PPTX Loader

PPTX Loader

PowerPointLoader

Bases: UnstructuredLoader

从PPT文档中读取数据

Attributes:

Name	Type	Description
mime_types	set[Literal[PPT, PPTX]]	支持的mime类型 默认值为 {PPT, PPTX}
extract_images	bool	是否提取图片（默认: False）
extract_image_block_output_dir	Optional[str]	图片输出目录（默认: None，表示使用 base64 模式）

load

load(
    path_or_uri: str,
    *,
    file: bytes | IO[bytes] | None = None,
    content_type: Optional[str] = None,
    extract_images: Optional[bool] = None,
    **kwargs: Any
) -> Document

从给定的 URI 或文件对象加载文档并返回 Document 对象 / Load document from the given URI or file object and return Document.

Parameters:

Name	Type	Description	Default
path_or_uri	str	文档的路径或 URI （必填）/ File path or uri (required)	required
file	bytes | IO[bytes] | None	文件内容，可以是 bytes 或 IO[bytes] 对象（与 path_or_uri 参数二选一）/ File content as bytes or IO[bytes] (mutually exclusive with path_or_uri).	None
content_type	Optional[str]	文档的内容类型（MIME 类型），如果不提供则尝试自动检测 / The content type (MIME type), auto-detected if not provided.	None
extract_images	Optional[bool]	是否提取文档中的图片（覆盖类属性配置）/ Whether to extract images from the document (overrides class attribute). Default is None (use class attribute).	None
**kwargs	Any	其他可选参数，传递给底层的分片函数 / Additional keyword arguments passed to the partition function.	{}

Returns:

Name	Type	Description
Document	Document	返回一个包含文档内容的 Document 对象 / The loaded document.

Raises:

Type	Description
ValueError	如果 path_or_uri 和 file 都未提供，或都提供了 / If neither or both path_or_uri and file are provided.

Source code in tfrobot/utils/document_loaders/pptx.py

def load(
    self,
    path_or_uri: str,
    *,
    file: bytes | IO[bytes] | None = None,
    content_type: Optional[str] = None,
    extract_images: Optional[bool] = None,
    **kwargs: Any,
) -> Document:
    """
    从给定的 URI 或文件对象加载文档并返回 Document 对象 / Load document from the given URI or file object and return Document.

    Args:
        path_or_uri: 文档的路径或 URI （必填）/ File path or uri (required)
        file: 文件内容，可以是 bytes 或 IO[bytes] 对象（与 path_or_uri 参数二选一）/ File content as bytes or IO[bytes] (mutually exclusive with path_or_uri).
        content_type: 文档的内容类型（MIME 类型），如果不提供则尝试自动检测 / The content type (MIME type), auto-detected if not provided.
        extract_images: 是否提取文档中的图片（覆盖类属性配置）/ Whether to extract images from the document (overrides class attribute). Default is None (use class attribute).
        **kwargs: 其他可选参数，传递给底层的分片函数 / Additional keyword arguments passed to the partition function.

    Returns:
        Document: 返回一个包含文档内容的 Document 对象 / The loaded document.

    Raises:
        ValueError: 如果 path_or_uri 和 file 都未提供，或都提供了 / If neither or both path_or_uri and file are provided.
    """
    uri = convert_to_file_url(path_or_uri)
    # 处理文件对象 / Handle file object
    file_obj = BytesIO(file) if isinstance(file, bytes) else file if file is not None else self.get_file_obj(uri)
    unique_element_ids = kwargs.pop("unique_element_ids", True)  # 是否使用唯一元素ID
    filename = kwargs.pop(
        "filename", get_filename_from_uri(uri)
    )  # 因为TFRobot partition封装均是使用IO流进行解析，如果再传入filename UnstructuredIO会报错。
    kwargs.pop("url", None)  # 因为TFRobot partition封装均是使用IO流进行解析，如果再传入url UnstructuredIO会报错。

    if not unique_element_ids:
        raise ValueError("TFRobot必须启用唯一元素ID以确保正确处理文档。")

    # 确定是否启用图片提取（参数覆盖类属性）
    should_extract = extract_images if extract_images is not None else self.extract_images

    # 注册图片分区器（如果需要提取图片）
    if should_extract:
        from unstructured.partition.pptx import register_picture_partitioner

        from tfrobot.utils.document_loaders.pptx_image_extractor import TFRobotPPTXPicturePartitioner

        # 配置分区器行为
        TFRobotPPTXPicturePartitioner.configure(output_dir=self.extract_image_block_output_dir, filename=filename)
        register_picture_partitioner(TFRobotPPTXPicturePartitioner)

    try:
        if content_type == "application/vnd.ms-powerpoint":
            from unstructured.partition.ppt import partition_ppt

            els = partition_ppt(file=file_obj, unique_element_ids=unique_element_ids)
            f_type = TFFileType.from_mime_type(content_type)
        elif content_type == "application/vnd.openxmlformats-officedocument.presentationml.presentation":
            from unstructured.partition.pptx import partition_pptx

            els = partition_pptx(file=file_obj, unique_element_ids=unique_element_ids)
            f_type = TFFileType.from_mime_type(content_type)
        else:
            from unstructured.file_utils.filetype import detect_filetype

            if not (ft := detect_filetype(file=file_obj, metadata_file_path=filename)):
                raise ValueError("无法识别文件类型")
            else:
                f_type = TFFileType.from_mime_type(ft.mime_type)
            if f_type not in self.mime_types:
                raise ValueError(f"不支持的文件类型：{f_type}")
            from unstructured.partition.auto import partition

            els = partition(file=file_obj, unique_element_ids=unique_element_ids)
        if f_type is None:
            raise ValueError("未正确识别文件类型")
        # 排除空值
        all_els = [
            create_element_by_unstructured_element(e, filename=filename)
            for e in els
            if e and e.id and str(e).strip()
        ]

        # 判断是否有chunk_size要求，如果有的话，按要求进行chuck调整
        if self.min_chunk_size or self.max_chunk_size:
            all_els = self._adjust_chunk_size(all_els)
        return Document.from_elements(
            all_els, file_uri=AnyUrl(uri), file_type=f_type, hash_strategy=DefaultHashStrategy()
        )
    finally:
        # 清理图片分区器配置（如果启用了图片提取）
        if should_extract:
            from unstructured.partition.pptx import PptxPartitionerOptions

            from tfrobot.utils.document_loaders.pptx_image_extractor import TFRobotPPTXPicturePartitioner

            TFRobotPPTXPicturePartitioner.reset()
            PptxPartitionerOptions._PicturePartitionerCls = None