@naimi/alib/node/net/puppeteer-save-htm.cjs

alib

const fs = require("fs");
const puppeteer = require("puppeteer");

(async () => {
  const url = process.argv[2];
  if (url == undefined) {
    console.log('Usage: node puppeteer-save-mht.cjs "URL"'
            + '\ne.g.:  node puppeteer-save-mht.cjs "http://google.com"');
    return;
  }
  const browser = await puppeteer.launch();
  //const browser = await puppeteer.launch({args:['--proxy-server=socks5://127.0.0.1:9050']}); // use tor
  const page = await browser.newPage();
  await page.setViewport({ width: 1600, height: 2200, deviceScaleFactor: 1 });

  // await page.setRequestInterception(true);
  // page.on("request", (request) => {
  //   console.log(`Intercepting: ${request.method} ${request.url}`);
  //   request.continue();
  // });

  await page.goto(url);
  // await page.waitForNavigation({waitUntil: 'load'});
  // await page.waitForNavigation({ waitUntil: "networkidle0" });
  await page.waitFor(5000);

  //! save
  const title = await page.title();
  const fn = "dl-" + title;
  console.log(title);

  await page.screenshot({ path: fn + ".png" });
  const data = await page.content();
  // console.log(data);
  fs.writeFileSync(fn + ".html", data);

  browser.close();
})();