#!/bin/bash rec_fetch() { echo fetching $1 curl --no-progress-meter https://www.sco.com/developers/gabi/latest/$1 -o $1 # Handle following link tags: # # # # # for page in $(grep href $1 |\ sed 's/.*href="\{0,1\}\([a-zA-Z._0-9]*\)"\{0,1\}[#>].*/\1/g' |\ sort | uniq); do if [[ -z $page || -f $page || ${page##*.} != html ]]; then continue; fi rec_fetch $page done } rec_fetch contents.html