Created
November 13, 2012 15:16
-
-
Save egm0121/4066265 to your computer and use it in GitHub Desktop.
Demo PhantomJs Scraping + WebServer
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
var endpoints = { | |
'demo': 'https://www.google.it/search?hl=it&output=search' | |
}, | |
system = require('system'), | |
server = require('webserver').create(), | |
evaluate = function (page, func) { | |
var args = [].slice.call(arguments, 2); | |
var fn = "function() { return (" + func.toString() + ").apply(this, " + JSON.stringify(args) + ");}"; | |
return page.evaluate(fn); | |
}, | |
searchStrategy = { | |
'demo' :function(endpoint,opts,callback){ | |
var page = require('webpage').create(); | |
page.open(endpoint+'&q='+opts.name); | |
page.onLoadFinished = function(){ | |
callback(evaluate(page,function(){ | |
return document.querySelector('.g a').innerText; | |
})); | |
}; | |
} | |
}, | |
Query = { | |
param : function(name,url){ | |
var results = new RegExp('[\\?&]' + name + '=([^&#]*)').exec(url); | |
if (!results){ return 0; } | |
return results[1] || 0; | |
}, | |
url: function(s){ | |
return s.match(/^(?:([A-Za-z]+):)?(\/{0,3})([0-9.\-A-Za-z]+)(?::(\d+))?(?:\/([^?#]*))?(?:\?([^#]*))?(?:#(.*))?$/); | |
} | |
}; | |
console.log('starting PhantomJS Scrape Server >-(*,*)-< ...'); | |
console.log('http://host:8081/demo') | |
server.listen(8081, function (request, response) { | |
console.log('request started...') | |
response.headers = { "Content-Type": "application/json", | |
"Vary" : "Accept-Encoding" }; | |
response.statusCode = 404; | |
var parts = Query.url('http://example.com'+request.url)[5] ? | |
Query.url('http://example.com'+request.url)[5].split('/') : []; | |
if( parts[0] == 'status'){ | |
response.statusCode = 200; | |
response.write('OK'); | |
response.close(); | |
return true; | |
} | |
if( parts[0] in endpoints ){ | |
try { response.statusCode = 200; | |
var p = { | |
'name': Query.param('name',request.url), | |
'corpUser':'tmfastweb', | |
'corpPwd':'fastweb0121Ntv!'}; | |
for(var i in p){if(!p[i].length){throw 'error: missing search params'};} | |
searchStrategy['demo'](endpoints['demo'],p,function(data){response.write(data);response.close();}) | |
} catch(err) { | |
response.statusCode = 400; | |
response.write(JSON.stringify({error:'bad request / error processing the request',debug: err.toString()})); | |
response.close(); | |
} | |
return true; | |
} | |
response.write(JSON.stringify({error:'Endpoint Not Found'})); | |
response.close(); | |
return; | |
}); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment