From d0bf30ec249ba6d329d768c46f2ab08ffbfdf883 Mon Sep 17 00:00:00 2001
From: Martin Czygan <martin.czygan@gmail.com>
Date: Wed, 19 May 2021 21:25:20 +0200
Subject: tasks: keep http only

---
 python/refcat/tasks.py | 1 +
 1 file changed, 1 insertion(+)

(limited to 'python')

diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py
index 6e641ad..877e2be 100644
--- a/python/refcat/tasks.py
+++ b/python/refcat/tasks.py
@@ -297,6 +297,7 @@ class URLList(Refcat):
                           cut -f 3 |
                           skate-cleanup -X -c url -B -S -f 1 |
                           LC_ALL=C sort -u -T {tmpdir} -k1,1 -S25% --parallel 4 |
+                          LC_ALL=C grep ^http |
                           zstd -T0 -c > {output}
                           """,
                           n=self.n,
-- 
cgit v1.2.3