find-link-path-sitemap.sh

#!/usr/bin/env bash

# Usage: ./find-link.sh https://example.com/sitemap.xml "/kategori/tittel"

SITEMAP_URL="$1"
SEARCH_STRING="$2"

if [ -z "$SITEMAP_URL" ] || [ -z "$SEARCH_STRING" ]; then
  echo "Usage: $0 <sitemap_url> <search_string>"
  exit 1
fi

# Download and extract URLs from sitemap using sed (BSD-compatible)
urls=$(curl -s "$SITEMAP_URL" | sed -n 's:.*<loc>\(.*\)</loc>.*:\1:p')

for url in $urls; do
  # Fetch HTML content
  html=$(curl -s "$url")

  # Look for exact match of string followed by delimiter (quote, space, >, /, or end of line)
  if echo "$html" | egrep -q "$SEARCH_STRING([\"' >/]|$)"; then
    echo "---- Found in $url ----"
    # Print matching lines with line numbers
    echo "$html" | egrep -n "$SEARCH_STRING([\"' >/]|$)"
    echo
  fi
done