ast*_*123 12 ajax google-chrome web-scraping phantomjs casperjs
网页上的数据是动态显示的,似乎检查html中的每个更改并提取数据是一项非常艰巨的任务,还需要我使用非常不可靠的XPath.所以我希望能够从XHR
数据包中提取数据.
我希望能够从XHR
数据包中提取信息,并生成要发送到服务器的"XHR"数据包.提取信息部分对我来说更重要,因为可以通过使用casperjs自动触发html元素来轻松处理信息的发送.
我附上了我的意思截图.
响应选项卡中的文本是我之后需要处理的数据.(已从服务器收到此XHR响应.)
Art*_* B. 22
这不容易实现,因为resource.received
事件处理程序仅提供元数据url
,headers
或者status
不提供实际数据.底层的phantomjs事件处理程序的行为方式相同.
如果ajax调用是无状态的,您可以重复该请求
casper.on("resource.received", function(resource){
// somehow identify this request, here: if it contains ".json"
// it also also only does something when the stage is "end" otherwise this would be executed two times
if (resource.url.indexOf(".json") != -1 && resource.stage == "end") {
var data = casper.evaluate(function(url){
// synchronous GET request
return __utils__.sendAJAX(url, "GET");
}, resource.url);
// do something with data, you might need to JSON.parse(data)
}
});
casper.start(url); // your script
Run Code Online (Sandbox Code Playgroud)
您可能想要添加事件侦听器resource.requested
.这样你就不需要通过电话来完成.
您也可以在控制流内部执行此操作(源:A:CasperJS waitForResource:如何获取我等待的资源):
casper.start(url);
var res, resData;
casper.waitForResource(function check(resource){
res = resource;
return resource.url.indexOf(".json") != -1;
}, function then(){
resData = casper.evaluate(function(url){
// synchronous GET request
return __utils__.sendAJAX(url, "GET");
}, res.url);
// do something with the data here or in a later step
});
casper.run();
Run Code Online (Sandbox Code Playgroud)
如果它不是无状态的,则需要替换XMLHttpRequest的实现.您需要注入自己的onreadystatechange
处理程序实现,收集页面window
对象中的信息,然后在另一个evaluate
调用中收集它.
您可能希望查看sinon.js中的XHR faker或使用以下完整代理XMLHttpRequest
(我在如何创建XMLHttpRequest包装器/代理的方法3之后对其进行建模?):
function replaceXHR(){
(function(window, debug){
function args(a){
var s = "";
for(var i = 0; i < a.length; i++) {
s += "\t\n[" + i + "] => " + a[i];
}
return s;
}
var _XMLHttpRequest = window.XMLHttpRequest;
window.XMLHttpRequest = function() {
this.xhr = new _XMLHttpRequest();
}
// proxy ALL methods/properties
var methods = [
"open",
"abort",
"setRequestHeader",
"send",
"addEventListener",
"removeEventListener",
"getResponseHeader",
"getAllResponseHeaders",
"dispatchEvent",
"overrideMimeType"
];
methods.forEach(function(method){
window.XMLHttpRequest.prototype[method] = function() {
if (debug) console.log("ARGUMENTS", method, args(arguments));
if (method == "open") {
this._url = arguments[1];
}
return this.xhr[method].apply(this.xhr, arguments);
}
});
// proxy change event handler
Object.defineProperty(window.XMLHttpRequest.prototype, "onreadystatechange", {
get: function(){
// this will probably never called
return this.xhr.onreadystatechange;
},
set: function(onreadystatechange){
var that = this.xhr;
var realThis = this;
that.onreadystatechange = function(){
// request is fully loaded
if (that.readyState == 4) {
if (debug) console.log("RESPONSE RECEIVED:", typeof that.responseText == "string" ? that.responseText.length : "none");
// there is a response and filter execution based on url
if (that.responseText && realThis._url.indexOf("whatever") != -1) {
window.myAwesomeResponse = that.responseText;
}
}
onreadystatechange.call(that);
};
}
});
var otherscalars = [
"onabort",
"onerror",
"onload",
"onloadstart",
"onloadend",
"onprogress",
"readyState",
"responseText",
"responseType",
"responseXML",
"status",
"statusText",
"upload",
"withCredentials",
"DONE",
"UNSENT",
"HEADERS_RECEIVED",
"LOADING",
"OPENED"
];
otherscalars.forEach(function(scalar){
Object.defineProperty(window.XMLHttpRequest.prototype, scalar, {
get: function(){
return this.xhr[scalar];
},
set: function(obj){
this.xhr[scalar] = obj;
}
});
});
})(window, false);
}
Run Code Online (Sandbox Code Playgroud)
如果要从一开始就捕获AJAX调用,则需要将其添加到第一个事件处理程序之一
casper.on("page.initialized", function(resource){
this.evaluate(replaceXHR);
});
Run Code Online (Sandbox Code Playgroud)
或者evaluate(replaceXHR)
当你需要它时.
控制流程如下所示:
function replaceXHR(){ /* from above*/ }
casper.start(yourUrl, function(){
this.evaluate(replaceXHR);
});
function getAwesomeResponse(){
return this.evaluate(function(){
return window.myAwesomeResponse;
});
}
// stops waiting if window.myAwesomeResponse is something that evaluates to true
casper.waitFor(getAwesomeResponse, function then(){
var data = JSON.parse(getAwesomeResponse());
// Do something with data
});
casper.run();
Run Code Online (Sandbox Code Playgroud)
如上所述,我为XMLHttpRequest创建了一个代理,这样每次在页面上使用它时,我都可以用它做一些事情.您抓取的页面使用xhr.onreadystatechange
回调来接收数据.通过定义特定的setter函数来完成代理,该函数将接收的数据写入window.myAwesomeResponse
页面上下文中.您唯一需要做的就是检索此文本.
如果你知道前缀(用加载的JSON调用的函数,例如insert({"data":["Some", "JSON", "here"],"id":"asdasda")
),为JSONP编写代理就更容易了.您可以insert
在页面上下文中覆盖
页面加载后
casper.start(url).then(function(){
this.evaluate(function(){
var oldInsert = insert;
insert = function(json){
window.myAwesomeResponse = json;
oldInsert.apply(window, arguments);
};
});
}).waitFor(getAwesomeResponse, function then(){
var data = JSON.parse(getAwesomeResponse());
// Do something with data
}).run();
Run Code Online (Sandbox Code Playgroud)或者在收到请求之前(如果函数是在调用请求之前注册的)
casper.on("resource.requested", function(resource){
// filter on the correct call
if (resource.url.indexOf(".jsonp") != -1) {
this.evaluate(function(){
var oldInsert = insert;
insert = function(json){
window.myAwesomeResponse = json;
oldInsert.apply(window, arguments);
};
});
}
}).run();
casper.start(url).waitFor(getAwesomeResponse, function then(){
var data = JSON.parse(getAwesomeResponse());
// Do something with data
}).run();
Run Code Online (Sandbox Code Playgroud)我可能会迟到这个聚会,但答案可能会帮助像我这样的人,以后会遇到这个问题.
我不得不从PhantomJS开始,然后转移到CasperJS但最终与SlimerJS达成和解.Slimer基于Phantom,与Casper兼容,并且可以使用相同的onResponseReceived方法将响应主体发送回"response.body"部分.
参考:https://docs.slimerjs.org/current/api/webpage.html#webpage-onresourcereceived
归档时间: |
|
查看次数: |
12850 次 |
最近记录: |