#!/bin/bash
# Fuente F3 del plan: inventario historico de URLs segun Internet Archive.
# No toca el origen ni produccion; es una consulta de solo lectura a web.archive.org.
set -uo pipefail
BASE=/home/rafa/joomla-migration/mirror-antiguo
INV=$BASE/inventory
mkdir -p "$INV"

for host in antiguo.feadulta.com feadulta.com; do
  out="$INV/wayback-${host%%.*}.txt"
  echo "-> $host"
  curl -s --max-time 300 \
    "https://web.archive.org/cdx/search/cdx?url=${host}*&output=text&fl=original&collapse=urlkey&limit=200000" \
    > "$out"
  echo "   $(wc -l < "$out") URLs"
done
wc -l "$INV"/wayback-*.txt