javascript - 错误: failed to find element matching selector for 转载 作者：行者123 更新时间：2023-12-01 01:03:00 36 4

Question

在 Puppeteer 上运行，全部更新。

预期的过程是访问网站，其中 url 是 url/{search item} 并运行搜索名称列表。然后对于每个搜索项 --> 搜索页面，获取每个列表的名称、价格和图像 url。现在出现错误，找不到选择器。感谢对此的任何帮助，非常感谢!

网站数据布局如下:

<div class="items-box-content">
   <section class="items-box">
      <a href="https://listingurl">
         <figure class="items-box-photo">
            <img data-src="https://imageurl.jpg" class=" lazyloaded" src="https://imageurl.jpg">
         </figure>
         <div class="items-box-main">
            <h3 class="items-box-name"> listing name </h3>

            <div class="items-box-figure">
               <div class="items-price font-4"> $29.95 </div> // item's price
            </h3>
         </div>

我现在拥有的是(引发错误):

const puppeteer = require('puppeteer');
const searches = ["a", "b", "c"]; //appended to url
(async () => {
   const browser = await puppeteer.launch({ headless: false });
   let results =[];
   for (const search of searches) {
         try {
            page = await browser.newPage();
            await page.goto(`https://weburl/?keyword=${search}`);
            await page.evaluate(() => { document.querySelector('div[class*="items-box"]').scrollIntoView();});
            let elements = await page.$$('div[class*="items-box"]');
            for (let element of elements) {
               let listImg = await element.$eval(('img[class="items-box-photo]'), img => img.getAttribute('src'));
               let listTitle = await element.$eval(('d[class="items-box-main"] > h[class="items-box-name"]'), node => node.innerText.trim());
               let listPrice = await element.$eval(('d[class="items-box-figure"] > d[class="items-price"]'), node => node.innerText.trim());
               let listUrl = await element.$eval(('d[class="items-box-content"] > a[class*="items-box"]'), node => node.getAttribute('href'));

               results.push({ 
                  listImg, 
                  listTitle, 
                  listPrice, 
                  listUrl 
               })
               return results;
            }
         } finally {
            await page.close
         }
   }
})();

抛出的错误是

(node:5168) UnhandledPromiseRejectionWarning: Error: Error: failed to find element matching selector "img[class="items-box-photo]"

Answer 1

我通过测试/调试更新了您的代码。

const puppeteer = require('puppeteer');

const searches = ["a"];

(async () => {

    const browser = await puppeteer.launch({ headless: false });

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

    let results = [];

    for (const search of searches) {

        try {
            page = await browser.newPage();
            await page.goto(`https:url/`);

            await page.evaluate(() => { document.querySelector('section[class*="items-box"]').scrollIntoView(); });

            let elements = await page.$$('section[class*="items-box"]');
            console.log(elements.length)
            console.log('wait 6  seconds')
            await delay(6000);

            for (let element of elements) {
                // await delay(6000);

                let listImg = await element.$eval(('img'), img => img.getAttribute('src'));
                let listTitle = await element.$eval(('h3[class="items-box-name font-2"]'), node => node.innerText.trim());
                let listPrice = await element.$eval(('div[class="items-box-price font-5"]'), node => node.innerText.trim());
                let listUrl = await element.$eval(('div[class="items-box-content clearfix"] a'), node => node.getAttribute('href'));

                results.push({
                    listImg,
                    listTitle,
                    listPrice,
                    listUrl
                });
            }

            debugger;

        } catch (error) {
            console.log(error)
        } finally {
            //await page.close
            await browser.close
        }
    }
    console.log(results)
    return results;
})();

<小时/>

更新内容:
1. for循环中的返回结果

for(){
   return result;
}

=>

for(){

}
return result;

更新了querySelector

section[class*="items-box"]

img  // There is only one img tags in "element"

h3[class="items-box-name font-2"]  // removed outer 'element'

div[class="items-box-figure"] > div[class="items-price font-4"]

div[class="items-box-price font-5  // updated class name? on my side 

items-box-price

div[class="items-box-content clearfix"] a 

更新 sleep 持续时间 6 秒，这是相对网络速度(网络加载持续时间)。

尝试 捕获 终于
catch 帮助您处理下一步，尽管一步崩溃。