Method _parse_metadata

pelican/readers.py:213–253

Return the dict containing document metadata

(self, document, source_path)

            self._language_code = "en"

    def _parse_metadata(self, document, source_path):
        """Return the dict containing document metadata"""
        formatted_fields = self.settings["FORMATTED_FIELDS"]

        output = {}

        if document.first_child_matching_class(docutils.nodes.title) is None:
            logger.warning(
                "Document title missing in file %s: "
                "Ensure exactly one top level section",
                source_path,
            )

        try:
            # docutils 0.18.1+
            nodes = document.findall(docutils.nodes.docinfo)
        except AttributeError:
            # docutils 0.18.0 or before
            nodes = document.traverse(docutils.nodes.docinfo)

        for docinfo in nodes:
            for element in docinfo.children:
                if element.tagname == "field":  # custom fields (e.g. summary)
                    name_elem, body_elem = element.children
                    name = name_elem.astext()
                    if name.lower() in formatted_fields:
                        value = render_node_to_html(
                            document, body_elem, self.field_body_translator_class
                        )
                    else:
                        value = body_elem.astext()
                elif element.tagname == "authors":  # author list
                    name = element.tagname
                    value = [element.astext() for element in element.children]
                else:  # standard fields (e.g. address)
                    name = element.tagname
                    value = element.astext()
                name = name.lower()

                output[name] = self.process_metadata(name, value)
        return output

    def _get_publisher(self, source_path):
        extra_params = {