從 PDF 擷取文字

# Extract text from a local PDF file
curl -X POST https://api.parsejet.com/v1/parse/auto/file \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "[email protected]"

# Extract text from a PDF URL
curl -X POST https://api.parsejet.com/v1/parse/auto/url \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com/report.pdf"}'

import httpx

# Extract text from a local PDF
with open("contract.pdf", "rb") as f:
    resp = httpx.post(
        "https://api.parsejet.com/v1/parse/auto/file",
        headers={"Authorization": "Bearer YOUR_API_KEY"},
        files={"file": ("contract.pdf", f, "application/pdf")},
    )
data = resp.json()
print(data["text"])      # Extracted text
print(data["title"])     # Document title
print(data["metadata"])  # Page count, author, etc.

// Extract text from a PDF URL
const res = await fetch("https://api.parsejet.com/v1/parse/auto/url", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ url: "https://example.com/report.pdf" }),
});
const { text, title, metadata } = await res.json();