openparser-sdk 0.0.1__py3-none-any.whl

openparser/__init__.py

@@ -0,0 +1,54 @@
+"""Official Python SDK for the OpenParser API.
+
+Example
+-------
+
+    from openparser import OpenParserClient
+
+    client = OpenParserClient(api_key=os.environ["OPENPARSER_API_KEY"])
+
+    result = client.parse.sync(
+        {"ocr_model": "paddleocr-vl-1.6", "output_format": "openparser@1"},
+        file=Path("invoice.pdf"),
+    )
+
+    print(result.page_count)
+"""
+
+from openparser.client import OpenParserClient
+from openparser.errors import (
+    OpenParserAuthError,
+    OpenParserConflictError,
+    OpenParserError,
+    OpenParserForbiddenError,
+    OpenParserGatewayTimeoutError,
+    OpenParserLimitExceededError,
+    OpenParserNotFoundError,
+    OpenParserPaymentRequiredError,
+    OpenParserRateLimitError,
+    OpenParserServerError,
+    OpenParserServiceUnavailableError,
+    OpenParserTimeoutError,
+    OpenParserUnprocessableError,
+    OpenParserUnsupportedMediaError,
+    OpenParserValidationError,
+)
+
+__all__ = [
+    "OpenParserClient",
+    "OpenParserError",
+    "OpenParserAuthError",
+    "OpenParserForbiddenError",
+    "OpenParserNotFoundError",
+    "OpenParserValidationError",
+    "OpenParserPaymentRequiredError",
+    "OpenParserConflictError",
+    "OpenParserLimitExceededError",
+    "OpenParserUnsupportedMediaError",
+    "OpenParserUnprocessableError",
+    "OpenParserRateLimitError",
+    "OpenParserServiceUnavailableError",
+    "OpenParserGatewayTimeoutError",
+    "OpenParserServerError",
+    "OpenParserTimeoutError",
+]

openparser/_files.py

@@ -0,0 +1,43 @@
+"""File upload helpers for parse, extract, and file pool requests."""
+
+from __future__ import annotations
+
+import mimetypes
+from pathlib import Path
+from typing import IO, Any, Optional, Tuple
+
+
+def is_file_input(value: Any) -> bool:
+    if isinstance(value, Path):
+        return True
+    if isinstance(value, dict):
+        content = value.get("content")
+        filename = value.get("filename")
+        return isinstance(filename, str) and isinstance(content, (bytes, bytearray))
+    if hasattr(value, "read") and hasattr(value, "name"):
+        return True
+    return False
+
+
+def to_upload_tuple(value: Any) -> Tuple[str, bytes, str]:
+    if isinstance(value, Path):
+        content = value.read_bytes()
+        filename = value.name
+        mime_type, _ = mimetypes.guess_type(filename)
+        return (filename, content, mime_type or "application/octet-stream")
+
+    if isinstance(value, dict):
+        raw_content = value["content"]
+        content = bytes(raw_content) if isinstance(raw_content, bytearray) else raw_content
+        filename = value["filename"]
+        mime_type = value.get("mime_type") or value.get("mimeType")
+        if not mime_type:
+            mime_type, _ = mimetypes.guess_type(filename)
+        return (filename, content, mime_type or "application/octet-stream")
+
+    handle: IO[bytes] = value
+    content = handle.read()
+    name = getattr(handle, "name", None)
+    filename = Path(name).name if isinstance(name, str) else "file"
+    mime_type, _ = mimetypes.guess_type(filename)
+    return (filename, content, mime_type or "application/octet-stream")

openparser/_generated/__init__.py

@@ -0,0 +1,8 @@
+
+""" A client library for accessing OpenParser API """
+from .client import AuthenticatedClient, Client
+
+__all__ = (
+    "AuthenticatedClient",
+    "Client",
+)

openparser/_generated/api/__init__.py

@@ -0,0 +1 @@
+""" Contains methods for accessing the API """

openparser/_generated/api/extract/__init__.py

@@ -0,0 +1 @@
+""" Contains endpoint functions for accessing the API """

openparser/_generated/api/extract/extract_async.py

@@ -0,0 +1,280 @@
+from http import HTTPStatus
+from typing import Any, cast
+from urllib.parse import quote
+
+import httpx
+
+from ...client import AuthenticatedClient, Client
+from ...types import Response, UNSET
+from ... import errors
+
+from ...models.error_response import ErrorResponse
+from ...models.extract_async_body import ExtractAsyncBody
+from ...models.job_accepted import JobAccepted
+from typing import cast
+
+
+
+def _get_kwargs(
+    *,
+    body: ExtractAsyncBody,
+    idempotency_key: str,
+
+) -> dict[str, Any]:
+    headers: dict[str, Any] = {}
+    headers["Idempotency-Key"] = idempotency_key
+
+
+
+
+
+
+
+    _kwargs: dict[str, Any] = {
+        "method": "post",
+        "url": "/extract/async",
+    }
+
+    _kwargs["files"] = body.to_multipart()
+
+
+
+    _kwargs["headers"] = headers
+    return _kwargs
+
+
+
+def _parse_response(*, client: AuthenticatedClient | Client, response: httpx.Response) -> ErrorResponse | JobAccepted | None:
+    if response.status_code == 202:
+        response_202 = JobAccepted.from_dict(response.json())
+
+
+
+        return response_202
+
+    if response.status_code == 400:
+        response_400 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_400
+
+    if response.status_code == 401:
+        response_401 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_401
+
+    if response.status_code == 402:
+        response_402 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_402
+
+    if response.status_code == 403:
+        response_403 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_403
+
+    if response.status_code == 409:
+        response_409 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_409
+
+    if response.status_code == 413:
+        response_413 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_413
+
+    if response.status_code == 415:
+        response_415 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_415
+
+    if response.status_code == 422:
+        response_422 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_422
+
+    if response.status_code == 429:
+        response_429 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_429
+
+    if response.status_code == 503:
+        response_503 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_503
+
+    if client.raise_on_unexpected_status:
+        raise errors.UnexpectedStatus(response.status_code, response.content)
+    else:
+        return None
+
+
+def _build_response(*, client: AuthenticatedClient | Client, response: httpx.Response) -> Response[ErrorResponse | JobAccepted]:
+    return Response(
+        status_code=HTTPStatus(response.status_code),
+        content=response.content,
+        headers=response.headers,
+        parsed=_parse_response(client=client, response=response),
+    )
+
+
+def sync_detailed(
+    *,
+    client: AuthenticatedClient | Client,
+    body: ExtractAsyncBody,
+    idempotency_key: str,
+
+) -> Response[ErrorResponse | JobAccepted]:
+    """ Extract structured data asynchronously
+
+     Admit a durable single extract job from file bytes, `file_id`, or `parse_job_id` and
+    return immediately. Parse reuse does not run OCR or add a page charge; OpenRouter usage
+    remains billable.
+
+    Args:
+        idempotency_key (str):
+        body (ExtractAsyncBody):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[ErrorResponse | JobAccepted]
+     """
+
+
+    kwargs = _get_kwargs(
+        body=body,
+idempotency_key=idempotency_key,
+
+    )
+
+    response = client.get_httpx_client().request(
+        **kwargs,
+    )
+
+    return _build_response(client=client, response=response)
+
+def sync(
+    *,
+    client: AuthenticatedClient | Client,
+    body: ExtractAsyncBody,
+    idempotency_key: str,
+
+) -> ErrorResponse | JobAccepted | None:
+    """ Extract structured data asynchronously
+
+     Admit a durable single extract job from file bytes, `file_id`, or `parse_job_id` and
+    return immediately. Parse reuse does not run OCR or add a page charge; OpenRouter usage
+    remains billable.
+
+    Args:
+        idempotency_key (str):
+        body (ExtractAsyncBody):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        ErrorResponse | JobAccepted
+     """
+
+
+    return sync_detailed(
+        client=client,
+body=body,
+idempotency_key=idempotency_key,
+
+    ).parsed
+
+async def asyncio_detailed(
+    *,
+    client: AuthenticatedClient | Client,
+    body: ExtractAsyncBody,
+    idempotency_key: str,
+
+) -> Response[ErrorResponse | JobAccepted]:
+    """ Extract structured data asynchronously
+
+     Admit a durable single extract job from file bytes, `file_id`, or `parse_job_id` and
+    return immediately. Parse reuse does not run OCR or add a page charge; OpenRouter usage
+    remains billable.
+
+    Args:
+        idempotency_key (str):
+        body (ExtractAsyncBody):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[ErrorResponse | JobAccepted]
+     """
+
+
+    kwargs = _get_kwargs(
+        body=body,
+idempotency_key=idempotency_key,
+
+    )
+
+    response = await client.get_async_httpx_client().request(
+        **kwargs
+    )
+
+    return _build_response(client=client, response=response)
+
+async def asyncio(
+    *,
+    client: AuthenticatedClient | Client,
+    body: ExtractAsyncBody,
+    idempotency_key: str,
+
+) -> ErrorResponse | JobAccepted | None:
+    """ Extract structured data asynchronously
+
+     Admit a durable single extract job from file bytes, `file_id`, or `parse_job_id` and
+    return immediately. Parse reuse does not run OCR or add a page charge; OpenRouter usage
+    remains billable.
+
+    Args:
+        idempotency_key (str):
+        body (ExtractAsyncBody):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        ErrorResponse | JobAccepted
+     """
+
+
+    return (await asyncio_detailed(
+        client=client,
+body=body,
+idempotency_key=idempotency_key,
+
+    )).parsed

openparser/_generated/api/extract/extract_batch.py

@@ -0,0 +1,284 @@
+from http import HTTPStatus
+from typing import Any, cast
+from urllib.parse import quote
+
+import httpx
+
+from ...client import AuthenticatedClient, Client
+from ...types import Response, UNSET
+from ... import errors
+
+from ...models.batch_job_accepted import BatchJobAccepted
+from ...models.error_response import ErrorResponse
+from ...models.extract_batch_body import ExtractBatchBody
+from typing import cast
+
+
+
+def _get_kwargs(
+    *,
+    body: ExtractBatchBody,
+    idempotency_key: str,
+
+) -> dict[str, Any]:
+    headers: dict[str, Any] = {}
+    headers["Idempotency-Key"] = idempotency_key
+
+
+
+
+
+
+
+    _kwargs: dict[str, Any] = {
+        "method": "post",
+        "url": "/extract/batch",
+    }
+
+    _kwargs["files"] = body.to_multipart()
+
+
+
+    _kwargs["headers"] = headers
+    return _kwargs
+
+
+
+def _parse_response(*, client: AuthenticatedClient | Client, response: httpx.Response) -> BatchJobAccepted | ErrorResponse | None:
+    if response.status_code == 202:
+        response_202 = BatchJobAccepted.from_dict(response.json())
+
+
+
+        return response_202
+
+    if response.status_code == 400:
+        response_400 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_400
+
+    if response.status_code == 401:
+        response_401 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_401
+
+    if response.status_code == 402:
+        response_402 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_402
+
+    if response.status_code == 403:
+        response_403 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_403
+
+    if response.status_code == 409:
+        response_409 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_409
+
+    if response.status_code == 413:
+        response_413 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_413
+
+    if response.status_code == 415:
+        response_415 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_415
+
+    if response.status_code == 422:
+        response_422 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_422
+
+    if response.status_code == 429:
+        response_429 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_429
+
+    if response.status_code == 503:
+        response_503 = ErrorResponse.from_dict(response.json())
+
+
+
+        return response_503
+
+    if client.raise_on_unexpected_status:
+        raise errors.UnexpectedStatus(response.status_code, response.content)
+    else:
+        return None
+
+
+def _build_response(*, client: AuthenticatedClient | Client, response: httpx.Response) -> Response[BatchJobAccepted | ErrorResponse]:
+    return Response(
+        status_code=HTTPStatus(response.status_code),
+        content=response.content,
+        headers=response.headers,
+        parsed=_parse_response(client=client, response=response),
+    )
+
+
+def sync_detailed(
+    *,
+    client: AuthenticatedClient | Client,
+    body: ExtractBatchBody,
+    idempotency_key: str,
+
+) -> Response[BatchJobAccepted | ErrorResponse]:
+    """ Extract structured data from multiple documents
+
+     Admit up to 100 file-backed extract child jobs in one durable batch. Every item uses
+    `file_index` or `file_id`; `parse_job_id` reuse is single-extract-only and is not accepted
+    in batch. Partial child failures are preserved. Parent status derivation follows
+    `JobStatus`; billing is evaluated per child.
+
+    Args:
+        idempotency_key (str):
+        body (ExtractBatchBody):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[BatchJobAccepted | ErrorResponse]
+     """
+
+
+    kwargs = _get_kwargs(
+        body=body,
+idempotency_key=idempotency_key,
+
+    )
+
+    response = client.get_httpx_client().request(
+        **kwargs,
+    )
+
+    return _build_response(client=client, response=response)
+
+def sync(
+    *,
+    client: AuthenticatedClient | Client,
+    body: ExtractBatchBody,
+    idempotency_key: str,
+
+) -> BatchJobAccepted | ErrorResponse | None:
+    """ Extract structured data from multiple documents
+
+     Admit up to 100 file-backed extract child jobs in one durable batch. Every item uses
+    `file_index` or `file_id`; `parse_job_id` reuse is single-extract-only and is not accepted
+    in batch. Partial child failures are preserved. Parent status derivation follows
+    `JobStatus`; billing is evaluated per child.
+
+    Args:
+        idempotency_key (str):
+        body (ExtractBatchBody):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        BatchJobAccepted | ErrorResponse
+     """
+
+
+    return sync_detailed(
+        client=client,
+body=body,
+idempotency_key=idempotency_key,
+
+    ).parsed
+
+async def asyncio_detailed(
+    *,
+    client: AuthenticatedClient | Client,
+    body: ExtractBatchBody,
+    idempotency_key: str,
+
+) -> Response[BatchJobAccepted | ErrorResponse]:
+    """ Extract structured data from multiple documents
+
+     Admit up to 100 file-backed extract child jobs in one durable batch. Every item uses
+    `file_index` or `file_id`; `parse_job_id` reuse is single-extract-only and is not accepted
+    in batch. Partial child failures are preserved. Parent status derivation follows
+    `JobStatus`; billing is evaluated per child.
+
+    Args:
+        idempotency_key (str):
+        body (ExtractBatchBody):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[BatchJobAccepted | ErrorResponse]
+     """
+
+
+    kwargs = _get_kwargs(
+        body=body,
+idempotency_key=idempotency_key,
+
+    )
+
+    response = await client.get_async_httpx_client().request(
+        **kwargs
+    )
+
+    return _build_response(client=client, response=response)
+
+async def asyncio(
+    *,
+    client: AuthenticatedClient | Client,
+    body: ExtractBatchBody,
+    idempotency_key: str,
+
+) -> BatchJobAccepted | ErrorResponse | None:
+    """ Extract structured data from multiple documents
+
+     Admit up to 100 file-backed extract child jobs in one durable batch. Every item uses
+    `file_index` or `file_id`; `parse_job_id` reuse is single-extract-only and is not accepted
+    in batch. Partial child failures are preserved. Parent status derivation follows
+    `JobStatus`; billing is evaluated per child.
+
+    Args:
+        idempotency_key (str):
+        body (ExtractBatchBody):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        BatchJobAccepted | ErrorResponse
+     """
+
+
+    return (await asyncio_detailed(
+        client=client,
+body=body,
+idempotency_key=idempotency_key,
+
+    )).parsed