[英]convert a pdf having a table to xlsx/xls using nodejs
I am having a pdf that contain a table and having data. 我有一个包含表和数据的pdf。
I want to convert it to xlsx /xls , I have tried many way ie pdf to json and json to xlsx/xls but I am not getting the result has I want, i want the json data in key and value pair 我想将其转换为xlsx / xls ,我尝试了很多方法,例如将pdf转换为json ,将json转换为xlsx / xls,但是我没有得到想要的结果,我想要键和值对中的json数据
code 码
let fs = require('fs'),
PDFParser = require("pdf2json");
let pdfParser = new PDFParser();
pdfParser.on("pdfParser_dataError", errData => console.error(errData.parserError) );
pdfParser.on("pdfParser_dataReady", pdfData => {
fs.writeFile("./pdf2.json", JSON.stringify(pdfData),(error) => {
if(error)
{
console.log(error);
}
});
});
pdfParser.loadPDF("./Sample Data.pdf");
you can use pdf2table or pdfreader to read data from pdf file and shape that data to required format of json. 您可以使用pdf2table或pdfreader从pdf文件中读取数据并将该数据成形为所需的json格式。
Adding sample codes for reference 添加示例代码以供参考
//pdf2table // pdf2table
var pdf2table = require('pdf2table');
var fs = require('fs');
fs.readFile('./tests.pdf', function (err, buffer) {
if (err) return console.log(err);
pdf2table.parse(buffer, function (err, rows, rowsdebug) {
if(err) return console.log(err);
console.log(rows);
});
});
//pdfreader // pdf阅读器
var pdfreader = require('pdfreader');
var table = new pdfreader.TableParser();
new pdfreader.PdfReader().parseFileItems('tests.pdf', function(err, item){
if( err ) {
console.log( err )
} else {
console.log( item.text)
//create json as you want
}
});
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.