solvecdp

Lightweight Chrome Debug Protocol (CDP) client for solveit

fastcdp provides an async Python client for the Chrome DevTools Protocol (CDP) over solveit’s js bridge. It exposes every CDP domain as a Python attribute with auto-generated signatures and docstrings — e.g. await cdp.page.navigate(url=...).

It includes event subscription via cdp.on()/cdp.wait_event(), navigation helpers (goto, wait_for_selector, wait_for), screenshot capture, and accessibility tree access. A cdp_search utility lets you search CDP commands by name or description. For use inside safepyrun sandboxes, cdp_yolo() registers all CDP classes.

Installation

You must install the solveit-chrome extension before using solvecdp.

Solveit already has solvecdp installed, but if you want to install the latest you can get it from pypi:

$ pip install solvecdp

How to use

from solvecdp import *

The JsCDP class

Every CDP domain is available as an attribute with auto-generated signatures. You can search for commands with cdp_search:

cdp_search('screenshot')

"Emulation.setVisibleSize: Resizes the frame/viewport of the page. Note that this does not affect the frame's container\n(e.g. browser window). Can \nHeadlessExperimental.beginFrame: Sends a BeginFrame to the target and returns when the frame was completed. Optionally captures a\nscreenshot from the res\n  evt Overlay.screenshotRequested: Fired when user asks to capture screenshot of some area on the page.\nPage.captureScreenshot: Capture page screenshot."

Create a new page:

jc = await JsCDP.new()

Go to a page:

await jc.goto('https://httpbin.org/forms/post')

Eval js:

await jc.eval('document.title')

'6. httpbin.org/forms/post'

Or you can wait_for any js expression to be truthy, and have it returned:

await jc.wait_for('document.title')

'6. httpbin.org/forms/post'

Take a screenshot of the page:

img = await jc.screenshot()

Clean up when done:

await jc.close()

See JsCDP docs for full details.

Filling forms

page = await JsCDP.new(url='https://httpbin.org/forms/post')

For finding elements to interact with, use ax_tree:

root = await page.ax_tree()
print(str(root)[:300])

- **RootWebArea** "6. httpbin.org/forms/post" `focusable=True` `url=https://httpbin.org/forms/post` [#14]
  - **LabelText** "" [#20]
    - **StaticText** "Customer name: " [#62]
      - **InlineTextBox** "Customer name: "
    - **textbox** "Customer name: " `focusable=True` `editable=plaintext` `set

find and find_id are used to identify elements in the tree:

nmid = root.find_id('textbox', 'Customer name')
nmid

2

You can use regular CDP methods, or one of the provided shortcuts:

await page.fill_text(nmid, 'Jeremy Howard')
await page.click(root.find_id('radio', 'Large'))
await page.js_node_run('this.value = "18:30"', root.find_id('InputTime', 'delivery time'));

You can use click to click a button, or click_and_wait to wait for the next page to load:

await page.click_and_wait(root.find_id('button', 'Submit order'))

await page.close()

To allow LLMs like solveit with safepyrun to access solvecdp, use:

cdp_yolo()

Then use a prompt such as:

Try using pyrun to create a page_ JsCDP object, then goto <url>, fill it out, read it to check it’s filled correctly, then submit it, and see what you get back. Don’t use find_id - you can get all the ids at once with ax_tree (don’t truncate the result of it). Don’t add extra waits etc - solvecdp handles it automatically. IDs can change so be sure to use the ax_tree IDs you read.