This script uses wget to generate a WARC that can be read by a player like OpenWayback and places it into a directory. It also handles creation and use of CDX indexes for de-duplication.

wget-warc-generator

#!/bin/bash
if [[ $# -ne 2 ]]; then
  echo "Must only have two arguments, the URL and the collection" >&2
  exit 1
fi

if [[ ! -d "/var/spool/openwayback/files2/${2}" ]]; then
  mkdir "/var/spool/openwayback/files2/${2}"
fi

cd "/var/spool/openwayback/files2/${2}" || exit 1

timestamp=$(date -u +%Y%m%d%H%M%S%N)

wget --delete-after \
  --execute robots=off \
  --no-directories \
  --no-warc-keep-log \
  --page-requisites \
  --span-hosts \
  --user-agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36" \
  --warc-cdx=on \
  $(if [[ -e "${2}.cdx" ]]; then echo "--warc-dedup="${2}.cdx""; fi) \
  --warc-file=at-${timestamp} \
  "${1}" #2> /dev/null

if [[ ! -e "${2}.cdx" ]]; then
  cp at-${timestamp}.cdx "${2}.cdx"
else
  tail -n +2 at-${timestamp}.cdx >> "${2}.cdx"
fi