="{}"><img src="{}"></a><div class="figc">{}</div>\n'.format(
-            x['share_link'], x['thumbnail_url'], x['caption'] + '<i> ' + x['credit'] + '</i>'
+        return '<br><a href="{}"><img src="{}"></a><div class="figc">{}</div>\n'.format(
+            x['share_link'], x['thumbnail_url'].split('?')[0] + '?width=600', x['caption'] + '<i> ' + x['credit'] + '</i>'
         )
     return
 
@@ -90,7 +94,6 @@ class WSJ(BasicNewsRecipe):
                 m_itm = soup.findAll('panel', attrs={'class':'media-item'})
                 if i_lst and m_itm:
                     for x, y in list(zip_longest(m_itm, i_lst)):
-                        x.name = 'p'
                         x.insert_after(BeautifulSoup(y, 'html.parser'))
         return soup
 
@@ -141,9 +144,9 @@ class WSJ(BasicNewsRecipe):
                 break
 
         dt = datetime.fromisoformat(date[:-1]) + timedelta(seconds=time.timezone)
-        dt = dt.strftime('%b %d, %Y')
-        self.log('Downloading ', dt)
-        self.timefmt = ' [' + dt + ']'
+        dt_ = dt.strftime('%b %d, %Y')
+        self.log('Downloading ', dt_)
+        self.timefmt = ' [' + dt_ + ']'
 
         feeds = []
 
@@ -153,7 +156,7 @@ class WSJ(BasicNewsRecipe):
                 if '-pages_' in k:
                     section = k.split('-pages_')[0].replace('_', ' ')
                     if 'MAGAZINE' in section:
-                        if not datetime.now().strftime("%d") == 1:
+                        if not dt.strftime('%d') == 1:
                             continue
                         self.log('Loading Magazine section')
                     self.log(section)
diff --git a/recipes/wsj_mag.recipe b/recipes/wsj_mag.recipe
index 718ee49958..0a82cab0ae 100644
--- a/recipes/wsj_mag.recipe
+++ b/recipes/wsj_mag.recipe
@@ -9,16 +9,19 @@ from calibre.web.feeds.news import BasicNewsRecipe, classes
 
 def media_bucket(x):
     if x.get('type', '') == 'image':
-        return '<img src="{}"><div class="figc">{}</div>\n'.format(
-            x['manifest-url'], x['caption'] + '<i> ' + x['credit'] + '</i>'
+        if x.get('subtype', '') == 'graphic':
+            return '<br><img src="{}"><div class="figc">{}</div>\n'.format(
+                x['manifest-url'], x['caption'] + '<i> ' + x['credit'] + '</i>'
+            )
+        return '<br><img src="{}"><div class="figc">{}</div>\n'.format(
+            x['manifest-url'].split('?')[0] + '?width=600', x['caption'] + '<i> ' + x['credit'] + '</i>'
         )
     if x.get('type', '') == 'video':
-        return '<a href="{}"><img src="{}"></a><div class="figc">{}</div>\n'.format(
-            x['share_link'], x['thumbnail_url'], x['caption'] + '<i> ' + x['credit'] + '</i>'
+        return '<br><a href="{}"><img src="{}"></a><div class="figc">{}</div>\n'.format(
+            x['share_link'], x['thumbnail_url'].split('?')[0] + '?width=600', x['caption'] + '<i> ' + x['credit'] + '</i>'
         )
     return
 
-
 class WSJ(BasicNewsRecipe):
     title = 'WSJ. Magazine'
     __author__ = 'unkn0wn'
@@ -87,7 +90,6 @@ class WSJ(BasicNewsRecipe):
                 m_itm = soup.findAll('panel', attrs={'class':'media-item'})
                 if i_lst and m_itm:
                     for x, y in list(zip_longest(m_itm, i_lst)):
-                        x.name = 'p'
                         x.insert_after(BeautifulSoup(y, 'html.parser'))
         return soup