Created
September 20, 2010 15:50
-
-
Save cou929/588110 to your computer and use it in GitHub Desktop.
Code snippet to scrape web site using jquery.
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
/** | |
* scrape.js | |
* Code snippet to scrape web site using jquery. | |
* This code is from WEB+DB Press Vol.51 JavaScript 今ドキ活用術 by Shinichi Tomita | |
*/ | |
jQuery.noConflict(); | |
(function($) { | |
jQuery.fn.scrape = function(def) { | |
// get text value from DOM node | |
function getText(n) { | |
return n && $(n).text(); | |
} | |
// make function which gets attribute value from DOM node | |
function getAttr(a) { | |
return function(n) { | |
return n && $(n).attr(a); | |
}; | |
} | |
// make function which construct Object from definition object | |
function getRecord(o) { | |
return function(n) { | |
if (!n) return null; | |
var rec = {}; | |
for (var k in o) { | |
if (o.hasOwnProperty(k)) | |
rec[k] = $(n).scrape(o[k]); | |
} | |
return rec; | |
}; | |
} | |
if (typeof def == 'string') | |
def = {'selector': def}; | |
var value = def.value; | |
var type = typeof value; | |
var toValue = | |
type == 'function' ? value : | |
type == 'object' ? getRecord(value) : | |
type == 'string' && value.indexOf('@') == 0 ? getAttr(value.substring(1)) : | |
getText; | |
return def.array ? | |
this.find(def.selector).map(function() {return toValue(this);}) : | |
toValue(this.find(def.selector).get(0)); | |
}; | |
})(jQuery); | |
// =========== | |
// how to use | |
// =========== | |
// | |
// var record = $(document).scrape({ | |
// selector: '#foo > div.bar', | |
// array: true, | |
// value: { | |
// title: 'div:first > div.foo a', | |
// link: { | |
// selector: 'div:first > div.foo a', | |
// value: '@href' | |
// }, | |
// price: { | |
// selector: 'span.price', | |
// value: function(n) { | |
// return parseInt(n.firstChild.data.replace(/[^\d]/g, '')); | |
// } | |
// } | |
// } | |
// }); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment