Class HTMLDocumentBackend

docling/backend/html_backend.py:397–4555

class HTMLDocumentBackend(DeclarativeDocumentBackend):
    @override
    def __init__(
        self,
        in_doc: InputDocument,
        path_or_stream: Union[BytesIO, Path],
        options: Optional[HTMLBackendOptions] = None,
    ):
        if options is None:
            options = HTMLBackendOptions()
        super().__init__(in_doc, path_or_stream, options)
        self.options: HTMLBackendOptions
        self.soup: Optional[BeautifulSoup] = None
        self.path_or_stream: Union[BytesIO, Path] = path_or_stream
        self.base_path: Optional[str] = (
            str(options.source_uri) if options.source_uri is not None else None
        )
        self._image_loader = ImageResourceLoader(
            enable_local_fetch=options.enable_local_fetch,
            enable_remote_fetch=options.enable_remote_fetch,
            max_image_data_base64_bytes=options.max_image_data_base64_bytes,
            max_remote_image_bytes=options.max_remote_image_bytes,
            max_redirects=options.max_redirects,
            headers=options.headers,
        )

        # Initialize the parents for the hierarchy
        self.max_levels = 10
        self.level = 0
        self.parents: dict[int, Optional[Union[DocItem, GroupItem]]] = {}
        self.ctx = _Context()
        self._disable_inline_group_depth: int = 0
        for i in range(self.max_levels):
            self.parents[i] = None
        self.hyperlink: Union[AnyUrl, Path, None] = None
        self.format_tags: list[str] = []
        self._raw_html_bytes: Optional[bytes] = None
        self._rendered_html: Optional[str] = None
        self._rendered_bbox_by_id: dict[str, _RenderedBBox] = {}
        self._rendered_text_bbox_by_id: dict[str, _RenderedBBox] = {}
        self._rendered_page_images: list[Image.Image] = []
        self._rendered_page_size: Optional[Size] = None
        self._suppressed_tag_ids_stack: list[set[str]] = []
        self._suppressed_tag_obj_ids_stack: list[set[int]] = []
        self._form_fields_by_key_id_stack: list[dict[str, _ExtractedFormField]] = []
        self._tag_name_by_docling_id_cache: dict[str, str] = {}
        self._generated_html_id_counter: int = 0
        self._render_visibility_cache: dict[int, bool] = {}

        try:
            raw = (
                path_or_stream.getvalue()
                if isinstance(path_or_stream, BytesIO)
                else Path(path_or_stream).read_bytes()
            )
            self._raw_html_bytes = raw
            self.soup = BeautifulSoup(raw, "html.parser")
        except Exception as e: