如何在 Node.js 中识别 Capy Puzzle 并保持会话

# capskip 1.3.0 added capy(); cheerio reads the form
npm install capskip cheerio

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

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

// fetch() keeps no cookies between calls, so carry them yourself.
const jar = new Map();
function addCookies(res) {
  for (const line of res.headers.getSetCookie()) {
    const pair = line.split(";")[0];
    const eq = pair.indexOf("=");
    if (eq > 0) jar.set(pair.slice(0, eq).trim(), pair.slice(eq + 1).trim());
  }
}

const page = await fetch(PAGE_URL);
addCookies(page);
const html = await page.text();
const $ = cheerio.load(html);

// The widget script's k= parameter, or a capy_captchakey input.
const key = html.match(/PUZZLE_[A-Za-z0-9_-]+/)?.[0];
// Everything before /puzzle/get_js/ is the Capy host.
const apiServer = html.match(/(https:\/\/[^"'\s<>]+?)\/puzzle\/get_js\//)?.[1];
// The form that holds the widget script or a capy_captchakey input.
const form = $("form")
  .has('script[src*="/puzzle/get_js/"], input[name="capy_captchakey"]').first();
console.log(key, apiServer ?? "default host", form.length);

// npm install capskip
import { CapSkip } from "capskip";

const solver = new CapSkip({
  host: "127.0.0.1",
  port: 8080,
  // Capy answers after a two second hold; poll often enough to catch it.
  pollingInterval: 0.5,
});

// undefined (no widget script in the HTML) is dropped, so CapSkip
// uses its default host.
const result = await solver.capy(key, PAGE_URL, { apiServer });

console.log(result.captchakey);     // goes in capy_captchakey
console.log(result.challengekey);   // goes in capy_challengekey
console.log(result.answer);         // goes in capy_answer

// The form's own fields, hidden CSRF token included.
const body = new URLSearchParams(
  form.serializeArray().map((f) => [f.name, f.value]),
);
// Use the page's own field names, password included.
body.set("username", "YOUR_USERNAME");
body.set("capy_captchakey", result.captchakey);
body.set("capy_challengekey", result.challengekey);
body.set("capy_answer", result.answer);

const res = await fetch(new URL(form.attr("action") || PAGE_URL, PAGE_URL), {
  method: "POST",
  headers: {
    cookie: [...jar].map(([k, v]) => `${k}=${v}`).join("; "),
    // fetch sends no Referer; strict servers refuse a post without one.
    referer: PAGE_URL,
  },
  body,
  // A login answers 302 with a new session cookie; keep it.
  redirect: "manual",
});
addCookies(res);
console.log(res.status, res.headers.get("location"));

import { ApiException } from "capskip";

async function solveCapy(key, url, options = {}, attempts = 3) {
  for (let attempt = 1; ; attempt++) {
    try {
      return await solver.capy(key, url, options);
    } catch (err) {
      // A missed hole reads as unsolvable, and the next try draws a
      // new puzzle. Anything else, such as a wrong API key, is final.
      const miss = err instanceof ApiException && err.message.includes("UNSOLVABLE");
      if (!miss || attempt === attempts) throw err;
    }
  }
}

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

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

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),
  pollingInterval: 0.5,
});

async function solveCapy(key, url, options = {}, attempts = 3) {
  for (let attempt = 1; ; attempt++) {
    try {
      return await solver.capy(key, url, options);
    } catch (err) {
      // A missed hole reads as unsolvable; the next try draws a new puzzle.
      const miss = err instanceof ApiException && err.message.includes("UNSOLVABLE");
      if (!miss || attempt === attempts) throw err;
      console.log(`attempt ${attempt}: ${err.message}`);
    }
  }
}

function addCookies(jar, res) {
  for (const line of res.headers.getSetCookie()) {
    const pair = line.split(";")[0];
    const eq = pair.indexOf("=");
    if (eq > 0) jar.set(pair.slice(0, eq).trim(), pair.slice(eq + 1).trim());
  }
}

async function logIn(pageUrl, username) {
  // One jar per run, so runs side by side never share a session.
  const jar = new Map();
  const page = await fetch(pageUrl);
  addCookies(jar, page);
  const html = await page.text();
  const $ = cheerio.load(html);

  const key = html.match(/PUZZLE_[A-Za-z0-9_-]+/)?.[0];
  if (!key) throw new Error("No PUZZLE_ key in the HTML; find it in DevTools.");
  const apiServer = html.match(/(https:\/\/[^"'\s<>]+?)\/puzzle\/get_js\//)?.[1];
  const form = $("form")
    .has('script[src*="/puzzle/get_js/"], input[name="capy_captchakey"]').first();
  if (!form.length) throw new Error("No form holds the widget; select it by id.");

  const result = await solveCapy(key, pageUrl, { apiServer });

  // All three together, straight away: the challenge key is single-use.
  const body = new URLSearchParams(form.serializeArray().map((f) => [f.name, f.value]));
  // Use the page's own field names, password included.
  body.set("username", username);
  body.set("capy_captchakey", result.captchakey);
  body.set("capy_challengekey", result.challengekey);
  body.set("capy_answer", result.answer);

  const action = new URL(form.attr("action") || page.url, page.url);
  const res = await fetch(action, {
    method: "POST",
    headers: {
      cookie: [...jar].map(([k, v]) => `${k}=${v}`).join("; "),
      referer: page.url,
    },
    body,
    // A login answers 302 with a new session cookie. Keep the 302, so
    // its Set-Cookie lands in the jar instead of being followed away.
    redirect: "manual",
  });
  addCookies(jar, res);
  return { res, jar };
}

try {
  const { res, jar } = await logIn(PAGE_URL, "YOUR_USERNAME");
  // A 302 to the account page means it worked; jar holds that session.
  console.log(res.status, res.headers.get("location"), [...jar.keys()]);
} catch (err) {
  if (err instanceof ValidationException) console.error(`not sent: ${err.message}`);
  else if (err instanceof TimeoutException) console.error("gave up after defaultTimeout");
  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 users = ["YOUR_USERNAME_1", "YOUR_USERNAME_2", "YOUR_USERNAME_3"];
const results = await mapLimited(users, 10, (user) => logIn(PAGE_URL, user));
for (const r of results) console.log(r instanceof Error ? r.message : r.res.status);