set a useragent

2020-12-15 10:17:28 -05:00 · 2020-12-15 10:17:28 -05:00 · 2b46e8899f
parent 8c4421108b
commit 2b46e8899f
1 changed files with 9 additions and 3 deletions
--- a/urls.sh
+++ b/urls.sh
@ -1,3 +1,9 @@
-wget --spider --force-html -r -l1 -H $@ 2>&1 \
-  | grep '^--' | awk '{ print $3 }' \
-  | grep -v '\.\(css\|js\|png\|gif\|jpg\|txt\|ico\|ttf\|svg\)$'
+wget --spider --force-html -r -l1 -H -U 'searplbot/1.0' $@ 2>&1 | tee wg
+
+grep '^--' wg | awk '{ print $3 }' \
+  | grep -v '\.\(css\|js\|png\|gif\|jpg\|txt\|ico\|ttf\|svg\)$' \
+  | tee ur
+
+sleep 10
+
+php crawl.php $(cat ur)