Update substack.recipe

recipes/substack.recipe

@@ -6,6 +6,7 @@
 # Copyright:    Nathan Cook (nathan.cook@gmail.com)
 ##
 # Written:      2020-12-18
+# Updated:      2024-11-04
 ##
 
 __license__ = 'GNU General Public License v3 – https://www.gnu.org/licenses/gpl-3.0.html'
@@ -14,6 +15,7 @@ __version__ = 'v0.1.1'
 __date__ = '2020-12-19'
 __author__ = 'topynate'
 
+import re
 import json
 
 from calibre.web.feeds.news import BasicNewsRecipe
@@ -21,21 +23,36 @@ from mechanize import Request
 
 
 class Substack(BasicNewsRecipe):
-    title          = 'Substack'
-    __author__     = 'topynate'
+    title = 'Substack'
+    __author__ = 'topynate, unkn0wn'
+    description = 'Use advanced menu if you want to add your own substack handles.'
     oldest_article = 7
     language = 'en'
     max_articles_per_feed = 100
-    auto_cleanup   = True
+    auto_cleanup = True
+    auto_cleanup_keep = '//*[@class="subtitle"]'
     needs_subscription = 'optional'
     use_embedded_content = False
+    masthead_url = 'https://substack.com/img/substack_wordmark.png'
+    cover_url = 'https://substack.com/img/substack.png'
+    extra_css = '.captioned-image-container, .image-container {font-size: small;}'
 
     recipe_specific_options = {
+        'auths': {
+            'short': 'enter the @handles you subscribe to:\nseperated by a space',
+            'long': 'julianmacfarlane ianleslie .... ....',
+            'default': 'julianmacfarlane ianleslie thesalvo',
+        },
         '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),
+        },
+        'res': {
+            'short': 'For hi-res images, select a resolution from the\nfollowing options: 800, 1000, 1200 or 1500',
+            'long': 'This is useful for non e-ink devices, and for a lower file size\nthan the default, use 400 or 300.',
+            'default': '600',
+        },
     }
 
     def __init__(self, *args, **kwargs):
@@ -44,12 +61,12 @@ class Substack(BasicNewsRecipe):
         if d and isinstance(d, str):
             self.oldest_article = float(d)
 
-# Every Substack publication has an RSS feed at https://{name}.substack.com/feed.
-# The same URL provides either all posts, or all free posts + previews of paid posts,
-# depending on whether you're logged in.
-    feeds          = [
-        ('Novum Lumen', 'https://novumlumen.substack.com/feed'),    # gratuitously self-promotional example
-    ]
+    # Every Substack publication has an RSS feed at https://{name}.substack.com/feed.
+    # The same URL provides either all posts, or all free posts + previews of paid posts,
+    # depending on whether you're logged in.
+    # feeds          = [
+    #     ('Novum Lumen', 'https://novumlumen.substack.com/feed'),    # gratuitously self-promotional example
+    # ]
 
     def get_browser(self):
         br = BasicNewsRecipe.get_browser(self)
@@ -70,3 +87,24 @@ class Substack(BasicNewsRecipe):
             if res.getcode() != 200:
                 raise ValueError('Login failed, check username and password')
         return br
+
+    def get_feeds(self):
+        ans = []
+        u = self.recipe_specific_options.get('auths')
+        if u and isinstance(u, str):
+            for x in u.split():
+                ans.append('https://' + x.replace('@', ' ') + '.substack.com/feed')
+        return ans
+
+    def preprocess_html(self, soup):
+        res = '600'
+        w = self.recipe_specific_options.get('res')
+        if w and isinstance(w, str):
+            res = w
+        for img in soup.findAll('img', attrs={'src': True}):
+            img['src'] = re.sub(r'w_\d+', 'w_' + res, img['src'])
+        for src in soup.findAll(['source', 'svg']):
+            src.extract()
+        for but in soup.findAll(attrs={'class': ['button-wrapper']}):
+            but.extract()
+        return soup