Extract archbee documentation document tree

archbee-parse.cjs

#!/usr/bin/env node

/**
 * Extracts all documentation pages from Archbee __NEXT_DATA__
 */

const https = require("https")

function fetch(url) {
  return new Promise((resolve, reject) => {
    https
      .get(url, (res) => {
        let data = ""
        res.on("data", (chunk) => (data += chunk))
        res.on("end", () => resolve({ status: res.statusCode, body: data }))
      })
      .on("error", reject)
  })
}

function extractNextData(html) {
  const match = html.match(/<script id="__NEXT_DATA__"[^>]*>([^<]+)<\/script>/)
  if (!match) return null

  try {
    return JSON.parse(match[1])
  } catch (e) {
    console.error("Failed to parse __NEXT_DATA__:", e.message)
    return null
  }
}

function extractPages(nextData) {
  const pages = []

  // Navigate to the document tree
  const docSpace = nextData?.props?.pageProps?._docSpace
  if (!docSpace || !docSpace.publicDocsTree) {
    console.error("Could not find publicDocsTree in data structure")
    return pages
  }

  const tree = docSpace.publicDocsTree

  // Recursively extract all documents from tree
  function extractFromNode(node, ancestors = []) {
    if (!node || !node.id) return

    const docId = node.id.replace("PUBLISHED-", "")
    const urlPath = "/" + node.urlKey
    const title = node.name || node.categoryName

    // Extract just the slug (last segment of urlKey)
    const slug = node.urlKey.split("/").pop()
    const ancestorsPath = ancestors.join("/")

    if (docId && urlPath && title) {
      pages.push({ title, urlPath, ancestors: ancestorsPath, docId })
    }

    // Process children recursively, passing current slug as ancestor
    if (node.children && Array.isArray(node.children)) {
      const childAncestors = [...ancestors, slug]
      node.children.forEach((child) => extractFromNode(child, childAncestors))
    }
  }

  // Extract from each root node
  tree.forEach((node) => extractFromNode(node, []))

  return pages
}

function escapeCSV(value) {
  if (value.includes('"') || value.includes(",") || value.includes("\n")) {
    return '"' + value.replace(/"/g, '""') + '"'
  }
  return value
}

async function main() {
  const docsUrl = process.argv[2]

  if (!docsUrl) {
    console.error("Usage: node archbee-parse.cjs <docs-url>")
    console.error("Example: node archbee-parse.cjs https://docs.your-page.com/")
    process.exit(1)
  }

  console.error("Fetching documentation data...\n")

  const { status, body } = await fetch(docsUrl)

  if (status !== 200) {
    console.error(`Failed to fetch page: HTTP ${status}`)
    process.exit(1)
  }

  const nextData = extractNextData(body)
  if (!nextData) {
    console.error("Could not extract __NEXT_DATA__ from page")
    process.exit(1)
  }

  const pages = extractPages(nextData)

  console.error(`Found ${pages.length} pages.\n`)

  // Output as CSV
  console.log("title,urlPath,ancestors,ID")
  pages.forEach((page) => {
    console.log(
      `${escapeCSV(page.title)},${escapeCSV(page.urlPath)},${escapeCSV(page.ancestors)},${page.docId}`,
    )
  })
}

main().catch(console.error)