Getting the source HTML of the current page from chrome extension

Inject a script into the page you want to get the source from and message it back to the popup....

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)
});

Here is my solution:

chrome.runtime.onMessage.addListener(function(request, sender) {
        if (request.action == "getSource") {
            this.pageSource = request.source;
            var title = this.pageSource.match(/<title[^>]*>([^<]+)<\/title>/)[1];
            alert(title)
        }
    });

    chrome.tabs.query({ active: true, currentWindow: true }, tabs => {
        chrome.tabs.executeScript(
            tabs[0].id,
            { code: 'var s = document.documentElement.outerHTML; chrome.runtime.sendMessage({action: "getSource", source: s});' }
        );
    });

Getting the source HTML of the current page from chrome extension

Related

Recent Posts