geminispace.info

commit b8fb69f84254a1cfd695683dd50d159e59d9ab14
parent d8fc5a1bec0f0e9d8eac3fad141aa96dddf3385f
Author: Natalie Pendragon <natpen@natpen.net>
Date:   Mon, 22 Jun 2020 16:57:03 -0400

[crawl] Ignore more bad content

Diffstat:
M
gus/crawl.py
 | 
10
++++++++++

1 file changed, 10 insertions(+), 0 deletions(-)
diff --git a/gus/crawl.py b/gus/crawl.py
@@ -147,6 +147,16 @@ EXCLUDED_URL_PREFIXES = [
 
     # youtube mirror
     "gemini://pon.ix.tc/cgi-bin/youtube.cgi?",
+
+    # wikipedia proxy
+    "gemini://wp.pitr.ca/",
+
+    # client torture test
+    "gemini://egsam.pitr.ca/",
+
+    # mozz's chat
+    "gemini://chat.mozz.us/stream",
+    "gemini://chat.mozz.us/submit",
 ]
 
 EXCLUDED_URL_PATHS = [