Method _parse_nodes

pandas/io/xml.py:197–281

Parse xml nodes. This method will parse the children and attributes of elements in ``xpath``, conditionally for only elements, only attributes or both while optionally renaming node names. Raises ------ ValueError * If only eleme

(self, elems: list[Any])

        raise AbstractMethodError(self)

    def _parse_nodes(self, elems: list[Any]) -> list[dict[str, str | None]]:
        """
        Parse xml nodes.

        This method will parse the children and attributes of elements
        in ``xpath``, conditionally for only elements, only attributes
        or both while optionally renaming node names.

        Raises
        ------
        ValueError
            * If only elements and only attributes are specified.

        Notes
        -----
        Namespace URIs will be removed from return node values. Also,
        elements with missing children or attributes compared to siblings
        will have optional keys filled with None values.
        """

        dicts: list[dict[str, str | None]]

        if self.elems_only and self.attrs_only:
            raise ValueError("Either element or attributes can be parsed not both.")
        if self.elems_only:
            if self.names:
                dicts = [
                    {
                        **(
                            {el.tag: el.text}
                            if el.text and not el.text.isspace()
                            else {}
                        ),
                        **{
                            nm: ch.text if ch.text else None
                            for nm, ch in zip(self.names, el.findall("*"), strict=True)
                        },
                    }
                    for el in elems
                ]
            else:
                dicts = [
                    {ch.tag: ch.text if ch.text else None for ch in el.findall("*")}
                    for el in elems
                ]

        elif self.attrs_only:
            dicts = [
                {k: v if v else None for k, v in el.attrib.items()} for el in elems
            ]

        elif self.names:
            dicts = [
                {
                    **el.attrib,
                    **({el.tag: el.text} if el.text and not el.text.isspace() else {}),
                    **{
                        nm: ch.text if ch.text else None