Cuiar
Sign inDownload

List every page of a website in a sheet

Each page with its title, description, H1, word count and last update, from the sitemap.

  • You start it: When you start it
Use in CuiarRun from your AI agent

What it does

The task

Open the sitemap of site url, usually at /sitemap.xml, and list each page in it. When there is no sitemap, follow the menu and the internal links, up to max pages pages. For each page, record the URL, the title, the meta description, the H1, the word count, the date of the last update, the language and the canonical URL. Put one row for each page in a new Google Sheet. Mark the pages with no title, a duplicate title, or fewer than 200 words.

  • It works in any website and Google Sheets, in the workspace you pick, and signs in with passwords from your Cuiar vault.
  • It runs once, when you start it.

What you give it

BlankWhat to giveExample
site urlThe website to listhttps://crumbandcrust.com
max pagesThe largest number of pages to read when there is no sitemap500

What you get back

An example run with the example values above. Your run uses your own data.

Pages: 612, from the sitemap of crumbandcrust.com

Columns: URL, Title, Description, H1, Words, Updated, Language, Canonical

No title: 4

Duplicate titles: 23 (most are /recipes/page/2 to /recipes/page/24)

Fewer than 200 words: 58

Not updated since 2023: 141

Sheet: Site inventory, 612 rows

Run it in Cuiar

  1. 01

    Open it

    Click Use in Cuiar on this page. The side panel opens with the task in the composer.

  2. 02

    Fill in 2 blanks

    Type site url and max pages. Tab moves to the next blank.

  3. 03

    Run it

    Run sends it to the agent. Follow each step in the panel, and stop it at any time.

From the terminal

cuiar exec "Open the sitemap of https://crumbandcrust.com, usually at /sitemap.xml, and list each page in it. When there is no sitemap, follow the menu and the internal links, up to 500 pages. For each page, record the URL, the title, the meta description, the H1, the word count, the date of the last update, the language and the canonical URL. Put one row for each page in a new Google Sheet. Mark the pages with no title, a duplicate title, or fewer than 200 words."

Run it from your AI agent

Claude Code, Codex, Cursor and other MCP clients reach Cuiar at https://mcp.cuiar.com/mcp. Add the server one time, then ask for the task in plain words, or call run_task yourself.

1. Add Cuiar to Claude Code

claude mcp add --transport http cuiar https://mcp.cuiar.com/mcp

2. Ask your agent

Use the Cuiar tool run_task to run my "List every page of a website in a sheet" template with site url = https://crumbandcrust.com; max pages = 500.

Setup for other agents: AI agents.

The tool call

{
  "name": "run_task",
  "arguments": {
    "task": "Open the sitemap of https://crumbandcrust.com, usually at /sitemap.xml, and list each page in it. When there is no sitemap, follow the menu and the internal links, up to 500 pages. For each page, record the URL, the title, the meta description, the H1, the word count, the date of the last update, the language and the canonical URL. Put one row for each page in a new Google Sheet. Mark the pages with no title, a duplicate title, or fewer than 200 words."
  }
}

Related templates

All data templates