helix-query.yaml

version: 1

indices:
  website: &website
    include:
      - '/events/**'
    target: /events/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:\/\/[^/]+(\/.*)')
      lastModified:
        select: none
        value: |
          parseTimestamp(headers['last-modified'], 'ddd, DD MMM YYYY hh:mm:ss GMT')
      shortTitle:
        select: head > meta[name="short-title"]
        value: |
          attribute(el, 'content')
      robots:
        select: head > meta[name="robots"]
        value: |
          attribute(el, 'content')

    include:
      - '/events/fragments/consents/*'
    target: /events/fragments/consents/consent-query-index.xlsx
    properties:
      countryCode:
        select: head > meta[name="country-code"]
        value: |
          attribute(el, 'content')
      countryName:
        select: head > meta[name="country-name"]
        value: |
          attribute(el, 'content')
      consentId:
        select: head > meta[name="consent-id"]
        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')