I’m using the pdf.js library to extract text from PDF files, but the extracted text isn’t formatted correctly, with some lines ending up at the end. The PDF file usually contains a resume, and since different resumes can have varying layouts and word structures, how can I segment the parsed text into different sections like introduction, education, and experience?

here is my code for parsing the pdf into text format

import React, { useState, useRef } from "react";
import * as pdfjs from "pdfjs-dist";
import { WorkerMessageHandler } from "pdfjs-dist/build/pdf.worker.min.mjs";



function PDFParser() {
  const [extractedText, setExtractedText] = useState("");
  const [pdfSrc, setPdfSrc] = useState(null);
  const [selectedFileName, setSelectedFileName] = useState("");
  const fileInputRef = useRef(null);

  const handleFileChange = async (event) => {
    const selectedFile = event.target.files[0];
  
    if (!selectedFile) {
      return;
    }
  
    const fileReader = new FileReader();
    fileReader.onload = async () => {
      const arrayBuffer = fileReader.result;
  
      try {
        pdfjs.GlobalWorkerOptions.workerSrc = "pdf.worker.min.mjs";
        const pdf = await pdfjs.getDocument({ data: arrayBuffer }).promise;
  
        const numPages = pdf.numPages;
        let extractedText = "";
  
        for (let i = 1; i <= numPages; i++) {
          const page = await pdf.getPage(i);
          const pageText = await page.getTextContent();
          
          // Map over text items and join them with a newline character
          const pageLines = pageText.items.map((item) => item.str).join("n");
  
          // Append the lines from this page to the extracted text
          if (extractedText !== "") {
            extractedText += "n";
          }
          extractedText += pageLines;
        }
  
        setExtractedText(extractedText);
        setPdfSrc(URL.createObjectURL(selectedFile));
        setSelectedFileName(selectedFile.name);
      } catch (error) {
        console.error("Error parsing PDF:", error);
        
      }
    };
  
    setExtractedText("");
    fileReader.readAsArrayBuffer(selectedFile);
  };
    return (
       <div>
        <input
          type="file"
          onChange={handleFileChange}
          accept=".pdf"
          ref={fileInputRef}
          style={{ display: "none" }}
        />
        <button className="UploadButton" onClick={openFileDialog}>
          Upload PDF
        </button>
      <div className="ScrollableContainer">
            {extractedText && (
             
              <HTMLContent text={extractedText}/>
              
            )}
          </div>
          </div>

 );
}

i have tried to convert it into html but pdfjs-dist does not allow to correctly convert it into htmL

so can someone suggest what other ways by which i can parse the text or suggest some library that help me do it