#!/bin/bash
# Pase B (2/2): descarga los recursos (css/js/img/pdf/mp3...) referenciados por las paginas
set -uo pipefail
BASE=/home/rafa/joomla-migration/mirror-antiguo
RUN=$(cat "$BASE/CURRENT_RUN")
DIR=$BASE/runs/$RUN
W=${WORKERS:-3}

[ -s "$DIR/assets-input.txt" ] || { echo "no hay assets-input.txt"; exit 1; }
mkdir -p "$DIR/chunks-assets" "$DIR/logs"
rm -f "$DIR/chunks-assets"/*.txt
split -n l/$W -d --additional-suffix=.txt "$DIR/assets-input.txt" "$DIR/chunks-assets/a-"

date -u +%FT%TZ > "$DIR/logs/passB.start"
for c in "$DIR/chunks-assets"/a-*.txt; do
  n=$(basename "$c" .txt)
  wget --input-file="$c" \
    --force-directories --directory-prefix="$DIR/raw" \
    --no-verbose -e robots=off --no-clobber \
    --user-agent='feadulta-archiver/1.0 (+incident-183; mirror local)' \
    --wait=0.05 --tries=2 --timeout=45 --waitretry=3 \
    --output-file="$DIR/logs/wget-$n.log" &
done
wait
date -u +%FT%TZ > "$DIR/logs/passB.end"
echo "PASE B TERMINADO"
find "$DIR/raw" -type f | wc -l
du -sh "$DIR/raw"
echo "=== errores ==="
grep -hoE 'ERROR [0-9]+' "$DIR/logs"/wget-a-*.log | sort | uniq -c