I am new to nodejs. I want to use jsdom to parse some web pages which may contain script code inside. But I got error said the function or variable was not defined. Can anyone give some directions about this.
my code
var jsdom = require('jsdom');
jsdom.env({
html: 'http://10.200.0.10:8080/test/a.html',
scripts: [
'http://code.jquery.com/jquery-1.5.min.js'
],
done: function(errors, window) {
var $ = window.$;
window.onload();
console.log(window.a);
}
});
and the html page here
<html>
<head>
<script>
var a = 0;
function loads(){
a=1000;
}
</script>
</head>
<body onload='loads()'>
</body>
</html>
and got error message below
dfddddfdf
undefined:1: ReferenceError: loads is not defined
loads()
^
ReferenceError: loads is not defined
at unknown source
at /root/node_modules/jsdom/node_modules/contextify/lib/contextify.js:10:24
at /root/node_modules/jsdom/lib/jsdom/level1/core.js:1024:50
at /root/testnode.js:18:12
at Array.0 (/root/node_modules/jsdom/lib/jsdom.js:199:39)
at EventEmitter._tickCallback (node.js:192:40)
node.js:201
throw e; // process.nextTick error, or 'error' event on first tick
^
ReferenceError: loads is not defined
at unknown source
at /root/node_modules/jsdom/node_modules/contextify/lib/contextify.js:10:24
at /root/node_modules/jsdom/lib/jsdom/level1/core.js:1024:50
at /root/testnode.js:18:12
at Array.0 (/root/node_modules/jsdom/lib/jsdom.js:199:39)
at EventEmitter._tickCallback (node.js:192:40)
It reports the loads function was not defined, but it actually was declared in the web page.
Can anyone give some suggestions, or just simply tell me jsdom cannot process the scripts embedded in page.
Here's the code that you want to have:
var fs = require('fs');
var jsdom = require('jsdom');
var doc = jsdom.jsdom(fs.readFileSync("a.html"), null, {
features: {
FetchExternalResources : ['script'],
ProcessExternalResources : ['script'],
MutationEvents : '2.0',
}
});
var window = doc.createWindow();
jsdom.jQueryify(window, "http://code.jquery.com/jquery-1.5.min.js", function() {
console.log(window.a);
console.log(window.$().jquery); //jquery version
});
Your code will not work because the jsdom.env
method does not process scripts.
Please note that you should use an awesome npm library request
Try this:
var http = require('http'),
jsdom = require('jsdom'),
request = require('request');
var server = http.createServer(function (request, response) {
getPage("http://isohunt.com/torrents/?iht=-1&ihq=life+is+beautiful", function (body) {
jsdom.env({
html: body,
scripts: ['http://code.jquery.com/jquery-1.6.min.js']
}, function(err, window){
var $ = window.jQuery;
//your code goes here
});
})
});
server.listen(3000);
function getPage(someUri, callback) {
request({uri : someUri}, function (error, response, body) {
callback(body);
});
}