使用坐标数组将 PDF 文本解析为 CSV

Question

我有一个如下输入文件，其中包含数字化 OCR 文本

https://drive.google.com/drive/folders/1mAzjcHKX1tsKhNvTtF8InhkXFZbmdbKz?usp=sharing

此 PDF 包含从第 3 页开始的人员详细信息

预期输出基于特定位置 我正在尝试使用 PDF 位置区域数组来完成，因为所有页面在相同区域都有文本

预期的输出数组是 “1”，“1YO6963656”，“ववनितासुनीलभोईर'，”तीचेनाव。 सुनील भोईर","घर क्रमांक", "32 लिंग:महिला" ... ...

我尝试过

<script src="https://cdnjs.cloudflare.com/ajax/libs/pdf.js/2.12.313/pdf.min.js" integrity="sha512-qa1o08MA0596eSNsnkRv5vuGloSKUhY09O31MY2OJpODjUVlaL0GOJJcyt7J7Z61FiEgHMgBkH04ZJ+vcuLs/w==" crossorigin="anonymous" referrerpolicy="no-referrer"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/pdf.js/2.12.313/pdf.worker.min.js" integrity="sha512-S9Dwzi4TCjPQkxlaXsqQLj2gXUjPZk4HBzE7zWU6Itc1r2RNmlBrVLH4EsYQrdnzLgvkN8P7l9SCru+2I4rZwg==" crossorigin="anonymous" referrerpolicy="no-referrer"></script>
<label for="myfile">Select a file:</label>
<input type="file" id="file" name="file">



<script>
/*Offical release of the pdfjs worker*/
pdfjsLib.GlobalWorkerOptions.workerSrc = 'https://cdnjs.cloudflare.com/ajax/libs/pdf.js/2.5.207/pdf.worker.js';

document.getElementById('file').onchange = function(event) {
  separator = ' '
  var file = event.target.files[0];
  var fileReader = new FileReader();
  fileReader.onload = function() {
    var typedarray = new Uint8Array(this.result);
    console.log(typedarray);

    let pdf = pdfjsLib.getDocument(typedarray);
    return pdf.promise.then(function(pdf) { // get all pages text
        let maxPages = pdf._pdfInfo.numPages;
        let countPromises = []; // collecting all page promises
        for (let i = 1; i <= maxPages; i++) {
            let page = pdf.getPage(i);
            countPromises.push(page.then(function(page) { // add page promise
                let textContent = page.getTextContent();
                return textContent.then(function(text) { // return content promise
                    return text.items.map(function(obj) {
                        return obj.str;
                    }).join(separator); // value page text
                });
            }));
        };

        return Promise.all(countPromises).then(function(texts) {
            for(let i = 0; i < texts.length; i++){
                texts[i] = texts[i].replace(/\s+/g, ' ').trim();
            };
            console.log(texts)
            alert(texts)
            return texts;
        });
    });
  }
  fileReader.readAsArrayBuffer(file);
}

</script>