I'm going to be honest. I'm way in over my head here.
I need to scrape data from a dynamic site for my employer. Before the data is visible on the page, there are some clicks and waits necessary. Simple PHP scraping won't do. So I found out about this NodeJS + PhantomJS combo. Quite a pain to set up, but I did manage to load a site, run some code and get a result.
I wrote a piece of jQuery which uses timeout loops to wait for some data to be loaded. Eventually I get a js object that I want to write to a file (JSON).
The issue I'm facing.
I build up the the js object inside the PhantomJS .evaluate scope, which runs in a headerless browser, so not directly in my Node.JS server scope. How do I send the variable I built up inside evaluate back to my server so I can write it to my file?
Some example code (I know it's ugly, but it's for illustrative purposes). I use node-phantom-simple as a bridge between Phantom and Node
var phantom = require('node-phantom-simple'),
fs = require('fs'),
webPage = 'https://www.imagemedia.com/printing/business-card-printing/'
phantom.create(function(err, ph) {
return ph.createPage(function(err, page) {
return page.open(webPage, function(err, status) {
page.onConsoleMessage = function(msg) {
console.log(msg);
};
console.log("opened site? ", status);
page.evaluate(function() {
setTimeout(function() {
$('.price-select-cnt').eq(0).find('select').val('1266').change()
timeOutLoop()
function timeOutLoop() {
console.log('looping')
setTimeout(function() {
if ($('#ajax_price_tool div').length != 6) {
timeOutLoop()
} else {
$('.price-select-cnt').eq(1).find('select').val('25')
$('.price-select-cnt').eq(2).find('select').val('Premium Card Stock')
$('.price-select-cnt').eq(3).find('select').val('Standard').change()
timeOutLoop2()
}
}, 100)
}
function timeOutLoop2() {
console.log('looping2')
setTimeout(function() {
if ($('.pricing-cost-cnt').text() == '$0' || $('.pricing-cost-cnt').text() == '') {
timeOutLoop2()
} else {
var price = $('.pricing-cost-cnt').text()
console.log(price)
}
}, 100)
}
}, 4000)
});
});
});
});
function writeJSON(plsWrite) {
var key = 'file'
fs.writeFile('./results/' + key + '.json', plsWrite, 'utf8', function() {
console.log('The JSON file is saved as');
console.log('results/' + key + '.json');
});
}
So do do I write the price this code takes from the website, get it out of the evaluate scope and write it to a file?
I'm building an app for windows using Electron. To package and distribute it I'm using electron-builder. Electron-builder relies on many packages, and for auto-updates it uses Squirrel-windows.
I've been battling with auto-update on Windows for 3 days and at the end I've come up with a working solution that seems to give no problems.
I wont' go into the details of what I've tried, and failed. Instead, I'll post here the solution with which I've come up.
I'm sharing it with you guys, to see if you may point out to me any flaws that will make my system fail, or, if it truly is a solid solution, to help those who are struggling as I was. For this latter reason, I'm posting some more code than it would be necessary, hoping it will help others.
The logic is as follows:
if the sub-folder fullupdate inside the path of the current executable does not exists (see later, it will be clarified), we connect with an online server and check if there is an update by sending the current app version;
if there is no update, do nothing.
if there is an update, we instruct the server to return a json string that contains the url from which we can download of the .exe installer produced by electron-builder. NB: not the .nupkg (server code not provided :-)).
we download the file and save it inside a sub folder fullupdate in the local folder in which our app is currently saved. This should be "safe" as electron-builder saves the app in the current user folder AppData, so we should not have permissions issues.
at the end of the download, we create a new file update inside the folder fullupdate to be sure the download has finished successfully. We could also rename the file, but I prefer this way.
next time the app opens:
if the folder fullupdate exists we check if the file update exists. If it does not exists, the download was not finished, so we delete the folder fullupdate and call the remote server again to start all over again.
else, if the file update exists, we launch the .exe file we have downloaded, and return true. This will prevent the app from opening the main window. The cool thing is that the updater will delete the whole old version of the app saved in AppData (while leaving local user data) and replace it with the new version. In this way we will get rid also of the folder fullupdate.
Now the code:
// we want to run this only on windows
var handleStartupEvent = function() {
if (process.platform !== 'win32') {
return false;
}
/////////////////
// MANUAL UPDATER
/////////////////
var appFolder = 'app-' + appVersion;
var pathApp = path.dirname(process.execPath);
var pathUpdate = pathApp + '\\fullupdate';
var checkupdateurl = 'https://api.mysite.com/getjson/' + appVersion.split('.').join('-');
function checkIfDownloaded(){
if (!fs.existsSync(pathUpdate)) checkUpdate();
else return checkIfInstallLocal();
}
function checkIfInstallLocal(){
if(fileExists('fullupdate\\update')) return installLocal();
else {
deleteFolderRecursive(pathUpdate);
checkUpdate();
}
}
function installLocal(){
cp.exec('fullupdate\\Update.exe', function( error, stdout, stderr){
if ( error != null ) {
console.log(stderr);
}
});
return true;
}
// from http://www.geedew.com/remove-a-directory-that-is-not-empty-in-nodejs/
var deleteFolderRecursive = function(path) {
if( fs.existsSync(path) ) {
fs.readdirSync(path).forEach(function(file,index){
var curPath = path + "/" + file;
if(fs.lstatSync(curPath).isDirectory()) deleteFolderRecursive(curPath);
else fs.unlinkSync(curPath);
});
fs.rmdirSync(path);
}
};
// from http://stackoverflow.com/questions/4482686/check-synchronously-if-file-directory-exists-in-node-js
function fileExists(path) {
try {
return fs.statSync(path).isFile();
}
catch (e) {
if (e.code == 'ENOENT') { // no such file or directory. File really does not exist
return false;
}
throw e; // something else went wrong, we don't have rights, ...
}
}
function checkUpdate(){
https.get('https://api.mysite.com/getjson/' + app.getVersion().split('.').join('-'), (res) => {
res.setEncoding('utf8');
res.on('data', function(chunk) {
if(chunk) thereIsUpdate(chunk);
});
}).on('error', (e) => {
console.log(e);
});
}
function thereIsUpdate(chunk){
var data = JSON.parse(chunk);
if(data && data.url) getNewUpdate(data.urlsetup);
}
function getNewUpdate(url){
fs.mkdirSync(pathUpdate);
var file = fs.createWriteStream(pathUpdate + '/Update.exe');
var responseSent = false; // flag to make sure that response is sent only once.
var request = https.get(url, function(response) {
response.pipe(file);
file.on('finish', () =>{
file.close(() => {
if(responseSent) return;
responseSent = true;
});
fs.closeSync(fs.openSync(pathUpdate + '/update', 'w'));
});
});
}
if(checkIfDownloaded()) return true;
/////////////////////////
// SQUIRREL EVENTS HANDLER
//////////////////////////
// see http://stackoverflow.com/questions/30105150/handle-squirrels-event-on-an-electron-app
};
// here we call the function. It is before the opening of the window, so that we prevent the opening if we are updating, or if there is a Squirrel event going on (see SO question, link above)
if (handleStartupEvent()) {
return;
}
I'm trying to stream a cat command using the ssh2 module but it just hangs at some point of the execution. I'm executing cat there.txt where there.txt is around 10 MB or so.
For example:
local = fs.createWriteStream('here.txt');
conn.exec('cat there.txt', function(err, stream) {
if (err) throw err;
stream.pipe(local).on('finish, function() { console.log('Done'); });
}
This just completely stops at one point. I've even piped the stream to local stdout, and it just hangs after a while. In my actual code, I pipe it through a bunch of other transform streams so I think this is better than transferring the files to the local system first (the files may get larger than 200MB).
I had just started working with streams recently so I when I was piping the ssh stream through various transform streams, I wasn't ending on a writable stream like I was in my example (I should've included my actual code, sorry!). This caused it to hang. This was originally so that I could execute multiple commands remotely and put their output sorted into a single file.
So, my original code was stream.pipe(transformStream), then push the transformStream to an array once it's finished. And then sort it using the mergesort-stream npm module. Instead of that, I just write the results from the multiple ssh commands (transformed) to temporary files and then sort them all at once.
Try out the createReadStream for serving huge files:
fs.exists(correctfilepath, function(exists) {
if (exists) {
var readstream = fs.createReadStream(correctfilepath);
console.log("About to serve " + correctfilepath);
res.writeHead(200);
readstream.setEncoding("binary");
readstream.on("data", function (chunk) {
res.write(chunk, "binary");
});
readstream.on("end", function () {
console.log("Served file " + correctfilepath);
res.end();
});
readstream.on('error', function(err) {
res.write(err + "\n");
res.end();
return;
});
} else {
res.writeHead(404);
res.write("No data\n");
res.end();
}
});
fs.watch( 'example.xml', function ( curr, prev ) {
// on file change we can read the new xml
fs.readFile( 'example.xml','utf8', function ( err, data ) {
if ( err ) throw err;
console.dir(data);
console.log('Done');
});
});
OUTPUT:
some data
Done X 1
some data
Done X 2
It is my usage fault or ..?
The fs.watch api:
is unstable
has known "behaviour" with regards repeated notifications. Specifically, the windows case being a result of windows design, where a single file modification can be multiple calls to the windows API
I make allowance for this by doing the following:
var fsTimeout
fs.watch('file.js', function(e) {
if (!fsTimeout) {
console.log('file.js %s event', e)
fsTimeout = setTimeout(function() { fsTimeout=null }, 5000) // give 5 seconds for multiple events
}
}
I suggest to work with chokidar (https://github.com/paulmillr/chokidar) which is much better than fs.watch:
Commenting its README.md:
Node.js fs.watch:
Doesn't report filenames on OS X.
Doesn't report events at all when using editors like Sublime on OS X.
Often reports events twice.
Emits most changes as rename.
Has a lot of other issues
Does not provide an easy way to recursively watch file trees.
Node.js fs.watchFile:
Almost as bad at event handling.
Also does not provide any recursive watching.
Results in high CPU utilization.
If you need to watch your file for changes then you can check out my small library on-file-change. It checks file sha1 hash between fired change events.
Explanation of why we have multiple fired events:
You may notice in certain situations that a single creation event generates multiple Created events that are handled by your component. For example, if you use a FileSystemWatcher component to monitor the creation of new files in a directory, and then test it by using Notepad to create a file, you may see two Created events generated even though only a single file was created. This is because Notepad performs multiple file system actions during the writing process. Notepad writes to the disk in batches that create the content of the file and then the file attributes. Other applications may perform in the same manner. Because FileSystemWatcher monitors the operating system activities, all events that these applications fire will be picked up.
Source
My custom solution
I personally like using return to prevent a block of code to run when checking something, so, here is my method:
var watching = false;
fs.watch('./file.txt', () => {
if(watching) return;
watching = true;
// do something
// the timeout is to prevent the script to run twice with short functions
// the delay can be longer to disable the function for a set time
setTimeout(() => {
watching = false;
}, 100);
};
Feel free to use this example to simplify your code. It may NOT be better than using a module from others, but it works pretty well!
Similar/same problem. I needed to do some stuff with images when they were added to a directory. Here's how I dealt with the double firing:
var fs = require('fs');
var working = false;
fs.watch('directory', function (event, filename) {
if (filename && event == 'change' && active == false) {
active = true;
//do stuff to the new file added
active = false;
});
It will ignore the second firing until if finishes what it has to do with the new file.
I'm dealing with this issue for the first time, so all of the answers so far are probably better than my solution, however none of them were 100% suitable for my case so I came up with something slightly different – I used a XOR operation to flip an integer between 0 and 1, effectively keeping track of and ignoring every second event on the file:
var targetFile = "./watchThis.txt";
var flippyBit = 0;
fs.watch(targetFile, {persistent: true}, function(event, filename) {
if (event == 'change'){
if (!flippyBit) {
var data = fs.readFile(targetFile, "utf8", function(error, data) {
gotUpdate(data);
})
} else {
console.log("Doing nothing thanks to flippybit.");
}
flipBit(); // call flipBit() function
}
});
// Whatever we want to do when we see a change
function gotUpdate(data) {
console.log("Got some fresh data:");
console.log(data);
}
// Toggling this gives us the "every second update" functionality
function flipBit() {
flippyBit = flippyBit ^ 1;
}
I didn't want to use a time-related function (like jwymanm's answer) because the file I'm watching could hypothetically get legitimate updates very frequently. And I didn't want to use a list of watched files like Erik P suggests, because I'm only watching one file. Jan Święcki's solution seemed like overkill, as I'm working on extremely short and simple files in a low-power environment. Lastly, Bernado's answer made me a little nervous – it would only ignore the second update if it arrived before I'd finished processing the first, and I can't handle that kind of uncertainty. If anyone were to find themselves in this very specific scenario, there might be some merit to the approach I used? If there's anything massively wrong with it please do let me know/edit this answer, but so far it seems to work well?
NOTE: Obviously this strongly assumes that you'll get exactly 2 events per real change. I carefully tested this assumption, obviously, and learned its limitations. So far I've confirmed that:
Modifying a file in Atom editor and saving triggers 2 updates
touch triggers 2 updates
Output redirection via > (overwriting file contents) triggers 2 updates
Appending via >> sometimes triggers 1 update!*
I can think of perfectly good reasons for the differing behaviours but we don't need to know why something is happening to plan for it – I just wanted to stress that you'll want to check for yourself in your own environment and in the context of your own use cases (duh) and not trust a self-confessed idiot on the internet. That being said, with precautions taken I haven't had any weirdness so far.
* Full disclosure, I don't actually know why this is happening, but we're already dealing with unpredictable behaviour with the watch() function so what's a little more uncertainty? For anyone following along at home, more rapid appends to a file seem to cause it to stop double-updating but honestly, I don't really know, and I'm comfortable with the behaviour of this solution in the actual case it'll be used, which is a one-line file that will be updated (contents replaced) like twice per second at the fastest.
first is change and the second is rename
we can make a difference from the listener function
function(event, filename) {
}
The listener callback gets two arguments (event, filename). event is either 'rename' or 'change', and filename is the name of the file which triggered the event.
// rm sourcefile targetfile
fs.watch( sourcefile_dir , function(event, targetfile)){
console.log( targetfile, 'is', event)
}
as a sourcefile is renamed as targetfile, it's will call three event as fact
null is rename // sourcefile not exist again
targetfile is rename
targetfile is change
notice that , if you want catch all these three evnet, watch the dir of sourcefile
I somtimes get multible registrations of the Watch event causing the Watch event to fire several times.
I solved it by keeping a list of watching files and avoid registering the event if the file allready is in the list:
var watchfiles = {};
function initwatch(fn, callback) {
if watchlist[fn] {
watchlist[fn] = true;
fs.watch(fn).on('change', callback);
}
}
......
Like others answers says... This got a lot of troubles, but i can deal with this in this way:
var folder = "/folder/path/";
var active = true; // flag control
fs.watch(folder, function (event, filename) {
if(event === 'rename' && active) { //you can remove this "check" event
active = false;
// ... its just an example
for (var i = 0; i < 100; i++) {
console.log(i);
}
// ... other stuffs and delete the file
if(!active){
try {
fs.unlinkSync(folder + filename);
} catch(err) {
console.log(err);
}
active = true
}
}
});
Hope can i help you...
Easiest solution:
const watch = (path, opt, fn) => {
var lock = false
fs.watch(path, opt, function () {
if (!lock) {
lock = true
fn()
setTimeout(() => lock = false, 1000)
}
})
}
watch('/path', { interval: 500 }, function () {
// ...
})
I was downloading file with puppeteer and once a file saved, I was sending automatic emails. Due to problem above, I noticed, I was sending 2 emails. I solved by stopping my application using process.exit() and auto-start with pm2. Using flags in code didn't saved me.
If anyone has this problem in future, one can use this solution as well. Exit from program and restart with monitor tools automatically.
Here's my simple solution. It works well every time.
// Update obj as file updates
obj = JSON.parse(fs.readFileSync('./file.json', 'utf-8'));
fs.watch('./file.json', () => {
const data = JSON.parse(fs.readFileSync('./file.json', 'utf-8') || '{}');
if(Object.entries(data).length > 0) { // This checks fs.watch() isn't false-firing
obj = data;
console.log('File actually changed: ', obj)
}
});
I came across the same issue. If you don't want to trigger multiple times, you can use a debounce function.
fs.watch( 'example.xml', _.debounce(function ( curr, prev ) {
// on file change we can read the new xml
fs.readFile( 'example.xml','utf8', function ( err, data ) {
if ( err ) throw err;
console.dir(data);
console.log('Done');
});
}, 100));
Debouncing The Observer
A solution I arrived at was that (a) there needs to be a workaround for the problem in question and, (b), there needs to be a solution to ensure multiple rapid Ctrl+s actions do not cause Race Conditions. Here's what I have...
./**/utilities.js (somewhere)
export default {
...
debounce(fn, delay) { // #thxRemySharp https://remysharp.com/2010/07/21/throttling-function-calls/
var timer = null;
return function execute(...args) {
var context = this;
clearTimeout(timer);
timer = setTimeout(fn.bind(context, ...args), delay);
};
},
...
};
./**/file.js (elsewhere)
import utilities from './**/utilities.js'; // somewhere
...
function watch(server) {
const debounced = utilities.debounce(observeFilesystem.bind(this, server), 1000 * 0.25);
const observers = new Set()
.add( fs.watch('./src', debounced) )
.add( fs.watch('./index.html', debounced) )
;
console.log(`watching... (${observers.size})`);
return observers;
}
function observeFilesystem(server, type, filename) {
if (!filename) console.warn(`Tranfer Dev Therver: filesystem observation made without filename for type ${type}`);
console.log(`Filesystem event occurred:`, type, filename);
server.close(handleClose);
}
...
This way, the observation-handler that we pass into fs.watch is [in this case a bound bunction] which gets debounced if multiple calls are made less than 1000 * 0.25 seconds (250ms) apart from one another.
It may be worth noting that I have also devised a pipeline of Promises to help avoid other types of Race Conditions as the code also leverages other callbacks. Please also note the attribution to Remy Sharp whose debounce function has repeatedly proven very useful over the years.
watcher = fs.watch( 'example.xml', function ( curr, prev ) {
watcher.close();
fs.readFile( 'example.xml','utf8', function ( err, data ) {
if ( err ) throw err;
console.dir(data);
console.log('Done');
});
});
I had similar similar problem but I was also reading the file in the callback which caused a loop.
This is where I found how to close watcher:
How to close fs.watch listener for a folder
NodeJS does not fire multiple events for a single change, it is the editor you are using updating the file multiple times.
Editors use stream API for efficiency, they read and write data in chunks which causes multiple updates depending on the chunks size and the amount of content. Here is a snippet to test if fs.watch fires multiple events:
const http = require('http');
const fs = require('fs');
const path = require('path');
const host = 'localhost';
const port = 3000;
const file = path.join(__dirname, 'config.json');
const requestListener = function (req, res) {
const data = new Date().toString();
fs.writeFileSync(file, data, { encoding: 'utf-8' });
res.end(data);
};
const server = http.createServer(requestListener);
server.listen(port, host, () => {
fs.watch(file, (eventType, filename) => {
console.log({ eventType });
});
console.log(`Server is running on http://${host}:${port}`);
});
I believe a simple solution would be checking for the last modified timestamp:
let lastModified;
fs.watch(file, (eventType, filename) => {
stat(file).then(({ mtimeMs }) => {
if (lastModified !== mtimeMs) {
lastModified = mtimeMs;
console.log({ eventType, filename });
}
});
});
Please note that you need to use all-sync or all-async methods otherwise you will have issues:
Update the file in a editor, you will see only single event is logged:
const http = require('http');
const host = 'localhost';
const port = 3000;
const fs = require('fs');
const path = require('path');
const file = path.join(__dirname, 'config.json');
let lastModified;
const requestListener = function (req, res) {
const data = Date.now().toString();
fs.writeFileSync(file, data, { encoding: 'utf-8' });
lastModified = fs.statSync(file).mtimeMs;
res.end(data);
};
const server = http.createServer(requestListener);
server.listen(port, host, () => {
fs.watch(file, (eventType, filename) => {
const mtimeMs = fs.statSync(file).mtimeMs;
if (lastModified !== mtimeMs) {
lastModified = mtimeMs;
console.log({ eventType });
}
});
console.log(`Server is running on http://${host}:${port}`);
});
Few notes on the alternative solutions: Storing files for comparison will be memory inefficient especially if you have large files, taking file hashes will be expensive, custom flags are hard to keep track of, especially if you are going to detect changes made by other applications, and lastly unsubscribing and re-subscribing requires unnecessary juggling.
If you don't need an instant result, you can use setTimout to debounce successive events:
let timeoutId;
fs.watch(file, (eventType, filename) => {
clearTimeout(timeoutId);
timeoutId = setTimeout(() => {
console.log({ eventType });
}, 100);
});