PDF OCR — 扫描PDF文字识别

# Scanned pages are detected and OCR'd automatically
curl -X POST "https://api.parsejet.com/v1/parse/auto/file?output_format=markdown" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "[email protected]"

# Non-Latin scripts: add a language hint (ko, ru, ar, hi, th, el ...)
curl -X POST "https://api.parsejet.com/v1/parse/auto/file?language=ru" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "[email protected]"

# Response metadata tells you which pages were recognized:
# "metadata": { "ocr_pages": [1, 2, 3], ... }

import httpx

resp = httpx.post(
    "https://api.parsejet.com/v1/parse/auto/file",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    files={"file": open("scan.pdf", "rb")},
    params={"output_format": "markdown"},
    timeout=120,
)
data = resp.json()
print(data["text"])
print("OCR'd pages:", data["metadata"].get("ocr_pages", []))

const formData = new FormData();
formData.append("file", pdfFile);

const res = await fetch(
  "https://api.parsejet.com/v1/parse/auto/file?output_format=markdown",
  { method: "POST", headers: { Authorization: "Bearer YOUR_API_KEY" }, body: formData },
);
const { text, metadata } = await res.json();
console.log(text);
console.log("OCR'd pages:", metadata.ocr_pages ?? []);