Created
March 3, 2025 14:51
-
-
Save clbarnes/23f9a6840c991f3202ac883ff1c74bb3 to your computer and use it in GitHub Desktop.
XML to pydantic model/ JSON
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from __future__ import annotations | |
from xml.etree import ElementTree as ET | |
from pydantic import BaseModel, Field | |
class XmlElement(BaseModel): | |
tag: str = Field(alias="#") | |
attributes: dict[str, str] = Field(alias="@", default_factory=dict) | |
children: list[str | XmlElement] = Field(alias="c", default_factory=list) | |
@property | |
def value(self) -> str | None: | |
"""If the element has exactly 1 child, which is text, return that text. | |
Otherwise, return None. | |
""" | |
if len(self.children) == 1 and isinstance(self.children[0], str): | |
return self.children[0] | |
return None | |
def all_text(self) -> str: | |
j = [] | |
self._all_text(j) | |
return "".join(j) | |
def _all_text(self, to_join: list[str]): | |
for c in self.children: | |
if isinstance(c, str): | |
to_join.append(c) | |
else: | |
c._all_text(to_join) | |
@classmethod | |
def from_str(cls, s: str) -> Self: | |
return cls.from_etree(ET.fromstring(s)) | |
@classmethod | |
def from_etree(cls, et: ET.Element) -> Self: | |
model = cls.model_validate({"#": et.tag, "@": et.attrib, "c": []}) | |
if et.text: | |
model.children.append(et.text) | |
for child in et: | |
model.children.append(XmlElement.from_etree(child)) | |
if child.tail: | |
model.children.append(child.tail) | |
return model | |
def xml_to_json(s: str) -> str: | |
return XmlElement.from_str(s).model_dump_json(by_alias=True) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment