木偶:懒惰图像未以无头模式加载

时间:2020-03-31 15:35:21

标签: javascript node.js puppeteer

这是我的代码。我正在使用AdBlock Plus Extension。

我有一个任务是截取网页的屏幕截图(使用了延迟加载),图像的右侧栏中标题为PAID CONTENT,底部的图像标题为PAID CONTENT。 / p>

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

(async () => {
  const pathToExtension = require('path').join(__dirname, 'abp_chrome');

  const browser = await puppeteer.launch({
    headless: true,
    args: [
     `--disable-extensions-except=${pathToExtension}`,
     `--load-extension=${pathToExtension}`
   ]
 });

 const page = await browser.newPage();
 await timeout(5000);
 await page.setViewport({width: 1200, height: 1200});
 await page.goto('https://edition.cnn.com/2015/07/31/world/mh370-debris- 
   investigation/index.html', {waitUntil: 'load', timeout: 0});
 await page.evaluate(() => {
   window.getDimensions = function(element) { 
    rect = element.getBoundingClientRect();
    return {
     x: rect.x,
     y: rect.y,
     width: rect.width,
     height: rect.height
  };
 };
});
await autoScroll(page);  
await page.screenshot({path: 'example.png', fullPage: true});
await browser.close();
})();

 async function timeout(ms) {
  return new Promise(resolve => setTimeout(resolve, ms));
 }

 async function autoScroll(page){
   await page.evaluate(async () => {
   await new Promise((resolve, reject) => {
   var totalHeight = 0;
   var distance = 100;
   var timer = setInterval(() => {
     var scrollHeight = document.body.scrollHeight;
     window.scrollBy(0, distance);
     totalHeight += distance;

     if(totalHeight >= scrollHeight){
      clearInterval(timer);
      resolve();
     }
    }, 500);
   });
 });
}

我已经使用滚动加载了懒惰的图像,但是却没有像截图所示那样加载图像。

这里是从代码捕获的屏幕截图。 enter image description here 如屏幕截图所示,没有图像图块,有什么办法可以实现?

2 个答案:

答案 0 :(得分:2)

我已经在GitHub issue的帮助下解决了这个问题。

我添加了用户代理:

page.setUserAgent("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36
WAIT_UNTIL=load")

答案 1 :(得分:0)

async function autoScroll(page){
   let criteria=3; //lazy load 3 page
   for (let pageIndex = 1; pageIndex < criteria; pageIndex++) {
      await page.evaluate(async () => {
        let x = await document.querySelectorAll(
          'set lazy element selector array'
        );
        await x[x.length - 1].scrollIntoView();
        return x.length;
      });
      await page.waitFor(1000);  
   }
}