From d963a61ea3e4bf278fd62047b258722967cd20c9 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Fri, 3 Sep 2021 10:37:18 -0700
Subject: HTML ingest: skip noisy print() statement
---
python/sandcrawler/html_metadata.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'python')
diff --git a/python/sandcrawler/html_metadata.py b/python/sandcrawler/html_metadata.py
index a1938e9..abcc428 100644
--- a/python/sandcrawler/html_metadata.py
+++ b/python/sandcrawler/html_metadata.py
@@ -661,7 +661,7 @@ def _extract_generic(doc: HTMLParser, selector: str, attrs: List[str], type_name
if skip:
continue
if url:
- print(url, file=sys.stderr)
+ #print(url, file=sys.stderr)
resources.append(dict(url=url.strip(), type=type_name))
return resources
--
cgit v1.2.3