@ridi/pdf-parser NPM

@ridi/pdf-parser

Common PDF data parser for Ridibooks services

Features

Structure parsing
Read files
- Read cover page
Encrypt and decrypt function when parsing or reading
Debug mode
Environment
- Node
- CLI
- Browser
Online demo

Install

npm install @ridi/pdf-parser

Usage

Basic:

import { PdfParser } from '@ridi/pdf-parser';
// or const { PdfParser } = require('@ridi/pdf-parser');

const parser = new PdfParser('./foo/bar.pdf');
parser.parse().then((book) => {
  ...
});
parser.read().then((pdfFileBuffer) => {
  ...
});

with AesCryptor:

import { CryptoProvider, AesCryptor } from '@ridi/pdf-parser';
// or const { CryptoProvider, AesCryptor } = require('@ridi/pdf-parser');

const { Purpose } = CryptoProvider;
const { Mode, Padding } = AesCryptor;

class ContentCryptoProvider extends CryptoProvider {
  constructor(key) {
    super();
    this.cryptor = new AesCryptor(Mode.ECB, { key });
  }

  getCryptor(filePath, purpose) {
    return this.cryptor;
  }

  // If use as follows:
  // const provider = new ContentCryptoProvider(...);
  // const parser = new PdfParser('encrypted.pdf', provider);
  // const book = await parser.parse();
  // const cover = await parser.readItem(book.cover);
  //
  // It will be called as follows:
  // 1. run(data, 'encrypted.pdf', Purpose.READ_IN_DIR)
  // 2. run(data, 'encrypted.pdf', Purpose.READ_IN_DIR)
  //
  run(data, filePath, purpose) {
    const cryptor = this.getCryptor(filePath, purpose);
    if (purpose === Purpose.READ_IN_DIR) {
      return cryptor.decrypt(data, { padding: Padding.AUTO });
    }
    return data;
  }
}

const cryptoProvider = new ContentCryptoProvider(key);
const parser = new PdfParser('./foo/bar.pdf', cryptoProvider);

Log level setting:

import { LogLevel, ... } from '@ridi/pdf-parser';
const parser = new PdfParser(/* path */, /* cryptoProvider */, /* logLevel */)
// or const parser = new PdfParser(/* path */, /* logLevel */)
parser.logger.logLevel = LogLevel.VERBOSE; // SILENT, ERROR, WARN(default), INFO, DEBUG, VERBOSE

API

parse(parseOptions)

Returns Promise<PdfBook> with:

PdfBook: Instance with pages info.

Or throw exception.

parseOptions: `?object`

read()

Returns PDF file as Buffer.

onProgress = callback(step, totalStep, action)

Tells the progress of parser through callback.

const { Action } = PdfParser; // PARSE, READ_ITEMS
parser.onProgress = (step, totalStep, action) => {
  console.log(`[${action}] ${step} / ${totalStep}`);
}