PDF 파서

# Parse a PDF and get text + metadata
curl -X POST https://api.parsejet.com/v1/parse/auto/file \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "[email protected]"

# Response:
# {
#   "text": "Invoice #1234\nDate: 2026-03-15\n...",
#   "title": "Invoice #1234",
#   "source_type": "pdf",
#   "metadata": { "pages": 2, "author": "Acme Corp" }
# }

import httpx

# Before (pdf-parse / pdfplumber):
#   import pdfplumber
#   with pdfplumber.open("invoice.pdf") as pdf:
#       text = "\n".join(p.extract_text() for p in pdf.pages)

# After (ParseJet — no dependencies):
resp = httpx.post(
    "https://api.parsejet.com/v1/parse/auto/file",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    files={"file": open("invoice.pdf", "rb")},
)
result = resp.json()
text = result["text"]          # All text, all pages
title = result["title"]        # Document title
pages = result["metadata"]["pages"]  # Page count

// Before (pdf-parse):
//   const pdfParse = require("pdf-parse");
//   const data = await pdfParse(buffer);

// After (ParseJet — no native dependencies):
const formData = new FormData();
formData.append("file", pdfBuffer, "invoice.pdf");

const res = await fetch("https://api.parsejet.com/v1/parse/auto/file", {
  method: "POST",
  headers: { Authorization: "Bearer YOUR_API_KEY" },
  body: formData,
});
const { text, title, source_type, metadata } = await res.json();
// Works in Node.js, Deno, Bun, Cloudflare Workers — anywhere with fetch