From 5b07a1126cfed92dae1b6e8297c5897b6e113ae5 Mon Sep 17 00:00:00 2001
From: Nick Sweeting <git@sweeting.me>
Date: Wed, 3 Jan 2024 19:00:19 -0800
Subject: [PATCH] add comment about why DOM is preferred over singlefile for
 readability parsing

---
 archivebox/extractors/readability.py | 2 ++
 archivebox/templates/admin/base.html | 1 +
 2 files changed, 3 insertions(+)

diff --git a/archivebox/extractors/readability.py b/archivebox/extractors/readability.py
index f849d909..574dc09c 100644
--- a/archivebox/extractors/readability.py
+++ b/archivebox/extractors/readability.py
@@ -99,6 +99,8 @@ def save_readability(link: Link, out_dir: Optional[str]=None, timeout: int=TIMEO
     except (Exception, OSError) as err:
         status = 'failed'
         output = err
+
+        # prefer Chrome dom output to singlefile because singlefile often contains huge url(data:image/...base64) strings that make the html too long to parse with readability
         cmd = [cmd[0], './{dom,singlefile}.html']
     finally:
         timer.end()
diff --git a/archivebox/templates/admin/base.html b/archivebox/templates/admin/base.html
index a29df4f5..5d4d4cc5 100644
--- a/archivebox/templates/admin/base.html
+++ b/archivebox/templates/admin/base.html
@@ -177,6 +177,7 @@
                 }
             </script>
         {% endif %}
+        
         <script>
             $ = django.jQuery;
             $.fn.reverse = [].reverse;