#!/bin/bash TMP="/tmp/danish-lessons" mkdir -p "${TMP}" cd "${TMP}" URL_BASE="http://theprint.vox.com/library/post" AUDIO_BASE="http://theprint.vox.com/library/audio" LIMIT=2 POST=1 while [ $POST -le $(($LIMIT+1)) ] do F="danish-lesson-${POST}.html" wget "${URL_BASE}/${F}" 1> /dev/null 2> /dev/null for line in $(cat ${F}) do if [[ $line =~ "[a-z0-9]{34}\.html" ]] then AUDIO=${BASH_REMATCH} wget "${AUDIO_BASE}/${AUDIO}" 1> /dev/null 2> /dev/null for line in $(cat ${AUDIO} | egrep " /dev/null 2> /dev/null mv "${LOCAL_FILE}" "danish-lesson-${POST}.mp3" fi fi done fi done POST=$(($POST+1)) done rm *.html*