From 5f44c236f82d3d02f9dd0061f0a0ab3d8010a3f5 Mon Sep 17 00:00:00 2001 From: Martin Czygan Date: Wed, 2 Jun 2021 01:39:20 +0200 Subject: tasks: cleanup url list --- python/refcat/tasks.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'python') diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py index 7c1fabc..4eefdcc 100644 --- a/python/refcat/tasks.py +++ b/python/refcat/tasks.py @@ -278,7 +278,7 @@ 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 | + LC_ALL=C grep -E 'https?://' zstd -T0 -c > {output} """, n=self.n, -- cgit v1.2.3