From 9599845b564eceeeaa17bf00457e2d5f98ef9dab Mon Sep 17 00:00:00 2001
From: Nick Sweeting <git@sweeting.me>
Date: Mon, 13 Mar 2023 10:49:26 +0000
Subject: [PATCH] ensure DOM HTML dump is non-zero length file when retrying

---
 archivebox/extractors/dom.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/archivebox/extractors/dom.py b/archivebox/extractors/dom.py
index ec2df073..e1c3571a 100644
--- a/archivebox/extractors/dom.py
+++ b/archivebox/extractors/dom.py
@@ -26,7 +26,8 @@ def should_save_dom(link: Link, out_dir: Optional[Path]=None, overwrite: Optiona
 
     out_dir = out_dir or Path(link.link_dir)
     if not overwrite and (out_dir / 'output.html').exists():
-        return False
+        if (out_dir / 'output.html').stat().st_size > 1:
+            return False
 
     return SAVE_DOM