#!/bin/bash
set -uo pipefail
BASE=/home/rafa/joomla-migration/mirror-antiguo
RUN=$(cat "$BASE/CURRENT_RUN")
D=$BASE/runs/$RUN
grep -hB1 'ERROR 404' "$D/logs"/wget-c-*.log | grep '^http' | sed 's/:$//' | sort -u > "$D/404-passC.txt"
echo "URLs con 404: $(wc -l < "$D/404-passC.txt")"
echo
echo "=== por tipo ==="
printf 'itemlist/user  %s\n' "$(grep -c '/itemlist/user/' "$D/404-passC.txt")"
printf 'item           %s\n' "$(grep -c '/item/' "$D/404-passC.txt")"
printf '/anterior      %s\n' "$(grep -c '/anterior/' "$D/404-passC.txt")"
printf 'resto          %s\n' "$(grep -vcE '/itemlist/user/|/item/|/anterior/' "$D/404-passC.txt")"
echo
echo "=== muestra item ==="
grep '/item/' "$D/404-passC.txt" | head -5
echo "=== muestra itemlist/user ==="
grep '/itemlist/user/' "$D/404-passC.txt" | head -5
echo "=== muestra resto ==="
grep -vE '/itemlist/user/|/item/|/anterior/' "$D/404-passC.txt" | head -8