Extract data

schema = client.schemas.create(
    name="Product Catalog",
    columns=[
        {"key": "product_name", "label": "Product Name", "type": "text", "required": True},
        {"key": "price", "label": "Price", "type": "number"},
        {"key": "description", "label": "Description", "type": "text"},
        {"key": "seo_title", "label": "SEO title", "type": "text"},
        {"key": "description_de", "label": "German description", "type": "text"},
        {"key": "image_url", "label": "Image", "type": "image"},
    ],
)

print(schema["id"])

uploaded = client.files.upload("/path/to/catalog.pdf")

print(uploaded["id"])  # "4be9e43c-f03a-4309-938c-d2e9482752cf"

table = client.tables.create(
    schema_id=schema["id"],
    name="Q1 Product Catalog",
    file_ids=[uploaded["id"]],
)

print(table["id"])      # "d2b3dbe0-c77d-40d8-a5d2-480722489c64"
print(table["status"])  # "queued_for_processing"

import time

completed = None
for _ in range(100):
    current = client.tables.get(table["id"])
    if current["status"] == "completed":
        completed = current
        break
    if current["status"] in ("error", "cancelled"):
        raise RuntimeError(current.get("error_message") or f"Extraction {current['status']}")
    time.sleep(3)

if completed is None:
    raise TimeoutError("Timed out waiting for extraction")

print(completed["status"])      # "completed"
print(completed["total_rows"])  # 42

rows = client.tables.rows(completed["id"], limit=100)

for row in rows["data"]:
    print(row["data"]["product_name"], row["data"]["price"])

# Or as a pandas DataFrame
df = client.tables.results_as_dataframe(completed["id"])
print(df.head())