下面是一个PhantomJS示例,它通过外部网页上的DOM id获取一些元素:
var page = require('webpage').create();
console.log('The default user agent is ' + page.settings.userAgent);
page.settings.userAgent = 'SpecialAgent';
page.open('http://www.httpuseragent.org', function(status) {
if (status !== 'success') {
console.log('Unable to access network');
} else {
var ua = page.evaluate(function() {
return document.getElementById('myagent').textContent;
});
console.log(ua);
}
phantom.exit();
});
我想获取网页的整个HTML源代码…我该怎么做?