Parse From Url (Node.js) - JavaScript
Document Parser sample in JavaScript demonstrating ‘Parse From Url (Node.js)’
MultiPageTable-template1.yml
templateName: Multipage Table Test
templateVersion: 4
templatePriority: 0
detectionRules:
keywords:
- Sample document with multi-page table
objects:
- name: total
objectType: field
fieldProperties:
fieldType: macros
expression: TOTAL{{Spaces}}({{Number}})
regex: true
dataType: decimal
- name: table1
objectType: table
tableProperties:
start:
expression: Item{{Spaces}}Description{{Spaces}}Price
regex: true
end:
expression: TOTAL{{Spaces}}{{Number}}
regex: true
row:
expression: '{{LineStart}}{{Spaces}}(?<itemNo>{{Digits}}){{Spaces}}(?<description>{{SentenceWithSingleSpaces}}){{Spaces}}(?<price>{{Number}}){{Spaces}}(?<qty>{{Digits}}){{Spaces}}(?<extPrice>{{Number}})'
regex: true
columns:
- name: itemNo
dataType: integer
- name: description
dataType: string
- name: price
dataType: decimal
- name: qty
dataType: integer
- name: extPrice
dataType: decimal
multipage: true
app.js
/*jshint esversion: 6 */
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");
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
const API_KEY = "***********************************";
// Source PDF file
// You can also upload your own file into PDF.co and use it as url. Check "Upload File" samples for code snippets: https://github.com/bytescout/pdf-co-api-samples/tree/master/File%20Upload/
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 (https://pdf.co/document-parser, https://app.pdf.co/document-parser)
// 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://api.pdf.co/v1/pdf/documentparser`;
var jsonRequestObject = {
url: SourceFileUrl,
template: templateText
};
request(
{
url: query,
headers: { "x-api-key": API_KEY },
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);
}
}
);
PDF.co Web API: the Web API with a set of tools for documents manipulation, data conversion, data extraction, splitting and merging of documents. Includes image recognition, built-in OCR, barcode generation and barcode decoders to decode bar codes from scans, pictures and pdf.
Download Source Code (.zip)
return to the previous page explore Document Parser endpoint
Copyright © 2016 - 2023 PDF.co