How do I retrieve text from user selection in pdf.js?

问题

This question is specific to pdf.js, a javascript based pdf renderer. I'm building a custom version where I need to extract the text that I select inside the pdf.

There are other posts where you can fetch the text from one page or the whole pdf document such as the one here , but I'm looking to grab a specific text that the user selects and perhaps alert it or print it in the console.

回答1:

What you are looking for is window.getSelection() method. This method returns a specific Selection object with the range of the selected text on the web page.

Here is how you can use getSelection() together with pdf.js:

function getHightlightCoords() {
var pageIndex = PDFViewerApplication.pdfViewer.currentPageNumber - 1; 
var page = PDFViewerApplication.pdfViewer.getPageView(pageIndex);
var pageRect = page.canvas.getClientRects()[0];
var selectionRects = window.getSelection().getRangeAt(0).getClientRects();
var viewport = page.viewport;
var selected = selectionRects.map(function (r) {
  return viewport.convertToPdfPoint(r.left - pageRect.x, r.top - pageRect.y).concat(
     viewport.convertToPdfPoint(r.right - pageRect.x, r.bottom - pageRect.y)); 
});
return {page: pageIndex, coords: selected};
}


function showHighlight(selected) {
var pageIndex = selected.page; 
var page = PDFViewerApplication.pdfViewer.getPageView(pageIndex);
var pageElement = page.canvas.parentElement;
var viewport = page.viewport;
selected.coords.forEach(function (rect) {
  var bounds = viewport.convertToViewportRectangle(rect);
  var el = document.createElement('div');
  el.setAttribute('style', 'position: absolute; background-color: pink;' + 
    'left:' + Math.min(bounds[0], bounds[2]) + 'px; top:' + Math.min(bounds[1], bounds[3]) + 'px;' +
    'width:' + Math.abs(bounds[0] - bounds[2]) + 'px; height:' + Math.abs(bounds[1] - bounds[3]) + 'px;');
  pageElement.appendChild(el);
});
}

来源：https://stackoverflow.com/questions/48950038/how-do-i-retrieve-text-from-user-selection-in-pdf-js