我尝试使用Puppeteer从第一个搜索页面中获取图像的所有链接,但我总共只有40个链接中有6个。这是我的代码:
const puppeteer = require('puppeteer');
puppeteer.launch({ headless: true }).then(async browser => {
const page = await browser.newPage();
await page.goto('https://shopee.vn/search?keyword=iphone%20xs' , {waitUntil: 'networkidle0'});
const links = await page.evaluate( () => {
let products_result = document.getElementsByClassName("_1T9dHf _3XaILN");
let images = [];
for(let i=0; i<products_result.length; i++){
images[i] = products_result[i].src;
}
return images;
});
for(let i=0; i<links.length;i++){
console.log('Links of ' + i +' images : ',links[i]);
}
await browser.close();
});
如何解决从第一个搜索页面获得40个链接的问题?谢谢。
答案 0 :(得分:1)
我相信相关站点正在对图像进行一些延迟加载和/或某些按需DOM操作。
因此,我们将尝试使用以下出色答案的改编方式滚动页面:
Puppeteer - scroll down until you can't anymore。
我们还要做的是拍摄页面图像(在运行脚本的目录中打开./page.png!),这可以帮助您查看正在加载的内容(或不加载!)。 代码如下:
const puppeteer = require('puppeteer');
// Scroll downwards slowly
async function scroll(page){
await page.evaluate(async () => {
await new Promise(resolve => {
// Adjust as necessary
const y = 50, speed = 20;
let heightScrolled = 0;
setInterval(() => {
window.scrollBy(0, y);
heightScrolled += y;
if (heightScrolled >= document.body.scrollHeight) {
resolve();
}
}, speed);
});
});
}
async function getImages(url) {
const browser = await puppeteer.launch();
const page = await browser.newPage();
await page.goto(url, {waitUntil: 'networkidle0'});
await page.setViewport({
width: 1200,
height: 800
});
await scroll(page);
// Take an image of the page.. see what it looks like!
await page.screenshot({
fullPage: true,
path: `./page.png`
});
const links = await page.evaluate( () => {
let products_result = document.getElementsByClassName("_1T9dHf _3XaILN");
let images = [];
for(let i=0; i<products_result.length; i++){
images[i] = products_result[i].src;
}
return images;
});
for(let i=0; i<links.length;i++){
console.log('Links of ' + i +' images : ',links[i]);
}
await browser.close();
}
let url = 'https://shopee.vn/search?keyword=iphone%20xs'
getImages(url);