From 1a4b33cbb21b3a51c6bca19f6043862f7c76bf95 Mon Sep 17 00:00:00 2001 From: Kai Hendry Date: Sat, 14 Jul 2012 17:55:31 +0200 Subject: [PATCH] peel out expand urls code --- expand-urls.sh | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100755 expand-urls.sh diff --git a/expand-urls.sh b/expand-urls.sh new file mode 100755 index 0000000..2972b78 --- /dev/null +++ b/expand-urls.sh @@ -0,0 +1,18 @@ +#!/usr/bin/env bash +# vim: set ts=4 sw=4 + +test -s $1 || exit +test ${1##*.} = 'txt' || exit + +temp=$(mktemp "$1.XXXX") + +IFS='|' +while read -r id date text +do + url=$(echo $text | grep --only-matching --perl-regexp "http(s?):\/\/[^ \"\(\)\<\>]*") + expandedURL=$(curl "$url" -m5 -s -L -I -o /dev/null -w '%{url_effective}') + t=${text/$url/$expandedURL} + echo "$id|$date|$t" +done < $1 > $temp + +mv $temp $1