如何在 Playwright 中识别 ALTCHA 并填写隐藏字段

# pip install playwright capskip
pip install playwright capskip
playwright install chromium

# pip install playwright capskip
from playwright.sync_api import sync_playwright

PAGE_URL = "https://example.com/signup"

with sync_playwright() as p:
    browser = p.chromium.launch(headless=True)
    page = browser.new_page()
    page.goto(PAGE_URL)

    # v1 and v2 use challengeurl; v3 and later use challenge.
    widget = page.locator("altcha-widget")
    endpoint = widget.get_attribute("challengeurl")
    if not endpoint:
        endpoint = widget.get_attribute("challenge")

# Filter out the widget's own script: its URL also contains
# altcha, and it loads before the challenge is ever requested.
is_challenge = lambda r: ("altcha" in r.url
    and "json" in r.headers.get("content-type", ""))

# This fires during navigation only when the widget carries
# auto="onload". Otherwise wrap the click that triggers it.
with page.expect_response(is_challenge) as caught:
    page.goto(PAGE_URL)

challenge = caught.value.json()
print(challenge["algorithm"], challenge["maxnumber"])

from capskip import CapSkip

solver = CapSkip(host="127.0.0.1", port=8080)

# The document from step 1, so nothing is fetched twice.
result = solver.altcha(url=PAGE_URL, challenge_json=challenge)

# Or hand over the endpoint and let CapSkip fetch it.
# result = solver.altcha(url=PAGE_URL, challenge_url=endpoint)

print(result["token"])    # base64 payload for the form field
print(result["number"])   # the counter that satisfied it

# Walk up from the submit button so the field lands in the
# form that actually posts, not in the first form on the page.
SET_ALTCHA_FIELD = """({name, token}) => {
    const button = document.querySelector('button[type=submit]');
    const form = button ? button.form : document.querySelector('form');
    let field = form.querySelector('[name=' + name + ']');
    if (!field) {
        field = document.createElement('input');
        field.type = 'hidden';
        field.name = name;
        form.appendChild(field);
    }
    field.value = token;
}"""

field_name = widget.get_attribute("name") or "altcha"
page.evaluate(SET_ALTCHA_FIELD, {"name": field_name, "token": result["token"]})
page.click("button[type=submit]")

import os
from capskip import CapSkip, ApiException, NetworkException, TimeoutException
from playwright.sync_api import sync_playwright

PAGE_URL = "https://example.com/signup"

SET_ALTCHA_FIELD = """({name, token}) => {
    const button = document.querySelector('button[type=submit]');
    const form = button ? button.form : document.querySelector('form');
    let field = form.querySelector('[name=' + name + ']');
    if (!field) {
        field = document.createElement('input');
        field.type = 'hidden';
        field.name = name;
        form.appendChild(field);
    }
    field.value = token;
}"""

solver = CapSkip(
    host=os.environ.get("CAPSKIP_HOST", "127.0.0.1"),
    port=int(os.environ.get("CAPSKIP_PORT", 8080)),
)

def is_challenge(r):
    return "altcha" in r.url and "json" in r.headers.get("content-type", "")

with sync_playwright() as p:
    page = p.chromium.launch(headless=True).new_page()

    # Catch, solve and submit with nothing slow in between.
    with page.expect_response(is_challenge) as caught:
        page.goto(PAGE_URL)

    try:
        result = solver.altcha(url=PAGE_URL, challenge_json=caught.value.json())
    except ApiException:
        raise SystemExit("refused: Argon2id, scrypt, or an expired challenge")
    except NetworkException:
        raise SystemExit("solver unreachable: check host and connection mode")
    except TimeoutException:
        raise SystemExit("no answer inside defaultTimeout")

    field_name = page.locator("altcha-widget").get_attribute("name") or "altcha"
    page.fill("input[name=email]", "someone@example.com")
    page.evaluate(SET_ALTCHA_FIELD, {"name": field_name, "token": result["token"]})
    page.click("button[type=submit]")