I'm trying to test a very simple code but it's not working. It must be doing a very simple mistake but I can't find the problem.
The code below runs with no errors but the browse does not open:
const puppeteer = require('puppeteer');
(async () => {
console.log("1");
const browser = await puppeteer.launch({ headless: false });
console.log("2");
const page = await browser.newPage();
console.log("3");
await page.goto('https://google.com/');
console.log("4");
await page.waitForSelector('#fakebox-input');
console.log("5");
await browser.close;
});
Related
I am trying to load a page, http://www.nhc.gov.cn/wjw/index.shtml, on puppeteer as part of a covid-tracking program. The page loads very quickly in the regular chrome browser, but when I load it in puppeteer, the page load fails with a 412. What can I do to get the page to load and fully simulate a regular browser going to the page?
The code for reproduction of this phenomenon is below:
const puppeteer = require('puppeteer-core');
(async () => {
const browser = await puppeteer.launch({ executablePath: '..\\executables\\chrome.exe', headless: false, args: ['--no-sandbox', '--disable-setuid-sandbox', '--disable-gpu'] });
const page = await browser.newPage();
Object.assign(global, { browser, page });
page.on('console', msg => console.log(`chrome[${msg.text()}]`));
await page.goto('http://www.nhc.gov.cn/wjw/index.shtml', { waitUntil: 'networkidle0' });
await page.waitFor(15000);
await page.screenshot({path: 'nhc_scrape.png'});
await browser.close();
})();
Thank you in advance for your help!
you can use puppeteer-extra with the StealthPlugin.
https://www.npmjs.com/package/puppeteer-extra-plugin-stealth
Here is my code :
const puppeteer = require('puppeteer-extra')
const StealthPlugin = require("puppeteer-extra-plugin-stealth");
(async () => {
puppeteer.use(StealthPlugin())
const browser = await puppeteer.launch({headless: false, ignoreHTTPSErrors: true})
const page = await browser.newPage();
await page.goto('http://www.nhc.gov.cn/wjw/index.shtml');
await page.waitForSelector('.inLists')
await page.screenshot({path: 'nhc_scrape.png'});
await browser.close();
})();
What should I do when I get a timeout error for async tests and hooks?
My code is :
const puppeteer = require('puppeteer');
describe('My First Puppeteer Test', () =>{
it('should launch the browser', async function(){
const browser = await puppeteer.launch({headless: false, slowMo: 500});
const page = await browser.newPage();
await page.goto('https://www.google.com');
await browser.close();
})
})
You can set a default timeout for all navigation operations using:
const page = await browser.newPage();
page.setDefaultNavigationTimeout(10000);
Or you can also set the timeout for a specific page.goto operation using:
await page.goto('https://www.google.com', {waitUntil: 'load', timeout: 10000});
I have this code:
const puppeteer = require("puppeteer");
(async () => {
const browser = await puppeteer.launch({ headless: false });
const page = await browser.newPage();
await page.goto("https://www.sisal.it/scommesse-matchpoint/quote/calcio/serie-a");
const [button1] = await
page.$x('//div[#class="marketBar_changeMarketLabel__l0vzl"]/p');
button1.click();
const [button2] = await page.$x('//div[#class="listItem_container__2IdVR white
marketList_listItemHeight__1aiAJ marketList_bgColorGrey__VdrVK"]/p[text()="1X2
ESITO FINALE"]');
button2.click();
})();
The proble is that after clicking button1 the page change and puppeteer executes immediately the following line of code, instead I want it to wait for the new page to be loaded becuase otherwise It will throw an error since It can't find button2.
I found this solution on stackoverflow:
const puppeteer = require("puppeteer");
function delay(time) {
return new Promise(function (resolve) {
setTimeout(resolve, time);
});
}
(async () => {
const browser = await puppeteer.launch({ headless: false });
const page = await browser.newPage();
await page.goto("https://www.sisal.it/scommesse-matchpoint/quote/calcio/serie-a");
const [button1] = await
page.$x('//div[#class="marketBar_changeMarketLabel__l0vzl"]/p');
button1.click();
await delay(4000);
const [button2] = await page.$x('//div[#class="listItem_container__2IdVR white
marketList_listItemHeight__1aiAJ
marketList_bgColorGrey__VdrVK"]/p[text()="1X2
ESITO FINALE"]');
button2.click();
})();
But of course this in't the best solution.
I think you have to modify a bit in your code:
await button1.click();
await page.waitForNavigation({waitUntil: 'networkidle2'});
For reference, see the documentation.
I found a solution, here's the code:
const puppeteer = require("puppeteer");
(async () => {
const browser = await puppeteer.launch({ headless: false });
const page = await browser.newPage();
await page.goto("https://www.sisal.it/scommesse
matchpoint/quote/calcio/serie-a");
await page.waitForXPath('//div[#class="marketBar_changeMarketLabel__l0vzl"]/p');
const [button1] = await page.$x('//div[#class="marketBar_changeMarketLabel__l0vzl"]/p');
await button1.click();
await page.waitForXPath('//div[#class="listItem_container__2IdVR white marketList_listItemHeight__1aiAJ marketList_bgColorGrey__VdrVK"]/p[text()="1X2 ESITO FINALE"]');
const [button2] = await page.$x('//div[#class="listItem_container__2IdVR white marketList_listItemHeight__1aiAJ marketList_bgColorGrey__VdrVK"]/p[text()="1X2 ESITO FINALE"]');
button2.click();
})();
As illustrated in here here, Puppeteer allows to override Javascript functions. I want to override showOpenFilePicker function. That is, when the showOpenFilePicker invoked by the web page. I want to run another function before the showOpenFilePicker.
const puppeteer = require("puppeteer");
(async () => {
const browser = await puppeteer.launch({ headless: false });
const page = await browser.newPage();
await page.evaluateOnNewDocument(() => {
Object.defineProperty(HTMLCanvasElement.prototype, "toBlob", {
value: () => {
console.log("Hey there");
},
});
});
await page.goto("https://example.com");
await page.evaluate(() => {
console.log(HTMLCanvasElement.prototype.toBlob.toString());
});
// await browser.close();
})();
You can override built-in functions in Puppeteer like in the code sample below. This replaces the original function with an override that logs the arguments to the console.
const puppeteer = require("puppeteer");
(async () => {
const browser = await puppeteer.launch({ headless: false });
const page = await browser.newPage();
await page.evaluateOnNewDocument(() => {
const originalShowOpenFilePicker = window.showOpenFilePicker;
window.showOpenFilePicker = (...args) => {
console.log('Modified `showOpenFilePicker` called with these arguments:', args);
return originalShowOpenFilePicker(...args);
};
});
await page.goto("https://example.com");
await page.evaluate(() => {
console.log(showOpenFilePicker());
});
// await browser.close();
})();
I want to take a screenshot with puppeteer and it's working for one post. But I want to make it iterate.
If it's normal function I can just wrote the function name in the last side of the code so that it can iterate. But this is async function so I don't know how to iterate it.
const puppeteer = require('puppeteer');
let postNumber = 1;
let by;
(async () => {
const browser = await puppeteer.launch({
executablePath: 'C:\\Program Files (x86)\\Google\\Chrome\\Application\\chrome.exe',
userDataDir: 'C:\\Users\\{computerName}\\AppData\\Local\\Google\\Chrome\\User Data',
headless: false
}); // default is true
const page = await browser.newPage();
await page.goto(`https://band.us/band/{someNumbers}/post/${postNumber}`, {
waitUntil: 'networkidle2'
});
let element = await page.$('.boardList');
by = await page.evaluate(() => document.getElementsByClassName('text')[0].textContent);
console.log(by);
await element.screenshot({
path: `./image/${postNumber}-${by}.png`
});
console.log(`SAVED : ${postNumber}-${by}.png`)
postNumber++;
await browser.close();
})();
After the function is finished, the postNumber variable should be increase by one. And then run the code again by new URLs.
As you want to run the code one iteration after another, a normal for (or while) loop can be used. async/await code works fine with these.
You can use a for in your case like this:
(async () => {
const browser = await puppeteer.launch(/* ... */);
const page = await browser.newPage();
for (let postNumber = 1; postNumber < 10; postNumber++) {
await page.goto(/* ... */);
let element = await page.$('.boardList');
// ...
}
await browser.close();
})();
You can use any appropriate loop, like while-loop:
'use strict';
const puppeteer = require('puppeteer');
(async () => {
const browser = await puppeteer.launch({
executablePath: 'C:\\Program Files (x86)\\Google\\Chrome\\Application\\chrome.exe',
userDataDir: 'C:\\Users\\{computerName}\\AppData\\Local\\Google\\Chrome\\User Data',
headless: false
}); // default is true
const page = await browser.newPage();
let postNumber = 1;
while (postNumber <= 10) {
await page.goto(`https://band.us/band/{someNumbers}/post/${postNumber}`, {
waitUntil: 'networkidle2'
});
const element = await page.$('.boardList');
const by = await page.evaluate(() => document.getElementsByClassName('text')[0].textContent);
console.log(by);
await element.screenshot({
path: `./image/${postNumber}-${by}.png`
});
console.log(`SAVED : ${postNumber}-${by}.png`)
postNumber++;
}
await browser.close();
})();