PandaScript

A PandaScript is a web automation script that can be run directly by Lightpanda browser.

No environment to set up like NodeJS or Python, no Puppeteer/Playwright to write, no CDP serialization cost, no LLM required: just vanilla Javascript with a small set of native primitives.

Use normal JavaScript variables, functions, loops, objects, arrays, JSON.parse, JSON.stringify, and other standard ECMAScript built-ins.

It’s reproducible, deterministic and token-free (no LLM required).

To run a PandaScript:

lightpanda agent <my_script>.js

Runtime Environment

Agent scripts run in their own V8 context. That context is separate from the web page’s JavaScript context.

• It is not the browser page environment. There is no window, document, DOM, localStorage, navigator, or page global state in the agent script. Read page data with extract(...), or explicitly run page JavaScript with evaluate(...) when that is the right tool.
• It is not Node.js. There is no require, process, fs, path, npm package loading, command-line argument API, or Node network/filesystem API.
• Page scripts cannot see agent variables or Lightpanda primitives. Agent scripts cannot directly see page variables.
• The global evaluate(...) primitive runs JavaScript in the page context, distinct from the agent context’s own native eval.
• Agent variables persist for the lifetime of one script run, across navigations and primitive calls. A later lightpanda agent script.js run starts with a fresh agent context.
• The installed primitives are synchronous and blocking. Do not write an async/await automation contract around them. Scripts compile as classic scripts, so top-level await is a SyntaxError; promise callbacks (.then) only run after the script body finishes, never in between primitive calls.
• Tool failures throw JavaScript Error exceptions and stop execution unless you catch them.
• The script’s completion value (its last top-level expression) is printed automatically (objects and arrays as JSON; other values coerced). End a script with the bare expression you want as output, e.g. a final extract({ ... }); or results;. console.log(...) is for extra or debug output and does not JSON-format objects.

The agent context includes a small console object:

console.log("printed to stdout");
console.info("printed to stdout");
console.debug("printed to stdout");
console.warn("printed to stderr");
console.error("printed to stderr");

Values And Return Types

Most primitives return the browser tool’s result text as a JavaScript string. extract(...) is the exception: it returns extracted data as a normal JavaScript value, so local script logic can use it directly. The result mirrors your schema: an object schema returns an object keyed by your fields (even with a single field), and a bare array schema returns an array:

const page = new Page();
await page.goto("https://news.ycombinator.com/");
 
const data = page.extract({
  title: "title",
  stories: [{
    selector: "tr.athing",
    limit: 5,
    fields: {
      id: { attr: "id" },
      title: ".titleline > a"
    }
  }]
});
 
data; // printed automatically as JSON

Destructure when a single field is all you need:

const { stories } = page.extract({
  stories: [{
    selector: "tr.athing",
    limit: 5,
    fields: {
      id: { attr: "id" },
      title: ".titleline > a"
    }
  }]
});
 
for (const story of stories) {
  console.log(story.title);
}

evaluate(...) still returns the page evaluate tool result text. When page evaluate(...) returns an object or array, that text is JSON.

Primitive arguments must be JSON-serializable. Strings, numbers, booleans, arrays, plain objects, and null work. undefined, functions, symbols, and cyclic objects do not.

Installed Primitives

Only recorded browser primitives are installed globally:

goto returns at the load event (a fast snapshot). When a page’s content is still loading (rendered by post-load JS), call waitForState("networkidle") before reading. waitForState’s state accepts "load", "domcontentloaded", "networkalmostidle", "networkidle", or "done". goto’s timeout defaults to 10000 ms; the waitFor* timeouts default to 5000 ms.

The [, { … }] is an optional trailing options object: leading arguments are positional (waitForSelector("#row", { timeout: 2000 })), and the options ride in a final object. Passing a single object with everything (waitForSelector({ selector: "#row", timeout: 2000 })) is equivalent; that’s the shape /save records into saved scripts. An option can’t be a bare positional, though: waitForSelector("#row", 2000) is an error. A null positional omits that field (press(null, "Enter") presses on the focused element), and setting the same field positionally and in the options object (goto(url, { url: ... })) is an invalid arguments error.

Script primitives address elements by CSS selector only. The tools that hand out backendNodeIds (tree, findElement, nodeDetails) aren’t installed in the script context, and a raw node ID wouldn’t survive replay anyway. When you’re exploring in the REPL and have a backendNodeId (e.g. the leading number on a /tree line, or a /findElement hit) run /nodeDetails backendNodeId=<id> to get a durable CSS selector, then paste that into your script.

Navigation

Use goto(...) to navigate to an URL:

const page = new Page();
await page.goto("https://example.com");
 
await page.goto({
  url: "https://example.com/app",
  timeout: 15000
});

The call returns a status string and throws if navigation fails. A timeout does not throw: the call returns "Navigation started but the page did not finish loading before the timeout." and the page stays in whatever state it reached. Check the return value, or follow with waitForState(...) / waitForSelector(...), when completeness matters.

Structured Extraction

Use page.extract(...) to read data from the current page without writing page-side JavaScript. This is the preferred bridge from page content into local agent logic.

const result = page.extract({
  heading: "h1",
  links: [{
    selector: "a",
    limit: 10,
    fields: {
      text: "",
      href: { attr: "href" }
    }
  }]
});

The schema forms are:

Return shape follows the top-level schema:

• extract({ title: "h1" }) returns { title: "..." }.
• extract({ title: "h1", links: [{ selector: "a" }] }) returns an object with both fields.
• extract({ links: [{ selector: "a" }] }) returns { links: [...] }. An object schema always returns an object, even with a single field.
• extract([{ selector: "a" }]) is shorthand for a single anonymous array extraction and returns the array directly.

Every value is a string (trimmed text or a raw attribute) or null; parse numbers in script logic. An array field that matches nothing yields [] without complaint (a page with zero comments is a valid result), but if every field in the schema misses, extract(...) throws no schema selector matched any element; treat that as “my selectors are wrong”, not “the page is empty”.

extract(...) reads only the current page. For list-to-detail scraping: capture the list, then loop in the script (goto each row’s URL and extract the detail). The local agent context keeps the data across navigations, so the assembly happens in plain JavaScript. See the complete example below.

When passing an object directly to extract(...), the runtime serializes it as the extractor schema. These forms are equivalent:

page.extract({ title: "h1" });
page.extract({ schema: { title: "h1" } });
page.extract('{ "title": "h1" }');

The wrapped form accepts only schema: the REPL’s save= option does not exist in scripts (extract({ schema: ..., save: ... }) is rejected). Keep results in local variables instead.

Use local variables to keep extracted data available to later script logic:

const data = page.extract({ title: "title" });

Page JavaScript

evaluate(...) is the explicit escape hatch into the current page’s JavaScript context. Its script string runs where window and document exist.

await page.goto("https://example.com");
 
const title = page.evaluate("document.title");
console.log(title);

Keep the boundary clear:

const selector = "h1";
 
// Good: local agent logic builds an extract schema.
const data = page.extract({ heading: selector });
 
// Bad: page evaluate cannot see local agent variables.
page.evaluate("document.querySelector(selector).textContent");

Page evaluate(...) cannot call goto, extract, or other agent primitives. Agent scripts cannot access document directly. If you need page DOM data, prefer extract(...); use evaluate(...) only for page behavior that extraction cannot express.

waitForScript(...) also evaluates in the page context, repeatedly, until the expression is truthy or the timeout expires:

page.waitForScript("document.querySelectorAll('.row').length >= 5");

Interaction Primitives

The action primitives operate on the current page. Most take one object whose fields match the browser tool schema:

page.click({ selector: "a.login" });
page.fill({ selector: "input[name='acct']", value: "$LP_HN_USERNAME" });
page.fill({ selector: "input[name='pw']", value: "$LP_HN_PASSWORD" });
page.press({ key: "Enter" });
 
page.waitForSelector("#logout");
 
page.hover({ selector: "#menu" });
page.selectOption({ selector: "select[name='country']", value: "FR" });
page.setChecked({ selector: "input[name='terms']", checked: true });
page.setChecked({ selector: "input[name='newsletter']", checked: false });
 
page.scroll({ y: 600 });
page.scroll();

setChecked defaults checked to true when the field is omitted (setChecked("#chk") checks the box). press’s leading positional is the optional selector, not key: a bare press("Enter") binds "Enter" to selector and fails. Press on the focused element with press({ key: "Enter" }) or press(null, "Enter"); target an element with press("#search", "Enter") or press({ key: "Enter", selector: "#search" }).

$LP_* placeholders in string arguments are resolved inside the Lightpanda process. This keeps credentials out of recorded scripts and LLM prompts. In recordings, resolved LP_* values are scrubbed back to placeholders.

Error Handling

Primitive failures throw JavaScript exceptions:

try {
  page.waitForSelector({ selector: "#dashboard", timeout: 1000 });
} catch (err) {
  console.error("dashboard did not appear:", err.message);
  throw err;
}

Common failures:

Complete Example

This script opens Hacker News, extracts five stories, visits each comments page, and prints one JSON object. The looping and object assembly happen in the local agent script, not in the page.

const HN = "https://news.ycombinator.com";
 
const page = new Page();
await page.goto(HN);
 
const { stories } = page.extract({
  stories: [{
    selector: "tr.athing",
    limit: 5,
    fields: {
      id: { attr: "id" },
      title: ".titleline > a",
      url: { selector: ".titleline > a", attr: "href" }
    }
  }]
});
 
for (const story of stories) {
  story.comments = [];
  if (!story.id) continue;
 
  await page.goto(`${HN}/item?id=${story.id}`);
  const { comments } = page.extract({
    comments: [{
      selector: "tr.athing.comtr:has(.commtext)",
      limit: 3,
      fields: {
        author: ".hnuser",
        text: ".commtext"
      }
    }]
  });
  story.comments = comments;
}
 
stories; // printed automatically as JSON