How can I get selected text in pdf in Javascript?

I’m writing a Chrome Extention to manipulate pdf file so I want to get selected text in the pdf. How can I do that.

Some thing like that:

Answer

You can use the internal undocumented commands of the built-in PDF viewer.

Here’s an example of a content script:

function getPdfSelectedText() {
  return new Promise(resolve => {
    window.addEventListener('message', function onMessage(e) {
      if (e.origin === 'chrome-extension://mhjfbmdgcfjbbpaeojofohoefgiehjai' &&
          e.data && e.data.type === 'getSelectedTextReply') {
        window.removeEventListener('message', onMessage);
        resolve(e.data.selectedText);
      }
    });
    // runs code in page context to access postMessage of the embedded plugin
    const script = document.createElement('script');
    if (chrome.runtime.getManifest().manifest_version > 2) {
      script.src = chrome.runtime.getURL('query-pdf.js');
    } else {
      script.textContent = `(${() => {
        document.querySelector('embed').postMessage({type: 'getSelectedText'}, '*');
      }})()`;
    }
    document.documentElement.appendChild(script);
    script.remove();
  });
}

chrome.runtime.onMessage.addListener((msg, sender, sendResponse) => {
  if (msg === 'getPdfSelection') {
    getPdfSelectedText().then(sendResponse);
    return true;
  }
});

This example assumes you send a message from the popup or background script:

chrome.tabs.query({active: true, currentWindow: true}, ([tab]) => {
  chrome.tabs.sendMessage(tab.id, 'getPdfSelection', sel => {
    // do something
  });
});

See also How to open the correct devtools console to see output from an extension script?

ManifestV3 extensions also need this:

• manifest.json should expose query-pdf.js

    "web_accessible_resources": [{
      "resources": ["query-pdf.js"],
      "matches": ["<all_urls>"],
      "use_dynamic_url": true
    }]
  

• query-pdf.js

  document.querySelector('embed').postMessage({type: 'getSelectedText'}, '*')