I'm trying to convert recordRTC webm file to mp4 using ffmpeg.js library in nextjs project, during conversion showing this issue
ffmpeg.FS('readFile', 'demo.mp4') error. Check if the path exists
const stopRecording = async () => {
if (recordRef.current) {
let blob = {}
recordRef.current.stopRecording(function(url) {
blob = recordRef.current.getBlob()
});
const webmFile = new File([blob], 'video.webm', {
type: 'video/webm'
})
convertBobToMpeg(webmFile)
}
}
const convertBobToMpeg = async (webmFile) => {
await ffmpeg.load();
await ffmpeg.FS('writeFile', 'video.webm', await fetchFile(webmFile))
ffmpeg.run('-i', 'video.webm', 'demo.mp4');
const data = await ffmpeg.FS('readFile', 'demo.mp4');
setVideo_obj(URL.createObjectURL(new Blob([data.buffer], {
type: 'video/mp4'
})))
}
I have a two step program :
Get a list of href from a page
Loop infinitely on each page of this list, get an element and display it in console
I try to use function with Puppeteer-Cluter but it doesn't work properly.
const { Cluster } = require('puppeteer-cluster');
const fs = require("fs");
const { addExtra } = require("puppeteer-extra");
const vanillaPuppeteer = require("puppeteer");
const StealthPlugin = require("puppeteer-extra-plugin-stealth");
var moment = require('moment');
var regexTemps = /(\d+)\s(\w+)$/;
const urlsToCheck = [];
TZ = 'Europe/Paris'
process.env.TZ = 'Europe/Paris'
(async () => {
const puppeteer = addExtra(vanillaPuppeteer);
puppeteer.use(StealthPlugin());
const cluster = await Cluster.launch({
puppeteer,
puppeteerOptions: {
headless: false,
args: ['--no-sandbox'],
},
maxConcurrency: 10,
concurrency: Cluster.CONCURRENCY_CONTEXT,
monitor: false,
skipDuplicateUrls: true,
timeout:30000,
retryLimit:10,
})
cluster.on('taskerror', (err, data, willRetry) => {
if (willRetry) {
console.warn(`Encountered an error while crawling ${data}. ${err.message}\nThis job will be retried`);
} else {
console.error(`Failed to crawl ${data}: ${err.message}`);
}
});
const getElementOnPage = async ({ page, data: url }) => {
console.log('=> Go to URL : ',url);
await page.goto(url);
while (true) {
console.log('=> Reload URL : ',page.url())
await page.reload();
await page.waitForTimeout(1000);
let allNews = await page.$$("article.news"); // [] if nothing
let firstNews = allNews[0];
await page.waitForTimeout(1000);
let info = await firstNews.$eval('.info span', s => s.textContent.trim());
console.log(new Date(), 'info : ',info);
}
};
const getListOfPagesToExplore = async ({ page, data: url }) => {
console.log(new Date(), 'Get the list of deal pages to explore');
await page.goto(url, {waitUntil: 'domcontentloaded'});
await page.waitForTimeout(500);
const hrefsToVisit = await page.$x('//a');
let idxTab=0;
for( let hrefToVisit of hrefsToVisit ) {
var link = await page.evaluate(el => el.getAttribute("href"), hrefToVisit);
console.log(new Date(), 'adding link to list : ', link);
idxTab++;
urlsToCheck.push(link);
}
};
cluster.queue('https://www.apagewithsomelinks.com', getListOfPagesToExplore);
await cluster.idle();
await cluster.close();
console.log(urlsToCheck);
//Display correctly several link in an array
for( let url of urlsToCheck ) {
console.log('Push in queue : ',url);
cluster.queue(url, getElementOnPage);
}
await cluster.idle();
await cluster.close();
})();
When I launch it, it retrieve the links to scrap.
It display "Push in queue : ..." for each URL.
But then, the method getElementOnPage is launched only for the first URL, and runs infinitely like asked. But why the other URL are note launched ??
Before that, I don't use function, I used one unique task with :
await cluster.task(async ({ page, data: url }) => {
But how combine function and this thing ?
My goal is to click on each link (called a footnote) on this page and then return the footnote link, text, and then all of the URLs that appear in the sidebar. I'm stuck on accessing the sidebar values when they appear and after a few weeks of failure, I'm looking for some pointers on what I'm doing wrong (very new to both javascript and puppeteer).
const puppeteer = require('puppeteer');
const url = 'https://www.churchofjesuschrist.org/study/scriptures/bofm/1-ne/11?lang=eng';
const selector = '.study-note-ref';
(async function () {
const browser = await puppeteer.launch({ headless: true });
const page = await browser.newPage();
await page.goto(url);
const footnotes = await page.$$eval(selector, nodes => {
return nodes.map(node => {
const ref = node.href.replace('https://www.churchofjesuschrist.org', '');
const txt = node.text;
return {
ref,
txt
};
});
});
for (const a of footnotes) {
page.click(a.ref);
const links = await page.$$eval('.scripture-ref', nodes => {
return nodes.map(node => {
return node.href
})
})
}
console.log(footnotes);
console.log(links);
// const fs = require('fs');
// fs.writeFile('./footnotes.json', JSON.stringify(footnotes), err => err ? console.log(err) : null);
await browser.close();
})();
Maybe something like this:
const puppeteer = require('puppeteer');
const url = 'https://www.churchofjesuschrist.org/study/scriptures/bofm/1-ne/11?lang=eng';
const selector = '.study-note-ref';
(async function main() {
const browser = await puppeteer.launch({ headless: true });
const [page] = await browser.pages();
await page.goto(url);
const data = {};
for (const footnote of await page.$$(selector)) {
const [href, text] = await page.evaluate(
(a) => {
a.click();
return [a.getAttribute('href').replace('/#note', ''), a.innerText.slice(1)];
},
footnote
);
data[href] = { text };
const header = await page.waitForXPath(`//aside/div/header/span[text()="${href} ${text}"]`);
data[href].links = await page.evaluate(
(span) => {
const aside = span.closest('aside');
return [...aside.querySelectorAll('a[href]')].map(
a => ({ [a.innerText]: a.href })
);
},
header
);
console.log(`Done: ${href} ${text}`);
}
console.log(JSON.stringify(data, null, 2));
await browser.close();
})();
Part of the output:
{
"1a": {
"text": "pondering",
"links": [
{
"D&C 76:19": "https://www.churchofjesuschrist.org/study/scriptures/dc-testament/dc/76.19?lang=eng#p19"
},
{
"TG Meditation": "https://www.churchofjesuschrist.org/study/scriptures/tg/meditation?lang=eng"
},
{
"Doctrine and Covenants 76:19": "https://www.churchofjesuschrist.org/study/scriptures/dc-testament/dc/76.19?lang=eng#p19#19"
},
{
"Meditation, Meditate": "https://www.churchofjesuschrist.org/study/scriptures/tg/meditation?lang=eng"
}
]
},
}
I want to use this package: sharp in beforeSaveFile trigger but it doesn't work. beforeSaveFile doesn't change anything.
My codes:
Parse.Cloud.define('test', async (req) => {
try {
const Resim = Parse.Object.extend('Resim')
const obj = new Resim()
const { photo } = req.params
let uploadedFile = await new Parse.File(
'galleryFile',
{ base64: photo },
'image/png'
)
obj.set('photo', uploadedFile)
const data = await obj.save()
return data
} catch (error) {
throw error
}
})
Parse.Cloud.beforeSaveFile(async (req) => {
const image = await sharp(req.file).resize(256)
return image
})
Thanks for help.
I figured out. This is the solution:
Parse.Cloud.beforeSaveFile(async (req) => {
const file = req.file
const fileData = await file.getData()
const str = fileData.toString('base64')
const imageBuffer = Buffer.from(str, 'base64')
const newImageBuffer = await sharp(imageBuffer)
.resize(800, 800)
.webp({ quality: 70, lossless: true })
.toBuffer()
return new Parse.File(
'image',
{ base64: newImageBuffer.toString('base64') },
'image/webp'
)
})
I'm new to web scraping and want to download all images on a webpage using puppeteer:
const puppeteer = require('puppeteer');
let scrape = async () => {
// Actual Scraping goes Here...
const browser = await puppeteer.launch({headless: false});
const page = await browser.newPage();
await page.goto('https://memeculture69.tumblr.com/');
// Right click and save images
};
scrape().then((value) => {
console.log(value); // Success!
});
I have looked at the API docs but could not figure out how to acheive this. So appreciate your help.
If you want to skip the manual dom traversal you can write the images to disk directly from the page response.
Example:
const puppeteer = require('puppeteer');
const fs = require('fs');
const path = require('path');
(async () => {
const browser = await puppeteer.launch();
const page = await browser.newPage();
page.on('response', async response => {
const url = response.url();
if (response.request().resourceType() === 'image') {
response.buffer().then(file => {
const fileName = url.split('/').pop();
const filePath = path.resolve(__dirname, fileName);
const writeStream = fs.createWriteStream(filePath);
writeStream.write(file);
});
}
});
await page.goto('https://memeculture69.tumblr.com/');
await browser.close();
})();
See the documentation for page.on and for the HTTPResponse object that you get from page.on('response', ...).
Here is another example. It goes to a generic search in google and downloads the google image at the top left.
const puppeteer = require('puppeteer');
const fs = require('fs');
async function run() {
const browser = await puppeteer.launch({
headless: false
});
const page = await browser.newPage();
await page.setViewport({ width: 1200, height: 1200 });
await page.goto('https://www.google.com/search?q=.net+core&rlz=1C1GGRV_enUS785US785&oq=.net+core&aqs=chrome..69i57j69i60l3j69i65j69i60.999j0j7&sourceid=chrome&ie=UTF-8');
const IMAGE_SELECTOR = '#tsf > div:nth-child(2) > div > div.logo > a > img';
let imageHref = await page.evaluate((sel) => {
return document.querySelector(sel).getAttribute('src').replace('/', '');
}, IMAGE_SELECTOR);
console.log("https://www.google.com/" + imageHref);
var viewSource = await page.goto("https://www.google.com/" + imageHref);
fs.writeFile(".googles-20th-birthday-us-5142672481189888-s.png", await viewSource.buffer(), function (err) {
if (err) {
return console.log(err);
}
console.log("The file was saved!");
});
browser.close();
}
run();
If you have a list of images you want to download then you could change the selector to programatically change as needed and go down the list of images downloading them one at a time.
You can use the following to scrape an array of all the src attributes of all images on the page:
const images = await page.evaluate(() => Array.from(document.images, e => e.src));
Then you can use the Node File System Module and HTTP or HTTPS Module to download each image.
Complete Example:
'use strict';
const fs = require('fs');
const https = require('https');
const puppeteer = require('puppeteer');
/* ============================================================
Promise-Based Download Function
============================================================ */
const download = (url, destination) => new Promise((resolve, reject) => {
const file = fs.createWriteStream(destination);
https.get(url, response => {
response.pipe(file);
file.on('finish', () => {
file.close(resolve(true));
});
}).on('error', error => {
fs.unlink(destination);
reject(error.message);
});
});
/* ============================================================
Download All Images
============================================================ */
(async () => {
const browser = await puppeteer.launch();
const page = await browser.newPage();
let result;
await page.goto('https://www.example.com/');
const images = await page.evaluate(() => Array.from(document.images, e => e.src));
for (let i = 0; i < images.length; i++) {
result = await download(images[i], `image-${i}.png`);
if (result === true) {
console.log('Success:', images[i], 'has been downloaded successfully.');
} else {
console.log('Error:', images[i], 'was not downloaded.');
console.error(result);
}
}
await browser.close();
})();
The logic is simple i think. You just need to make a function which will take url of image and save it to your directory. The puppeteer will just scrape the image url and pass it to downloader function. Here is an example:
const puppeteer = require('puppeteer');
const fs = require('fs');
const request = require('request');
// This is main download function which takes the url of your image
function download(uri, filename) {
return new Promise((resolve, reject) => {
request.head(uri, function (err, res, body) {
request(uri).pipe(fs.createWriteStream(filename)).on('close', resolve);
});
});
}
let main = async () => {
const browser = await puppeteer.launch({ headless: false });
const page = await browser.newPage();
await page.goto('https://memeculture69.tumblr.com/');
await page.waitFor(1000);
const imageUrl = await page.evaluate(
// here we got the image url from the selector.
() => document.querySelector('img.image')
);
// Now just simply pass the image url
// to the downloader function to download the image.
await download(imageUrl, 'image.png');
};
main();
This code saves all images found on the page into images folder
page.on('response', async (response) => {
const matches = /.*\.(jpg|png|svg|gif)$/.exec(response.url());
if (matches && (matches.length === 2)) {
const extension = matches[1];
const buffer = await response.buffer();
fs.writeFileSync(`images/${matches[0]}.${extension}`, buffer, 'base64');
}
});
For image download by its selector I did the following:
Obtained uri for the image using selector
Passed uri to the download function
const puppeteer = require('puppeteer');
const fs = require('fs');
var request = require('request');
//download function
var download = function (uri, filename, callback) {
request.head(uri, function (err, res, body) {
console.log('content-type:', res.headers['content-type']);
console.log('content-length:', res.headers['content-length']);
request(uri).pipe(fs.createWriteStream(filename)).on('close', callback);
});
};
(async () => {
const browser = await puppeteer.launch({
headless: true,
args: ['--no-sandbox', '--disable-setuid-sandbox'], //for no sandbox
});
const page = await browser.newPage();
await page.goto('http://example.com');// your url here
let imageLink = await page.evaluate(() => {
const image = document.querySelector('#imageId');
return image.src;
})
await download(imageLink, 'myImage.png', function () {
console.log('done');
});
...
})();
Resource: Downloading images with node.js
It is possible to get all the images without visiting each url independently. You need to listen to all the requests to the server:
await page.setRequestInterception(true)
await page.on('request', function (request) {
request.continue()
})
await page.on('response', async function (response) {
// Filter those responses that are interesting
const data = await response.buffer()
// data contains the img information
})
You can also filter based on the request type.
const blocked_resources = [
'stylesheet',
/*'image',*/
'media',
'font'
];
const _handleRequest = request => {
const type = request.resourceType();
if (blocked_resources.some(r => type === r)) {
request.abort();
return;
}
request.continue();
return;
}
const puppeteer = require("puppeteer")
const fs = require("fs/promises")
// add the url of website below which you want to scrape
const yourURL = "example.com"
async function scrapeIt() {
// it will launch browser
const browser = await puppeteer.launch()
// This line of code opens new page in browser
const page = await browser.newPage()
// page will open the webpage of your provided url
await page.goto(yourURL)
const photos = await page.$$eval("img", (imgs) => {
return imgs.map((x) => x.src)
})
for (const photo of photos) {
const imagepage = await page.goto(photo)
await fs.writeFile(photo.split("/").pop(), await imagepage.buffer())
}
await browser.close()
}
scrapeIt()
Download google images with 100% quality based on your search query using puppeteer in nodejs.
It is a straightforward approach.
Open google images.
Search for images using keyword.
Click the images one by one to open it's right preview panel.
Store all the links.
Download the images.
Note: If you download the images without previewing , you will lose quality.
const request = require('request');
const cheerio = require('cheerio');
const fs = require('fs');
var puppeteer = require('puppeteer');
const readline = require("readline-sync");
const path = require('path');
const axios = require('axios').default;
// fileUrl: the absolute url of the image or video you want to download
// downloadFolder: the path of the downloaded file on your machine
const downloadFile = async (fileUrl,localFilePath) => {
try {
const response = await axios({
method: 'GET',
url: fileUrl,
responseType: 'stream',
});
const w = response.data.pipe(fs.createWriteStream(localFilePath));
w.on('finish', () => {
console.log('Successfully downloaded file!');
});
} catch (err) {
throw new Error(err);
}
};
const Google_Image = 'https://www.google.com/search?site=&tbm=isch&source=hp&biw=1873&bih=990&'
let data = 'Ramayana HD Images Good Quality wallpaper'
let search_url = Google_Image + 'q=' + data;
var imagelinkslist =[];
let main = async () => {
const browser = await puppeteer.launch({ headless: false });
const page = await browser.newPage();
let result;
await page.goto(search_url);
// /html/body/div[2]/c-wiz/div[3]/div[1]/div/div/div/div[1]/div[1]/span/div[1]/div[1]/div[1]/a[1]/div[1]/img
// /html/body/div[2]/c-wiz/div[3]/div[1]/div/div/div/div[1]/div[1]/span/div[1]/div[1]/div[2]/a[1]/div[1]/img
let previewimagexpath = '/html/body/div[2]/c-wiz/div[3]/div[2]/div[3]/div/div/div[3]/div[2]/c-wiz/div/div[1]/div[1]/div[2]/div/a/img'
// previewimagexpath = '//*[#id="Sva75c"]/div/div/div[3]/div[2]/c-wiz/div/div[1]/div[1]/div[2]/div/a/img'
for(let i=1;i<20;i++)
{
let imagexpath = '/html/body/div[2]/c-wiz/div[3]/div[1]/div/div/div/div[1]/div[1]/span/div[1]/div[1]/div['+i+']/a[1]/div[1]/img'
const elements = await page.$x(imagexpath)
await elements[0].click();
await page.waitForTimeout(3000);
const image = await page.$x(previewimagexpath);
let d = await image[0].getProperty('src')
//console.log(d._remoteObject.value);
imagelinkslist.push(d._remoteObject.value)
}
await browser.close();
};
main().then(()=>{
console.log('Got Image links');
imagelinkslist.map((el,index)=>{
let url = el;
//console.log(url);
const path = `./images/image${index+1}.png`;
if(url.includes('https'))
downloadFile(url , path);
})
// console.log(imagelinkslist)
});