#!/bin/bash
# Downloads videos from youtube based on selection from http://thebestofyoutube.com
# (c) Ken Fallon http://kenfallon.com
# Released under the CC-0
# https://www.youtube.com/subscription_manager -> /mnt/media/Videos/channels/subscription_manager.opml
# xmllint --format /mnt/media/Videos/channels/subscription_manager.opml | sponge /mnt/media/Videos/channels/subscription_manager.opml

savepath="/mnt/media/Videos/channels"
subscriptions="${savepath}/subscription_manager.opml"
logfile="${savepath}/log/downloaded.log"
youtubedl="/mnt/media/Videos/youtube-dl/youtube-dl"
DRYRUN="echo DEBUG: "
maxlength=7200 # two hours
#skipcrap="fail |react |live |Best Pets|BLOOPERS|Kids Try"

if [ ! -e "${subscriptions}" ]
then
  echo "Cannot find subscription file \"${subscriptions}\""
  exit 1
fi

if [ -e "${logfile}_getlist" ]
then
  rm -v "${logfile}_getlist"
fi

if [ -e "${logfile}_todo" ]
then
  rm -v "${logfile}_todo"
fi

if [ -e "${logfile}" ]
then
  cp -v "${logfile}" "${logfile}".$(/bin/date +%Y%m%d%H%M%S)
else
  touch "${logfile}"
fi

xmlstarlet sel -T -t -m '/opml/body/outline/outline' -v 'concat( @xmlUrl, " ", @title)' -n "${subscriptions}" | while read subscription title
do
  echo "Getting \"${title}\""
  wget -q "${subscription}" -O - | xmlstarlet sel -T -t -m '/_:feed/_:entry/media:group/media:content' -v '@url' -n - | awk -F '?' '{print $1}'  >> "${logfile}_getlist"
done

count=1
total=$( sort "${logfile}_getlist" | uniq | wc -l )

sort "${logfile}_getlist" | uniq | while read thisvideo
do 
  if [ "$( grep "${thisvideo}" "${logfile}" | wc -l )" -eq 0 ];
  then
    metadata="$( ${youtubedl} --dump-json ${thisvideo} )"
    uploader="$( echo $metadata | jq '.uploader' | awk -F '"' '{print $2}' )"
    title="$( echo $metadata | jq '.title' | awk -F '"' '{print $2}' )"
    upload_date="$( echo $metadata | jq '.upload_date' | awk -F '"' '{print $2}' )"
    id="$( echo $metadata | jq '.id' | awk -F '"' '{print $2}' )"
    duration="$( echo $metadata | jq '.duration' )"
    if [[ -z ${duration} || ${duration} -le 0 ]]
    then
      echo -e "\nError: The duration \"${length}\" is strange. \"${thisvideo}\"."
      continue
    elif [[ ${duration} -ge ${maxlength} ]]
    then
      echo -e "\nFilter: You told me not to download titles over ${maxlength} seconds long \"${title}\", \"${thisvideo}\""
      continue
    fi
    
    if [[ ! -z "${skipcrap}" && $( echo ${title} | egrep -i "${skipcrap}" | wc -l ) -ne 0 ]]
    then
      echo -e "\nSkipping: You told me not to download this stuff. ${uploader}: \"${title}\", \"${thisvideo}\""
      continue
    else
      echo -e "\n${uploader}: \"${title}\", \"${thisvideo}\""
    fi
        
    echo ${thisvideo} >> "${logfile}_todo"
    echo -e $( echo $metadata | jq '.description' ) > "${savepath}/description/${id}.txt"
  else
    echo -ne "\rProcessing ${count} of ${total}"
  fi
  count=$((count+1))
done
echo ""

# Download the list
if [ -e "${logfile}_todo" ];
then
  cat "${logfile}_todo" | ${youtubedl} --batch-file - --ignore-errors --no-mtime --restrict-filenames --format mp4 -o "${savepath}"'/%(uploader)s/%(upload_date)s-%(title)s⋄%(id)s.%(ext)s'
  cat "${logfile}_todo" >> ${logfile}
fi

if [ -e "${logfile}_getlist" ]
then
  rm -v "${logfile}_getlist"
fi

if [ -e "${logfile}_todo" ]
then
  rm -v "${logfile}_todo"
fi

echo "${savedir}"