Extracting text from a defined position in Adobe Acrobat DC using Javascript

hi,
Try this script and let me know if it suits to you:

function DumpBookmark(bkm, nLevel)
{
    var s = "";
    for (var i = 0; i < nLevel; i++) s += " ";
	//
	bkm.execute();
	var p=this.pageNum;
	var pageName="";
	var numWords=this.getPageNumWords(p);
	for (var i=0; i<numWords; i++) {
		var ckWord=this.getPageNthWord(p, i, false);
		var q=this.getPageNthWordQuads(p, i);
		m=(new Matrix2D).fromRotated(this,p);
		mInv=m.invert();
		r=mInv.transform(q);
		r=r.toString();
		r=r.split(",");
		if (Number(r[0])>300 && Number(r[1])<35) pageName+=ckWord;
	}
    if (bkm.name!="Root" && pageName!="") console.println(s + "+-" + bkm.name.replace(/\s$/,"")+" -> page: "+pageName.replace(/\s$/,""));
	// console.println(s + "+-" + bkm.name);
	//
    if (bkm.children != null)
        for (var i = 0; i < bkm.children.length; i++)
            DumpBookmark(bkm.children[i], nLevel + 1);
}
console.clear(); console.show();
console.println("Dumping all bookmarks in the document.");
DumpBookmark(this.bookmarkRoot, 0);

@bebarthThankyou for the script!

However I decided to go another route and use NodeJS for this task. Since running a script on a 2000+ page document inside Adobe Debugging console (this is the only way I know, there are probably other ways too) was a bit too much and time consuming, I decided to make an actual NodeJS script to do this task.

I am posting the logic below for anyone who wants to use or for anyone requiring logic to perform this on their own programming language of choice.

Two node packages were required for

// Project dependencies from package.json
"dependencies": {
    "pdf.js-extract": "^0.2.0",
    "pdfjs-dist": "^2.16.105"
}

The task was divided in two parts.

1. Extract outline and the corresponding PDF Document Page Number and save it in JSON for later use.

app.js

const pdfjsLib = require("pdfjs-dist/legacy/build/pdf.js");
const fs = require("fs");
const url = "Path to the PDF";
const LoadDocument = pdfjsLib.getDocument(url);

let docOutline = []; // Empty array to store document outline

/**
 * Get PDF outline and call `getToc` with initial indent of 0
 */

const getOutline = async () => {
  const pdf = await LoadDocument.promise;
  const bookmarks = await pdf.getOutline();
  await getToC(pdf, bookmarks, "");
  fs.writeFileSync("PDFOutline.json", JSON.stringify(docOutline));
};

/**
 *
 * @param {PDFDocumentProxy} pdf - PDFDocumentProxy returned when LoadDocument Resolves
 * @param {Object[]} bookmarks - Array returned when `getOutline()` method of `PDFDocumentProxy` Resolves
 * @param {String} indent - Amount of indentation to be applied to Bookmark Title, used when being recursively called
 */
const getToC = async (pdf, bookmarks, indent) => {
  //for..of loop for synchronous processing of each bookmark item in an array
  for await (const bookmark of bookmarks) {
    // For Each Bookmark item, get its page index (page 1 will be have an index of 0)
    const dest = await pdf.getDestination(bookmark.dest);
    const pageNumIndex = await pdf.getPageIndex(dest[0]);
    // Adding the title, page number and level of indent
    docOutline = [
      ...docOutline,
      {
        title: indent + bookmark.title,
        pageNumber: pageNumIndex + 1,
        level: indent.length / 2,
      },
    ];
    if (bookmark.items) {
      await getToC(pdf, bookmark.items, indent + "  ");
    }
  }
};
getOutline();

2. Extract Displayed Page Number on each PDF Document Page associated with the bookmarks from the previously saved JSON and save the result in yet another JSON for later use

extractOutline.js

const fs = require("fs");
const PDFExtract = require("pdf.js-extract").PDFExtract;
const data = require("./PDFOutline.json");
const url = "Path to the PDF";
var options = {};
var tocLine = "";
tableOfContents = [];
var prevPageNum; // Page number to be assigned to this variable at the end of each loop iteration for comparison
var prevDispPage; // Display Page number to be assigned to this variable at the end of each loop iteration for comparison

const pdfExtract = new PDFExtract();

const extractOutline = async () => {
  for await (bookmark of data) {
    const pageNumber = bookmark.pageNumber;
    options = {
      firstPage: pageNumber,
      lastPage: pageNumber,
      password: null,
      verbosity: -1,
      normalizeWhitespace: false,
      disableCombineTextItems: false,
    };
    if (pageNumber === prevPageNum) {
      tocLine = bookmark.title.padEnd(60, ".") + prevDispPage.padStart(6, ".");
      console.log(tocLine);
      tableOfContents = [
        ...tableOfContents,
        {
          title: bookmark.title,
          pdfPageNum: bookmark.pageNumber,
          displayPage: prevDispPage,
          indent: bookmark.level,
        },
      ];
    } else {
      const pdfData = await pdfExtract.extract(url, options);
      for await (page of pdfData.pages) {
        for await (content of page.content) {
          // Change Extraction Criteria based on requirements.
          // Needs trial and error to figure out the exact conditions
          // For Display Page Number Extraction,
          // User may benefit from running this alogorithm on a single page
          // and apply text-matching comparison in the condition below
          // then note the position of the text
          if (content.x > 590 && content.y > 500 && content.height == 6.96) {
            tocLine =
              bookmark.title.padEnd(60, ".") + content.str.padStart(6, ".");
            console.log(tocLine);
            tableOfContents = [
              ...tableOfContents,
              {
                title: bookmark.title,
                pdfPageNum: bookmark.pageNumber,
                displayPage: content.str,
                indent: bookmark.level,
              },
            ];
            prevDispPage = content.str;
            prevPageNum = bookmark.pageNumber;
          }
        }
      }
    }
  }
};

const execute = async () => {
  await extractOutline();
  fs.writeFileSync(
    "TableOfContentWithLevel.json",
    JSON.stringify(tableOfContents)
  );
};

execute();

Here is the part of console logging I got:

Since the whole thing is now saved in JSON, it can easily be used in any way required.

Thanks for the reply. The method getPageNthWordQuads only returns the boundary coordinates. I used getPageNth word to find the displayed page number and then used the getPageNthWordQuads to get the bounding box. Since the Nth word for displayed page number differs for each page, I am hopeful that the bounding box will remain same.

However, I still am not sure how to extract the text from the bounding box