PDF zu TXT Dateikonverter

# Convert a single PDF to .txt
curl -X POST https://api.parsejet.com/v1/parse/auto/file \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "[email protected]" \
  | jq -r '.text' > output.txt

import httpx
from pathlib import Path

# Batch-convert all PDFs in a folder to .txt files
pdf_dir = Path("pdfs/")
txt_dir = Path("txt_output/")
txt_dir.mkdir(exist_ok=True)

for pdf_file in pdf_dir.glob("*.pdf"):
    resp = httpx.post(
        "https://api.parsejet.com/v1/parse/auto/file",
        headers={"Authorization": "Bearer YOUR_API_KEY"},
        files={"file": (pdf_file.name, pdf_file.read_bytes(), "application/pdf")},
    )
    txt_path = txt_dir / pdf_file.with_suffix(".txt").name
    txt_path.write_text(resp.json()["text"], encoding="utf-8")
    print(f"Saved {txt_path}")

import { readdir, readFile, writeFile } from "fs/promises";
import { join, basename } from "path";

// Batch-convert all PDFs in a folder to .txt files
const pdfDir = "./pdfs";
const outDir = "./txt_output";

for (const file of await readdir(pdfDir)) {
  if (!file.endsWith(".pdf")) continue;
  const formData = new FormData();
  formData.append("file", new Blob([await readFile(join(pdfDir, file))]));

  const res = await fetch("https://api.parsejet.com/v1/parse/auto/file", {
    method: "POST",
    headers: { Authorization: "Bearer YOUR_API_KEY" },
    body: formData,
  });
  const { text } = await res.json();
  await writeFile(join(outDir, basename(file, ".pdf") + ".txt"), text);
}