如何在 Node.js 中用正确的 user agent 识别 CaptchaFox

# capskip 1.3.0 added captchafox(); cheerio reads the HTML
npm install capskip cheerio

// npm install capskip cheerio
import * as cheerio from "cheerio";

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

// fetch() keeps no cookies between calls, so carry the page's own.
const jar = new Map();
const page = await fetch(PAGE_URL);
for (const line of page.headers.getSetCookie()) {
  const pair = line.split(";")[0];
  const eq = pair.indexOf("=");
  jar.set(pair.slice(0, eq).trim(), pair.slice(eq + 1).trim());
}
const html = await page.text();
const $ = cheerio.load(html);

// The container, matched on the whole class name.
const widget = $(".captchafox").first();
// MAM pages may carry the key in the package's script src instead.
const mamSrc = $('script[src*="mampkg/@mamdev/core.frontend.libs.captchafox"]').attr("src");
const sitekey = widget.attr("data-sitekey")
  ?? (mamSrc && new URL(mamSrc, PAGE_URL).searchParams.get("key"))
  ?? html.match(/captchafox\.render\([\s\S]{0,300}?sitekey\s*:\s*["']([^"']+)/)?.[1];
const form = widget.length ? widget.closest("form") : $("form").first();

console.log(sitekey, Boolean(mamSrc));   // a MAM page needs a MAM_ token

import { CapSkip } from "capskip";

const solver = new CapSkip({ host: "127.0.0.1", port: 8080 });
// Copied from the script tag on MAM pages.
const MAM_PACKAGE = "https://s.uicdn.com/mampkg/@mamdev/core.frontend.libs.captchafox/";

const result = await solver.captchafox(sitekey, PAGE_URL, {
  // undefined is dropped, so the standard widget sends nothing extra.
  apiServer: mamSrc ? MAM_PACKAGE : undefined,
});

console.log(result.token.slice(0, 24));   // goes in cf-captcha-response
console.log(result.userAgent);            // the browser that minted it

// The form's own fields, hidden CSRF token included.
const body = new URLSearchParams(
  form.serializeArray().map((f) => [f.name, f.value]),
);
body.set("email", "YOUR_EMAIL");
body.set("cf-captcha-response", result.token);

const headers = {
  cookie: [...jar].map(([k, v]) => `${k}=${v}`).join("; "),
  // Browsers send the page as Referer; strict servers want one.
  referer: PAGE_URL,
};
// Without this line, fetch announces itself as user-agent: node.
if (result.userAgent) headers["user-agent"] = result.userAgent;

const res = await fetch(new URL(form.attr("action") || PAGE_URL, PAGE_URL), {
  method: "POST",
  headers,
  body,
});
console.log(res.status);

import { ApiException } from "capskip";

async function solveCaptchaFox(sitekey, url, options = {}, attempts = 3) {
  for (let attempt = 1; ; attempt++) {
    try {
      return await solver.captchafox(sitekey, url, options);
    } catch (err) {
      // Select, audio and unreadable slide draws come back unsolvable;
      // redraw. Anything else, such as a wrong API key, is final.
      const redraw = err instanceof ApiException && err.message.includes("UNSOLVABLE");
      if (!redraw || attempt === attempts) throw err;
    }
  }
}

// npm install capskip cheerio
// signup.mjs: run with node signup.mjs
import * as cheerio from "cheerio";
import {
  CapSkip, ApiException, CapSkipError, TimeoutException, ValidationException,
} from "capskip";

const PAGE_URL = "https://example.com/signup";
// Copied from the script tag on MAM pages.
const MAM_PACKAGE = "https://s.uicdn.com/mampkg/@mamdev/core.frontend.libs.captchafox/";

const solver = new CapSkip({
  apiKey: process.env.CAPSKIP_API_KEY ?? "capskip",
  host: process.env.CAPSKIP_HOST ?? "127.0.0.1",
  port: Number(process.env.CAPSKIP_PORT ?? 8080),
});

async function solveCaptchaFox(sitekey, url, options = {}, attempts = 3) {
  for (let attempt = 1; ; attempt++) {
    try {
      return await solver.captchafox(sitekey, url, options);
    } catch (err) {
      // Select, audio and unreadable slide draws come back unsolvable.
      const redraw = err instanceof ApiException && err.message.includes("UNSOLVABLE");
      if (!redraw || attempt === attempts) throw err;
      console.log(`attempt ${attempt}: ${err.message}`);
    }
  }
}

async function signUp(pageUrl, email) {
  // One jar per run, so runs side by side never share a session.
  const jar = new Map();
  const page = await fetch(pageUrl);
  for (const line of page.headers.getSetCookie()) {
    const pair = line.split(";")[0];
    const eq = pair.indexOf("=");
    jar.set(pair.slice(0, eq).trim(), pair.slice(eq + 1).trim());
  }
  const html = await page.text();
  const $ = cheerio.load(html);

  const widget = $(".captchafox").first();
  const mamSrc = $('script[src*="mampkg/@mamdev/core.frontend.libs.captchafox"]').attr("src");
  const sitekey = widget.attr("data-sitekey")
    ?? (mamSrc && new URL(mamSrc, pageUrl).searchParams.get("key"))
    ?? html.match(/captchafox\.render\([\s\S]{0,300}?sitekey\s*:\s*["']([^"']+)/)?.[1];
  if (!sitekey) throw new Error("No sitekey in the HTML; find it in DevTools.");
  const form = widget.length ? widget.closest("form") : $("form").first();

  const result = await solveCaptchaFox(sitekey, pageUrl, {
    apiServer: mamSrc ? MAM_PACKAGE : undefined,
  });

  const body = new URLSearchParams(form.serializeArray().map((f) => [f.name, f.value]));
  body.set("email", email);
  body.set("cf-captcha-response", result.token);
  const headers = {
    cookie: [...jar].map(([k, v]) => `${k}=${v}`).join("; "),
    referer: pageUrl,
  };
  if (result.userAgent) headers["user-agent"] = result.userAgent;

  const action = new URL(form.attr("action") || pageUrl, pageUrl);
  return fetch(action, { method: "POST", headers, body });
}

try {
  const res = await signUp(PAGE_URL, "YOUR_EMAIL");
  console.log(res.status, (await res.text()).slice(0, 80));
} catch (err) {
  if (err instanceof ValidationException) console.error(`not sent: ${err.message}`);
  else if (err instanceof TimeoutException) console.error("gave up after recaptchaTimeout");
  else if (err instanceof CapSkipError) console.error(`solve failed: ${err.name}: ${err.message}`);
  else throw err;
  process.exitCode = 1;
}

// At most `limit` calls in flight; a failure becomes that item's Error.
async function mapLimited(items, limit, fn) {
  const results = new Array(items.length);
  let next = 0;
  async function worker() {
    while (next < items.length) {
      const i = next++;
      results[i] = await fn(items[i]).catch((err) => err);
    }
  }
  await Promise.all(Array.from({ length: Math.min(limit, items.length) }, worker));
  return results;
}

const emails = ["YOUR_EMAIL_1", "YOUR_EMAIL_2", "YOUR_EMAIL_3"];
const results = await mapLimited(emails, 10, (email) => signUp(PAGE_URL, email));
for (const r of results) console.log(r instanceof Error ? r.message : r.status);