API REST

# Enviar
curl -s -F files=@invoice.pdf -F outputTypes=json http://localhost:8080/parse
# {"jobs":[{"file":"invoice.pdf","jobId":"e08f769f-..."}]}

# Consultar
curl -s http://localhost:8080/jobs/e08f769f-...
# {"status":"successful","files":["e08f769f-.../invoice.json"],...}

# Descargar
curl -OJ http://localhost:8080/jobs/e08f769f-.../invoice.json

import pathlib, time

import requests

FP = "http://localhost:8080"

with open("invoice.pdf", "rb") as f:
    r = requests.post(f"{FP}/parse", files={"files": f}, data={"outputTypes": ["json"]})
r.raise_for_status()
job = r.json()["jobs"][0]["jobId"]

while (status := requests.get(f"{FP}/jobs/{job}").json())["status"] in ("pending", "in-progress"):
    time.sleep(3)
if status["status"] != "successful":
    raise RuntimeError(status["failure"])

for entry in status["files"]:
    r = requests.get(f"{FP}/jobs/{entry}")
    r.raise_for_status()
    pathlib.Path(pathlib.Path(entry).name).write_bytes(r.content)