ParseJet SDK

The official ParseJet SDK for Node.js, Bun, and Deno. Extract text from URLs, PDFs, YouTube videos, web pages, and images with a single API.

Installation

# npm
npm install parsejet

# pnpm
pnpm add parsejet

# yarn
yarn add parsejet

# bun
bun add parsejet

Requirements: Node.js 18+ (uses native fetch).

Quick Start

import { ParseJet } from "parsejet";

const client = new ParseJet({ apiKey: "pj_YOUR_KEY" });

const result = await client.parse.url("https://example.com");
console.log(result.title);
console.log(result.text);

Authentication

Pass your API key directly or set it as an environment variable:

// Option 1: Pass directly
const client = new ParseJet({ apiKey: "pj_YOUR_KEY" });

// Option 2: Environment variable (PARSEJET_API_KEY)
const client = new ParseJet();

API Reference

All parse methods return a ParseResult:

type ParseResult = {
  text: string;
  title: string;
  source_type: string;
  metadata: Record<string, any>;
};

client.parse.url(url, options?)

Parse any URL. ParseJet auto-detects the content type (web page, PDF, YouTube, etc.).

const result = await client.parse.url("https://example.com/report.pdf");
console.log(result.text);
console.log(result.source_type); // "pdf", "webpage", "youtube", etc.

With markdown output:

const result = await client.parse.url("https://example.com/article", {
  outputFormat: "markdown",
});

client.parse.file(buffer, filename, options?)

Parse a file from a Buffer or Uint8Array.

import fs from "fs";

const buffer = fs.readFileSync("report.pdf");
const result = await client.parse.file(buffer, "report.pdf");
console.log(result.text);

client.parse.filePath(path, options?)

Parse a file directly from a local path.

const result = await client.parse.filePath("/path/to/report.pdf");
console.log(result.text);

client.parse.youtube(url, options?)

Extract a YouTube video transcript.

const result = await client.parse.youtube(
  "https://youtube.com/watch?v=dQw4w9WgXcQ",
  { language: "en" }
);
console.log(result.text);

client.parse.webpage(url, options?)

Parse a web page and extract its content.

const result = await client.parse.webpage("https://example.com/article");
console.log(result.title);
console.log(result.text);

client.parse.ocr(buffer, filename, options?)

Perform OCR on an image.

import fs from "fs";

const image = fs.readFileSync("screenshot.png");
const result = await client.parse.ocr(image, "screenshot.png");
console.log(result.text);

Options

ParseOptions

Available on all methods:

| Option | Type | Description | | -------------- | ------------------------ | ---------------------- | | outputFormat | "text" | "markdown" | Output format |

YouTubeOptions

Additional options for client.parse.youtube():

| Option | Type | Description | | ---------- | -------- | ---------------------------------- | | language | string | Preferred transcript language code |

Error Handling

The SDK throws ParseJetError for API errors, which includes the HTTP status code and the error body.

import { ParseJet, ParseJetError } from "parsejet";

const client = new ParseJet();

try {
  const result = await client.parse.url("https://example.com");
} catch (error) {
  if (error instanceof ParseJetError) {
    console.error(`API error ${error.status}: ${error.message}`);
    console.error(error.body);
  } else {
    throw error;
  }
}

Configuration

const client = new ParseJet({
  apiKey: "pj_YOUR_KEY",       // API key (or set PARSEJET_API_KEY env var)
  baseUrl: "https://api.parsejet.com", // Custom base URL (optional)
});

Environment Variables

| Variable | Description | | ------------------ | ------------- | | PARSEJET_API_KEY | Your API key |

License

MIT