ByteScout Cloud API Server – Document Parser API – JavaScript – Parse From Url (Node.js)

On-demand (REST Web API) version:
 Web API (on-demand version)

On-premise offline SDK for Windows:
 60 Day Free Trial (on-premise)

MultiPageTable-template1.yml

      
---
# Template that demonstrates parsing of multi-page table using only 
# regular expressions for the table start, end, and rows.
# If regular expression cannot be written for every table row (for example, 
# if the table contains empty cells), try the second method demonstrated 
# in `MultiPageTable-template2.yml` template.
templateVersion: 3
templatePriority: 0
sourceId: Multipage Table Test
detectionRules:
  keywords:
  - Sample document with multi-page table
fields:
  total:
    type: regex
    expression: TOTAL {{DECIMAL}}
    dataType: decimal
tables:
- name: table1
  start:
    # regular expression to find the table start in document
    expression: Item\s+Description\s+Price\s+Qty\s+Extended Price
  end:
    # regular expression to find the table end in document
    expression: TOTAL\s+\d+\.\d\d
  row:
    # regular expression to find table rows
    expression: '^\s*(?<itemNo>\d+)\s+(?<description>.+?)\s+(?<price>\d+\.\d\d)\s+(?<qty>\d+)\s+(?<extPrice>\d+\.\d\d)'
  columns: 
  - name: itemNo
    type: integer
  - name: description
    type: string
  - name: price
    type: decimal
  - name: qty
    type: integer
  - name: extPrice
    type: decimal
  multipage: true
    

app.js

      
/*jshint esversion: 6 */

// Please NOTE: In this sample we're assuming Cloud Api Server is hosted at "https://localhost". 
// If it's not then please replace this with with your hosting url.

var https = require("https");
var fs = require("fs");

// `request` module is required for file upload.
// Use "npm install request" command to install.
var request = require("request");

// Source PDF file
const SourceFileUrl = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/document-parser/MultiPageTable.pdf";

// Destination PDF file name
const DestinationFile = "./result.json";

// Template text. Use Document Parser SDK (https://bytescout.com/products/developer/documentparsersdk/index.html)
// to create templates.
// Read template from file:
var templateText = fs.readFileSync("./MultiPageTable-template1.yml", "utf-8");

// URL for `Document Parser` API call
var query = `https://localhost/pdf/documentparser`;
var jsonRequestObject = {
    url: SourceFileUrl,
    template: templateText
};

request(
    {
        url: query,
        method: "POST",
        json: true,
        body: jsonRequestObject
    },
    function (error, response, body) {

        if (error) {
            return console.error("Error: ", error);
        }

        // Parse JSON response
        let data = JSON.parse(JSON.stringify(body));

        if (data.error == false) {
            //Download generated file
            var file = fs.createWriteStream(DestinationFile);
            https.get(data.url, (response2) => {
                response2.pipe(file)
                    .on("close", () => {
                        console.log(`Generated result file saved as "${DestinationFile}" file.`);
                    });
            });
        }
        else {
            // Service reported error
            console.log("Error: " + data.message);
        }
    }
);
    

package.json

      
{
  "name": "test",
  "version": "1.0.0",
  "description": "PDF.co",
  "main": "app.js",
  "scripts": {
  },
  "keywords": [
    "pdf.co",
    "web",
    "api",
    "bytescout",
    "api"
  ],
  "author": "ByteScout & PDF.co",
  "license": "ISC",
  "dependencies": {
    "request": "^2.88.2"
  }
}

    

ON-PREMISE OFFLINE SDK

Get 60 Day Free Trial

See also:

• Explore Documentation
• Explore Source Code Samples
• Watch Video Course

ON-DEMAND REST WEB API

Get Your API Key

See also:

• Web API Docs
• Learn About Security
• Explore Source Code Samples