Method extractHeadings

apps/sim/lib/file-parsers/html-parser.ts:248–263

* Extract heading structure for metadata

($: cheerio.CheerioAPI)

   * Extract heading structure for metadata
   */
  private extractHeadings($: cheerio.CheerioAPI): Array<{ level: number; text: string }> {
    const headings: Array<{ level: number; text: string }> = []

    $('h1, h2, h3, h4, h5, h6').each((_, element) => {
      const $element = $(element)
      const tagName = element.tagName?.toLowerCase()
      const level = Number.parseInt(tagName?.charAt(1) || '1', 10)
      const text = $element.text().trim()

      if (text) {
        headings.push({ level, text })
      }
    })

    return headings
  }

  /**
   * Extract links from the document