I use NodeJs and ZombieJS to receive url requests in a virtual browser environment.
I am using the following code:
var zombie = require('zombie'),
jsdom = require('jsdom'),
my_sandbox = require('sandbox'),
url = require('url'),
http = require('http'),
request = require('request'),
httpProxy = require('./lib/node-http-proxy'),
des = '',
util = require('util'),
colors = require('colors'),
is_host = true;
var s = new my_sandbox();
var browser = new zombie.Browser;
httpProxy.createServer(9000, 'localhost').listen(8000);
function zombieFetching(page) {
browser.visit(page, { debug: false },
function(err, browser, status) {
if(err) {
console.log('There is an error. Fix it');
throw(err.message);
} else {
console.log('Browser visit successful') ;
}
});
}
var server = http.createServer(function (req, res) {
var pathname = '';
if(is_host) {
dest = req.url.substr(0, req.url.length);
pathname = dest;
is_host = false;
} else {
pathname = req.url.substr(0, req.url.length);
if(pathname.charAt(0) == "/") {
console.log('new request');
console.log(pathname);
pathname = dest + pathname;
}
}
request.get({uri: pathname}, function (err, response, html) {
console.log('The pathname is:::::::::: ' + pathname);
zombieFetching(pathname);
res.end(html);
});
});
server.listen(9000);
I see the following error when trying to get the url: "www.yahoo.com"
home/seed/Desktop/Cloud project/node_modules/zombie/node_modules/html5/lib/html5/tokenizer.js:62
throw(e);
^
Error: undefined: Invalid character in tag name:
at Object.createElement (/home/seed/Desktop/Cloud project/node_modules/zombie/node_modules/jsdom/lib/jsdom/level1/core.js:1174:13)
at TreeBuilder.createElement (/home/seed/Desktop/Cloud project/node_modules/zombie/node_modules/html5/lib/html5/treebuilder.js:29:25)
at TreeBuilder.insert_element_normal (/home/seed/Desktop/Cloud project/node_modules/zombie/node_modules/html5/lib/html5/treebuilder.js:61:21)
at TreeBuilder.insert_element (/home/seed/Desktop/Cloud project/node_modules/zombie/node_modules/html5/lib/html5/treebuilder.js:52:15)
at Object.startTagOther (/home/seed/Desktop/Cloud project/node_modules/zombie/node_modules/html5/lib/html5/parser/in_body_phase.js:483:12)
at Object.processStartTag (/home/seed/Desktop/Cloud project/node_modules/zombie/node_modules/html5/lib/html5/parser/phase.js:43:44)
at EventEmitter.do_token (/home/seed/Desktop/Cloud project/node_modules/zombie/node_modules/html5/lib/html5/parser.js:94:20)
at EventEmitter.<anonymous> (/home/seed/Desktop/Cloud project/node_modules/zombie/node_modules/html5/lib/html5/parser.js:112:30)
at EventEmitter.emit (events.js:64:17)
at EventEmitter.emitToken (/home/seed/Desktop/Cloud project/node_modules/zombie/node_modules/html5/lib/html5/tokenizer.js:84:7)
In addition, the log statements are as follows:
The pathname is:::::::::: http://www.yahoo.com/
The pathname is:::::::::: http://l1.yimg.com/a/i/ww/news/2011/05/06/zuckhouse-sm.jpg
The pathname is:::::::::: http://l1.yimg.com/a/i/ww/news/2011/05/07/cable-sm.jpg
The pathname is:::::::::: http://l.yimg.com/a/a/1-/flash/promotions/yahoo/081120/70x50iltlb_2.jpg
Browser visit successful
Browser visit successful
Browser visit successful
Browser visit successful
The pathname is:::::::::: http://l.yimg.com/a/i/vm/2011may/bird74.jpg
The pathname is:::::::::: http://www.yahoo.com/jserror?ad=1&target=cms&data=FPAD
From what I understand, the first four requests were successful. However, I don't know why the zombie is retrieving the wrong request:
"http://www.yahoo.com/jserror?ad=1&target=cms&data=FPAD"
Also, what causes an invalid character in the tag name error?
Thanks Sony