Amy*_*oin 2 node.js scrape puppeteer
我登录到一个站点,它提供了一个浏览器cookie。
我去一个URL,它是一个json响应。
输入后如何刮取页面await page.goto('blahblahblah.json');
?
Rip*_*ppo 10
另一种不给您的方法intermittent issues是评估主体,使其变为可用,然后将其作为JSON返回,例如
const puppeteer = require('puppeteer');
async function run() {
const browser = await puppeteer.launch( {
headless: false //change to true in prod!
});
const page = await browser.newPage();
await page.goto('https://raw.githubusercontent.com/GoogleChrome/puppeteer/master/package.json');
var content = await page.content();
innerText = await page.evaluate(() => {
return JSON.parse(document.querySelector("body").innerText);
});
console.log("innerText now contains the JSON");
console.log(innerText);
//I will leave this as an excercise for you to
// write out to FS...
await browser.close();
};
run();
Run Code Online (Sandbox Code Playgroud)
您可以拦截网络响应,如下所示:
const puppeteer = require('puppeteer');
const fs = require('fs');
(async () => {
const browser = await puppeteer.launch()
const page = await browser.newPage()
page.on('response', async response => {
console.log('got response', response._url)
const data = await response.buffer()
fs.writeFileSync('/tmp/response.json', data)
})
await page.goto('https://raw.githubusercontent.com/GoogleChrome/puppeteer/master/package.json', {waitUntil: 'networkidle0'})
await browser.close()
})()
Run Code Online (Sandbox Code Playgroud)