From 13a3e1d128b62a5c3928f17856bb2006b3e52f99 Mon Sep 17 00:00:00 2001 From: lickthecheese Date: Fri, 20 Mar 2020 10:23:33 -0400 Subject: [PATCH] fixed cleaning script --- clean | 2 +- crawly | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/clean b/clean index 0eac0fc..70bbda6 100755 --- a/clean +++ b/clean @@ -1,7 +1,7 @@ #!/bin/bash mv urls.txt urls.txt.bak -cat urls.txt.bak | sort | uniq > urls.txt +cat urls.txt.bak | sort | uniq -w 20 > urls.txt rm urls.txt.bak diff --git a/crawly b/crawly index 2977dac..a93b436 100755 --- a/crawly +++ b/crawly @@ -52,7 +52,7 @@ visit $fn urls.txt done mv urls.txt urls.txt.bak -cat urls.txt.bak | sort | uniq > urls.txt +cat urls.txt.bak | sort | uniq -w 20 > urls.txt rm urls.txt.bak find ./content/ -type 'f' -size -100c -delete