helix-query.yaml

version: 1

indices:
  blog:
    include:
      - '/blog/**'
    exclude:
      - '/blog/drafts/**'
    target: /blog/query-index.xlsx
    properties:
      title:
        select: head > meta[property="og:title"]
        value: |
          attribute(el, 'content')
      image:
        select: head > meta[property="og:image"]
        value: |
          match(attribute(el, 'content'), 'https:\/\/[^/]+(\/.*)')
      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')
  blog-de:
    include:
      - '/de/blog/**'
    exclude:
      - '/de/blog/drafts/**'
    target: /de/blog/query-index.xlsx
    properties:
      title:
        select: head > meta[property="og:title"]
        value: |
          attribute(el, 'content')
      image:
        select: head > meta[property="og:image"]
        value: |
          match(attribute(el, 'content'), 'https:\/\/[^/]+(\/.*)')
      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')