@serguun42/pdf-parse NPM

@serguun42/pdf-parse

Installation

npm install @serguun42/pdf-parse

Basic Usage - Local Files

const fs = require("fs");
const PdfParse = require("@serguun42/pdf-parse");

let dataBuffer = fs.readFileSync("path/to/file.pdf");

PdfParse(dataBuffer).then((data) => {
	// number of pages
	console.log(data.numpages);
	// number of rendered pages
	console.log(data.numrender);
	// PDF info
	console.log(data.info);
	// PDF metadata
	console.log(data.metadata);
	// PDF.js version
	// check https://mozilla.github.io/pdf.js/getting_started/
	console.log(data.version);
	// PDF text
	console.log(data.text);
});

Basic Usage - HTTP

You can use crawler-request which uses the pdf-parse

Exception Handling

const fs = require("fs");
const PdfParse = require("@serguun42/pdf-parse");

const dataBuffer = fs.readFileSync("path/to/file.pdf");

PdfParse(dataBuffer)
	.then((data) => {
		// use data
	})
	.catch((error) => {
		// handle exceptions
	});

Extend

v1.0.9 and above break pagerender callback changelog
If you need another format like json, you can change page render behaviour with a callback
Check out https://mozilla.github.io/pdf.js/

// default render callback
function render_page(pageData) {
	//check documents https://mozilla.github.io/pdf.js/
	let render_options = {
		//replaces all occurrences of whitespace with standard spaces (0x20). The default value is `false`.
		normalizeWhitespace: false,
		//do not attempt to combine same line TextItem's. The default value is `false`.
		disableCombineTextItems: false
	};

	return pageData.getTextContent(render_options).then((textContent) => {
		let lastY,
			text = "";
		for (let item of textContent.items) {
			if (lastY == item.transform[5] || !lastY) {
				text += item.str;
			} else {
				text += "\n" + item.str;
			}
			lastY = item.transform[5];
		}
		return text;
	});
}

let options = {
	pagerender: render_page
};

const dataBuffer = fs.readFileSync("path/to/file.pdf");

PdfParse(dataBuffer, options).then((data) => {
	// use new format
});

Options

const DEFAULT_OPTIONS = {
	// internal page parser callback
	// you can set this option, if you need another format except raw text
	pagerender: render_page,

	// max page number to parse
	max: 0,
};