Rename binscripts more tersely

1 files changed, 25 insertions, 0 deletions

diff --git a/bin/hurl b/bin/hurl
new file mode 100755
index 00000000..23dc7dcc
--- /dev/null
+++ b/bin/hurl
@@ -0,0 +1,25 @@
+#!/usr/bin/env bash
+
+#
+# Extract <a href="..."> URLs from an HTML document or documents.
+#
+# Author: Tom Ryder <tom@sanctum.geek.nz>
+# Copyright: 2016
+# License: Public domain
+#
+
+# Set a sensible locale so that sort(1) doesn't act dumbly
+LANG=C.UTF-8
+export LANG
+
+# Check we have the programs we need
+hash pup || exit
+
+# Emit the content of the args, or stdin
+cat -- "${@:-/dev/stdin}" |  ## shellcheck disable=SC2002
+
+# Pipe it through a pup filter to get all the values of the a href elements
+pup 'a attr{href}' |
+
+# Sort it uniquely
+sort | uniq