output.txt

http://m.     ########## normal URLs ##########     ?embed=copyright
http://m.wsbtv.com/news/news/minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.     ########## URLs with www in them ##########     ?embed=copyright
http://m.wsbtv.com/news/news/www.minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/www.minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/www.minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/www.minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/www.minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/www.minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/www.minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.     ########## URLs with http:// in them ##########     ?embed=copyright
http://m.wsbtv.com/news/news/http://www.minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/http://www.minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/http://www.minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/http://www.minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/http://www.minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/http://www.minute-minute-updates-winter-storm/nc6BK/?embed=copyright
http://m.wsbtv.com/news/news/http://www.minute-minute-updates-winter-storm/nc6BK/?embed=copyright

URL_transforms.sh

#!/bin/bash

## The regex string to use for all detail page transforms is:
regex='s/([^:]{4,5}:\/\/)?((www|m)\.)?(.*)/http:\/\/m.\4?embed=copyright/'
## It is hardened against transient protocol and subdomain presence.
## It does not account for preexisting query strings.
## That would require 2 separate regexes and is not likely to occur in our feed.


## Here is the test suite.
sed -E -e "$regex" << EOF
     ########## normal URLs ##########     
wsbtv.com/news/news/minute-minute-updates-winter-storm/nc6BK/
m.wsbtv.com/news/news/minute-minute-updates-winter-storm/nc6BK/
www.wsbtv.com/news/news/minute-minute-updates-winter-storm/nc6BK/
http://m.wsbtv.com/news/news/minute-minute-updates-winter-storm/nc6BK/
http://www.wsbtv.com/news/news/minute-minute-updates-winter-storm/nc6BK/
https://m.wsbtv.com/news/news/minute-minute-updates-winter-storm/nc6BK/
https://www.wsbtv.com/news/news/minute-minute-updates-winter-storm/nc6BK/
     ########## URLs with www in them ##########     
wsbtv.com/news/news/www.minute-minute-updates-winter-storm/nc6BK/
m.wsbtv.com/news/news/www.minute-minute-updates-winter-storm/nc6BK/
www.wsbtv.com/news/news/www.minute-minute-updates-winter-storm/nc6BK/
http://m.wsbtv.com/news/news/www.minute-minute-updates-winter-storm/nc6BK/
http://www.wsbtv.com/news/news/www.minute-minute-updates-winter-storm/nc6BK/
https://m.wsbtv.com/news/news/www.minute-minute-updates-winter-storm/nc6BK/
https://www.wsbtv.com/news/news/www.minute-minute-updates-winter-storm/nc6BK/
     ########## URLs with http:// in them ##########     
wsbtv.com/news/news/http://www.minute-minute-updates-winter-storm/nc6BK/
m.wsbtv.com/news/news/http://www.minute-minute-updates-winter-storm/nc6BK/
www.wsbtv.com/news/news/http://www.minute-minute-updates-winter-storm/nc6BK/
http://m.wsbtv.com/news/news/http://www.minute-minute-updates-winter-storm/nc6BK/
http://www.wsbtv.com/news/news/http://www.minute-minute-updates-winter-storm/nc6BK/
https://m.wsbtv.com/news/news/http://www.minute-minute-updates-winter-storm/nc6BK/
https://www.wsbtv.com/news/news/http://www.minute-minute-updates-winter-storm/nc6BK/
EOF