使用 Node.js 进行验证码抓取：完整教程

Node.js 擅长 I/O-heavy 抓取工作负载。当目标站点提供验证码时，CaptchaAI 的 API 会在您的脚本处理 HTTP 请求时解决这些问题。本教程涵盖了使用 axios 和 Cheerio 的完整工作流程。

要求

CaptchaAI 求解器模块

// captcha-solver.js
const axios = require("axios");

class CaptchaSolver {
  constructor(apiKey) {
    this.apiKey = apiKey;
    this.baseUrl = "https://ocr.captchaai.com";
  }

  async _submit(params) {
    params.key = this.apiKey;
    const resp = await axios.get(`${this.baseUrl}/in.php`, { params });
    if (!resp.data.startsWith("OK|")) {
      throw new Error(`Submit error: ${resp.data}`);
    }
    return resp.data.split("|")[1];
  }

  async _poll(taskId, timeout = 300000) {
    const deadline = Date.now() + timeout;
    while (Date.now() < deadline) {
      await new Promise((r) => setTimeout(r, 5000));
      const resp = await axios.get(`${this.baseUrl}/res.php`, {
        params: { key: this.apiKey, action: "get", id: taskId },
      });
      if (resp.data === "CAPCHA_NOT_READY") continue;
      if (resp.data.startsWith("OK|")) return resp.data.split("|")[1];
      throw new Error(`Solve error: ${resp.data}`);
    }
    throw new Error("Solve timed out");
  }

  async solveRecaptchaV2(siteKey, pageUrl) {
    const taskId = await this._submit({
      method: "userrecaptcha",
      googlekey: siteKey,
      pageurl: pageUrl,
    });
    return this._poll(taskId);
  }

  async solveRecaptchaV3(siteKey, pageUrl, action = "verify") {
    const taskId = await this._submit({
      method: "userrecaptcha",
      googlekey: siteKey,
      pageurl: pageUrl,
      version: "v3",
      action,
    });
    return this._poll(taskId);
  }

  async solveTurnstile(siteKey, pageUrl) {
    const taskId = await this._submit({
      method: "turnstile",
      sitekey: siteKey,
      pageurl: pageUrl,
    });
    return this._poll(taskId);
  }
}

module.exports = CaptchaSolver;

抓取受 reCAPTCHA 保护的页面

const axios = require("axios");
const cheerio = require("cheerio");
const CaptchaSolver = require("./captcha-solver");

const solver = new CaptchaSolver("YOUR_API_KEY");

async function scrapeProtectedPage(url) {
  // Step 1: Load the page
  const { data: html } = await axios.get(url, {
    headers: {
      "User-Agent":
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
    },
  });

  const $ = cheerio.load(html);

  // Step 2: Extract site key
  const siteKey = $(".g-recaptcha").attr("data-sitekey");
  if (!siteKey) {
    console.log("No CAPTCHA found, page loaded directly");
    return html;
  }

  console.log("Site key found:", siteKey);

  // Step 3: Solve the CAPTCHA
  const token = await solver.solveRecaptchaV2(siteKey, url);
  console.log("Token received:", token.substring(0, 50));

  // Step 4: Submit with the token
  const result = await axios.post(
    url,
    new URLSearchParams({
      "g-recaptcha-response": token,
      q: "search query",
    }),
    {
      headers: {
        "Content-Type": "application/x-www-form-urlencoded",
        "User-Agent":
          "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
      },
    }
  );

  return result.data;
}

同时抓取多个页面

async function scrapePages(urls, siteKey, concurrency = 3) {
  const results = [];
  const queue = [...urls];

  const worker = async () => {
    while (queue.length > 0) {
      const url = queue.shift();
      try {
        const token = await solver.solveRecaptchaV2(siteKey, url);
        const { data } = await axios.post(
          url,
          new URLSearchParams({ "g-recaptcha-response": token }),
          {
            headers: {
              "User-Agent":
                "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
            },
          }
        );
        results.push({ url, data, success: true });
        console.log(`Scraped: ${url}`);
      } catch (err) {
        results.push({ url, error: err.message, success: false });
        console.error(`Failed: ${url} - ${err.message}`);
      }
    }
  };

  // Run workers concurrently
  const workers = Array(concurrency)
    .fill(null)
    .map(() => worker());
  await Promise.all(workers);

  return results;
}

// Usage
const urls = [
  "https://example.com/page/1",
  "https://example.com/page/2",
  "https://example.com/page/3",
];
const results = await scrapePages(urls, "6Le-wvkS...", 3);

处理 Cookie 和会话

对于需要会话 cookie 的站点，使用具有 cookie 持久性的 axios：

const { wrapper } = require("axios-cookiejar-support");
const { CookieJar } = require("tough-cookie");

const jar = new CookieJar();
const client = wrapper(
  axios.create({
    jar,
    headers: {
      "User-Agent":
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
    },
  })
);

async function scrapeWithSession(url, siteKey) {
  // Initial page load sets cookies
  await client.get(url);

  // Solve CAPTCHA
  const token = await solver.solveRecaptchaV2(siteKey, url);

  // Submit with maintained cookies
  const result = await client.post(
    url,
    new URLSearchParams({ "g-recaptcha-response": token })
  );

  return result.data;
}

使用 Cheerio 解析结果

function parseResults(html) {
  const $ = cheerio.load(html);
  const items = [];

  $(".result-item").each((_, el) => {
    items.push({
      title: $(el).find(".title").text().trim(),
      url: $(el).find("a").attr("href"),
      description: $(el).find(".description").text().trim(),
    });
  });

  return items;
}

故障排除

常问问题

我什么时候应该使用 Puppeteer 而不是 axios？

当目标站点返回带有标准表单提交的 HTML 时，请使用 axios + Cheerio。当网站需要 JavaScript 执行、动态渲染或复杂的用户交互时，请使用 Puppeteer。

我可以同时解决多个验证码吗？

是的。同时向 CaptchaAI 提交多个验证码任务并轮询每个结果。上面的并发抓取示例演示了这种模式。

如何处理受 Cloudflare 保护的网站？

如果站点使用 Turnstile，请使用 solver.solveTurnstile()。如需完整的 Cloudflare 挑战页面，请使用Cloudflare 验证流程解决它返回 qa_session_cookie cookie。

相关指南

• 使用 Node.js 解决 Puppeteer CAPTCHA 问题
• 使用 Python 进行验证码抓取
• 用于验证码抓取的代理轮换