从chrome扩展获取当前页面的源HTML

时间:2012-07-27 08:48:59

标签: html google-chrome-extension

我有一个chrome扩展程序。我需要从当前页面的HTML源代码进行分析。我在这里找到了各种带有背景页面和内容脚本的解决方案,但没有人帮助我。这是我到目前为止: 的manifest.json:

{
  "name": "Extension",
  "version": "1.0",
  "description": "Extension",
  "browser_action": {
    "default_icon": "bmarkred.ico",
    "popup": "Test.html"
  },
  "content_scripts": [
    {
      "matches": ["http://*/*"],
      "js": ["content.js"]
    }
  ],
  "background": {
    "page": "backgroundPage.html"
  },
  "permissions": [
    "cookies",
    "tabs",
    "http://*/*", 
    "https://*/*"
  ]
}

background.html:

<html>
<head>
<script type="text/javascript">
    try {
        chrome.tabs.getSelected(null, function (tab) {
            chrome.tabs.sendRequest(tab.id, {action: "getSource"}, function(source) {
                alert(source);
            });
        });
    }
    catch (ex) {
        alert(ex);
    }
</script>
</head>
</html>

content.js:

chrome.extension.onRequest.addListener(function(request, sender, callback) {
    if (request.action == "getSource") {
        callback(document.getElementsByTagName('html')[0].innerHTML);
    }
});

警报始终警告未定义。即使我将content.js文件中的回调函数更改为:

callback('hello'); 

仍然是相同的结果。我究竟做错了什么?也许我正以错误的方式前进。我真的需要的是这个。当用户打开扩展弹出窗口时(仅此时),我需要当前页面的HTML,以便我可以分析它。有什么建议?

2 个答案:

答案 0 :(得分:132)

将脚本注入您想要获取源代码的页面,并将其发送回弹出窗口....

manifest.json

{
  "name": "Get pages source",
  "version": "1.0",
  "manifest_version": 2,
  "description": "Get pages source from a popup",
  "browser_action": {
    "default_icon": "icon.png",
    "default_popup": "popup.html"
  },
  "permissions": ["tabs", "<all_urls>"]
}

popup.html

<!DOCTYPE html>
<html style=''>
<head>
<script src='popup.js'></script>
</head>
<body style="width:400px;">
<div id='message'>Injecting Script....</div>
</body>
</html>

popup.js

chrome.runtime.onMessage.addListener(function(request, sender) {
  if (request.action == "getSource") {
    message.innerText = request.source;
  }
});

function onWindowLoad() {

  var message = document.querySelector('#message');

  chrome.tabs.executeScript(null, {
    file: "getPagesSource.js"
  }, function() {
    // If you try and inject into an extensions page or the webstore/NTP you'll get an error
    if (chrome.runtime.lastError) {
      message.innerText = 'There was an error injecting script : \n' + chrome.runtime.lastError.message;
    }
  });

}

window.onload = onWindowLoad;

getPagesSource.js

// @author Rob W <http://stackoverflow.com/users/938089/rob-w>
// Demo: var serialized_html = DOMtoString(document);

function DOMtoString(document_root) {
    var html = '',
        node = document_root.firstChild;
    while (node) {
        switch (node.nodeType) {
        case Node.ELEMENT_NODE:
            html += node.outerHTML;
            break;
        case Node.TEXT_NODE:
            html += node.nodeValue;
            break;
        case Node.CDATA_SECTION_NODE:
            html += '<![CDATA[' + node.nodeValue + ']]>';
            break;
        case Node.COMMENT_NODE:
            html += '<!--' + node.nodeValue + '-->';
            break;
        case Node.DOCUMENT_TYPE_NODE:
            // (X)HTML documents are identified by public identifiers
            html += "<!DOCTYPE " + node.name + (node.publicId ? ' PUBLIC "' + node.publicId + '"' : '') + (!node.publicId && node.systemId ? ' SYSTEM' : '') + (node.systemId ? ' "' + node.systemId + '"' : '') + '>\n';
            break;
        }
        node = node.nextSibling;
    }
    return html;
}

chrome.runtime.sendMessage({
    action: "getSource",
    source: DOMtoString(document)
});

答案 1 :(得分:0)

这是我的解决方案:

?-delMidNumber([1,3,2,4,5],L).
L = [1, 3, 4, 5]

?-delMidNumber([1,3,4,5],L).
List has even length