puppeteer实现批量下载coding仓库代码

2022-05-17 22:37:26

记录下批量下载仓库代码的方法

工具来由

需要把指定帐号下的所有仓库批量下载下来,一个个复制仓库地址进行克隆太忙,所以做了这个自动化工具,如果你有类似需求,可供参考。

操作准备

本地需要安装 git,生成私钥后添加到指定帐号的 SSH 公钥中。

代码

核心代码参考:


const puppeteer = require('puppeteer');
const account = '帐号';
const password = '密码';
const localPath = '本地存放代码的目录';
const { exec, execSync } = require('child_process');

(async () => {
  const browser = await puppeteer.launch({
    headless: true,
    args: [
      '--no-sandbox',
      '--disable-setuid-sandbox',
      '--disable-blink-features=AutomationControlled',
    ],
    dumpio: false,
  });
  const page = await browser.newPage();

  // webdriver
  await page.evaluateOnNewDocument(() => {
    const newProto = navigator.__proto__;
    delete newProto.webdriver; //删除 navigator.webdriver字段
    navigator.__proto__ = newProto;
  });

  // 添加 window.chrome字段,向内部填充一些值
  await page.evaluateOnNewDocument(() => {
    window.chrome = {};
    window.chrome.app = {
      InstallState: 'hehe',
      RunningState: 'haha',
      getDetails: 'xixi',
      getIsInstalled: 'ohno',
    };
    window.chrome.csi = function() {};
    window.chrome.loadTimes = function() {};
    window.chrome.runtime = function() {};
  });

  // userAgent设置
  await page.evaluateOnNewDocument(() => {
    Object.defineProperty(navigator, 'userAgent', {
      //userAgent在无头模式下有headless字样,所以需覆盖
      get: () =>
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.113 Safari/537.36',
    });
  });

  // plugins设置
  await page.evaluateOnNewDocument(() => {
    Object.defineProperty(navigator, 'plugins', {
      //伪装真实的插件信息
      get: () => [
        {
          0: {
            type: 'application/x-google-chrome-pdf',
            suffixes: 'pdf',
            description: 'Portable Document Format',
            enabledPlugin: Plugin,
          },
          description: 'Portable Document Format',
          filename: 'internal-pdf-viewer',
          length: 1,
          name: 'Chrome PDF Plugin',
        },
        {
          0: {
            type: 'application/pdf',
            suffixes: 'pdf',
            description: '',
            enabledPlugin: Plugin,
          },
          description: '',
          filename: 'mhjfbmdgcfjbbpaeojofohoefgiehjai',
          length: 1,
          name: 'Chrome PDF Viewer',
        },
        {
          0: {
            type: 'application/x-nacl',
            suffixes: '',
            description: 'Native Client Executable',
            enabledPlugin: Plugin,
          },
          1: {
            type: 'application/x-pnacl',
            suffixes: '',
            description: 'Portable Native Client Executable',
            enabledPlugin: Plugin,
          },
          description: '',
          filename: 'internal-nacl-plugin',
          length: 2,
          name: 'Native Client',
        },
      ],
    });
  });

  // languages设置
  await page.evaluateOnNewDocument(() => {
    Object.defineProperty(navigator, 'languages', {
      //添加语言
      get: () => ['zh-CN', 'zh', 'en'],
    });
  });

  // permissions设置
  await page.evaluateOnNewDocument(() => {
    const originalQuery = window.navigator.permissions.query; //notification伪装
    window.navigator.permissions.query = (parameters) =>
      parameters.name === 'notifications'
        ? Promise.resolve({ state: Notification.permission })
        : originalQuery(parameters);
  });

  // WebGL设置
  await page.evaluateOnNewDocument(() => {
    const getParameter = WebGLRenderingContext.getParameter;
    WebGLRenderingContext.prototype.getParameter = function(parameter) {
      // UNMASKED_VENDOR_WEBGL
      if (parameter === 37445) {
        return 'Intel Inc.';
      }
      // UNMASKED_RENDERER_WEBGL
      if (parameter === 37446) {
        return 'Intel(R) Iris(TM) Graphics 6100';
      }
      return getParameter(parameter);
    };
  });

  await page.goto('https://xxx.coding.net/login', {
    waitUntil: 'networkidle0',
  });

  await page.type('input[name="account"]', account);
  await page.type('input[name="password"]', password);
  console.log('登录...');
  await page.click('.cuk2-button-type-confirm');
  await page.waitForNavigation({
    waitUntil: 'networkidle0',
  });

  page.on('response', async (response) => {
    const request = response.request();
    if (request.url().includes('xxx/depot-group/depots')) {
      console.log('获取所有仓库地址');
      const json = await response.text();
      let repos = JSON.parse(json).data;
      // 下载到本地
      repos.forEach((r) => {
        console.log('下载:' + r.gitSshUrl);
        execSync(`cd ${localPath} && git clone ${r.gitSshUrl}`);
      });

      // await browser.close();
    }
  });

  console.log('跳转仓库列表页');
  await page.goto('https://jnpfsoft.coding.net/p/xxx/repos', {
    waitUntil: 'networkidle2',
  });
})();

参考资料

本文链接:
版权声明:本博客所有文章除特别声明外,均采用 CC BY-NC-ND 3.0 许可协议。可自由转载、引用,但需署名作者且注明文章出处。如转载至微信公众号,请在文末添加作者公众号二维码。

扫描下方二维码阅读当前文章

浏览器、微信扫码

评 论:

好文推荐
每天进步一点点~