helix-query.yaml

version: 1
# See https://main--helix-home--adobe.hlx.page/docs/setup-indexing.html for more information.

indices:
  site:
    include:
      - '/**'
    exclude:
      - '**/Document.*'
      - '/drafts/**'
    target: /query-index.xlsx
    properties:
      author:
        select: head > meta[name="author"]
        value: |
          attribute(el, 'content')
      title:
        select: head > meta[property="og:title"]
        value: |
          attribute(el, 'content')
      date:
        select: head > meta[name="publication-date"]
        value: |
          attribute(el, 'content')
      image:
        select: head > meta[property="og:image"]
        value: |
          match(attribute(el, 'content'), 'https:\/\/[^/]+(\/.*)')
      category:
        select: head > meta[name="category"]
        value: |
          attribute(el, 'content')
      topics:
        select: head > meta[name="topics"]
        value: |
          attribute(el, 'content')
      description:
        select: head > meta[name="description"]
        value: |
          attribute(el, 'content')
      lastModified:
        select: none
        value: |
          parseTimestamp(headers['last-modified'], 'ddd, DD MMM YYYY hh:mm:ss GMT')
      robots:
        select: head > meta[name="robots"]
        value: |
          attribute(el, 'content')
      logoWhite:
        select: head > meta[name="logo-white"]
        value: |
          attribute(el, 'content')
      link:
        select: head > meta[name="external-link"]
        value: |
          attribute(el, 'content')