PythonでPDFをMarkdown（マークダウン）に変換

# pip install requests
import requests, time

API = "https://pdf2md.dev/api/v2"
H = {"Authorization": "Bearer p2m_your_key"}

# 1) create a job from a PDF URL
r = requests.post(f"{API}/jobs", headers={**H, "Idempotency-Key": "report-2026-01"},
                  json={"url": "https://example.com/report.pdf"})
r.raise_for_status()
jid = r.json()["job_id"]

# 2) poll until ready or error
while True:
    job = requests.get(f"{API}/jobs/{jid}", headers=H).json()
    if job["status"] in ("ready", "error"):
        break
    time.sleep(3)

if job["status"] == "error":
    raise SystemExit(f"conversion failed: {job.get('error_code')} {job.get('error_message')}")

# 3) download the Markdown
md = requests.get(f"{API}/jobs/{jid}/download", headers=H).text
if job.get("truncated"):
    print("note: partial result (hit the time budget)")
open("report.md", "w").write(md)

多数のPDFを変換する場合は、ファイルごとに1つのジョブを作成し、スロット上限まで並列に状態を確認します。無料プランは3スロットで、有料プランでは増加します。再試行で処理が重複しないよう、ファイルごとに異なるIdempotency-Keyを使い、429ではRetry-Afterヘッダーに従って待機してください。

// Node 18+ (global fetch)
const API = "https://pdf2md.dev/api/v2";
const H = { Authorization: "Bearer p2m_your_key" };

let r = await fetch(`${API}/jobs`, { method: "POST",
  headers: { ...H, "Content-Type": "application/json" },
  body: JSON.stringify({ url: "https://example.com/report.pdf" }) });
let { job_id } = await r.json();

let job;
do { await new Promise(s => setTimeout(s, 3000));
     job = await (await fetch(`${API}/jobs/${job_id}`, { headers: H })).json();
} while (!["ready", "error"].includes(job.status));

const md = await (await fetch(`${API}/jobs/${job_id}/download`, { headers: H })).text();