How to Convert XML to JSON in Python: A Step‑by‑Step Guide

Original XML Overview

XML is a tree‑structured data format ideal for representing hierarchical information such as a company's organization, employee details, and project data.

Basic Rules for XML to JSON Conversion

After parsing XML with Python's xml.etree.ElementTree, each element is recursively transformed into a dictionary, ultimately producing a JSON object. The conversion follows these general rules:

✅ Example: XML snippet and its resulting JSON structure.

<?xml version="1.0" encoding="UTF-8"?>
<department id="D101" name="研发部">
    <manager id="EMP2001">张伟</manager>
    <employees>
        <employee id="EMP1001" role="高级开发工程师">
            <fullname>李娜</fullname>
            <skills>
                <skill level="expert">Python</skill>
            </skills>
        </employee>
    </employees>
</department>

{
    "department": {
        "@attributes": {
            "id": "D101",
            "name": "研发部"
        },
        "manager": {
            "@attributes": {"id": "EMP2001"},
            "text": "张伟"
        },
        "employees": {
            "employee": {
                "@attributes": {"id": "EMP1001", "role": "高级开发工程师"},
                "fullname": {"text": "李娜"},
                "skills": {
                    "skill": {
                        "@attributes": {"level": "expert"},
                        "text": "Python"
                    }
                }
            }
        }
    }
}

Key Points Explained

1. Root Element – Becomes the outermost JSON object that wraps all content.

2. Attributes – Converted to an @attributes object. Example:

"@attributes": {
    "id": "D101",
    "name": "研发部"
}

3. Text Content – Stored under a text key, e.g., "ABC科技有限公司" becomes: "name": {"text": "ABC科技有限公司"} 4. Repeated Tags – The first occurrence is an object; subsequent identical tags are automatically turned into an array.

"projects": {
    "project": [
        {"@attributes": {"status": "进行中"}, ...},
        {"@attributes": {"status": "已完成"}, ...}
    ]
}

5. CDATA Sections – Treated as ordinary text.

"description": {"text": "一个基于深度学习的对话式 AI 系统"}

6. Namespaces – Preserved in full form, e.g., {http://example.com/hr}id. They can be stripped beforehand if desired.

Code Implementation

The following Python script provides a Tkinter GUI that displays XML input on the left, JSON output on the right, highlights parsing errors, and includes utility buttons for conversion and clearing.

# xml_str_to_json_gui_final.py
import tkinter as tk
from tkinter import messagebox, ttk
import xml.etree.ElementTree as ET
import json

def xml_to_dict(element):
    """Recursively convert an XML element to a dictionary"""
    node = {}
    if element.attrib:
        node['@attributes'] = element.attrib
    if element.text and element.text.strip():
        node['text'] = element.text.strip()
    for child in element:
        child_data = xml_to_dict(child)
        if child.tag in node:
            if not isinstance(node[child.tag], list):
                node[child.tag] = [node[child.tag]]
            node[child.tag].append(child_data)
        else:
            node[child.tag] = child_data
    return node

def convert_xml_str_to_json(xml_str):
    try:
        root = ET.fromstring(xml_str)
        data = {root.tag: xml_to_dict(root)}
        return json.dumps(data, indent=4, ensure_ascii=False)
    except ET.ParseError as pe:
        return {'error': str(pe), 'exception': pe}
    except Exception as e:
        return {'error': f"转换失败: {e}"}

def on_convert():
    xml_input = xml_text.get("1.0", tk.END).strip()
    if not xml_input:
        messagebox.showwarning("警告", "请输入有效的 XML 内容")
        return
    result = convert_xml_str_to_json(xml_input)
    if isinstance(result, dict) and 'error' in result:
        error_msg = result['error']
        messagebox.showerror("解析错误", error_msg)
        if 'exception' in result and isinstance(result['exception'], ET.ParseError):
            exc = result['exception']
            line, column = exc.position
            try:
                start_index = f"1.0 + {line-1} lines + {column} chars"
                end_index = f"{start_index} + 1 chars"
                xml_text.tag_remove("error", "1.0", tk.END)
                xml_text.tag_add("error", start_index, end_index)
                xml_text.tag_config("error", background="yellow", foreground="red")
                xml_text.see(start_index)
            except tk.TclError:
                pass
        return
    else:
        xml_text.tag_remove("error", "1.0", tk.END)
        json_text.delete("1.0", tk.END)
        json_text.insert(tk.END, result)

def on_clear():
    xml_text.delete("1.0", tk.END)
    json_text.delete("1.0", tk.END)
    xml_text.tag_remove("error", "1.0", tk.END)

app = tk.Tk()
app.title("XML 转 JSON 工具 - 完整版")
app.geometry("1200x700")
style = ttk.Style()
style.configure("Convert.TButton", font=("微软雅黑", 12, "bold"), foreground="white", background="#2E7D32", padding=10, relief="flat")
style.map("Convert.TButton", background=[('active', '#1B5E20')], foreground=[('active', 'white')])

paned_window = tk.PanedWindow(app, orient=tk.HORIZONTAL, sashrelief=tk.SUNKEN)
paned_window.pack(fill="both", expand=True, padx=10, pady=10)

left_frame = ttk.Frame(paned_window)
tk.Label(left_frame, text="输入 XML 内容：", font=("微软雅黑", 12)).pack(anchor="w", padx=5, pady=5)
xml_text = tk.Text(left_frame, wrap="word", font=("Consolas", 12), undo=True)
xml_text.pack(fill="both", expand=True, padx=5, pady=5)
paned_window.add(left_frame, width=600)

right_frame = ttk.Frame(paned_window)
tk.Label(right_frame, text="JSON 输出内容：", font=("微软雅黑", 12)).pack(anchor="w", padx=5, pady=5)
json_text = tk.Text(right_frame, wrap="word", font=("Consolas", 12))
json_text.pack(fill="both", expand=True, padx=5, pady=5)
paned_window.add(right_frame, width=600)

btn_frame = ttk.Frame(app)
btn_frame.pack(pady=10)
convert_btn = ttk.Button(btn_frame, text="🔄 转换为 JSON", width=20, command=on_convert, style="Convert.TButton")
convert_btn.grid(row=0, column=0, padx=10)
clear_btn = ttk.Button(btn_frame, text="🧹 清空内容", width=15, command=on_clear)
clear_btn.grid(row=0, column=1, padx=10)

app.mainloop()

The GUI presents a side‑by‑side layout for clear input/output visualization, highlights errors directly in the XML editor, and includes additional features such as content clearing and automatic resizing.

Summary

This guide provides a comprehensive overview of XML structure, detailed conversion rules to JSON, explanations of handling attributes, text, repeated elements, CDATA, and namespaces, and supplies a ready‑to‑run Python/Tkinter application that demonstrates the entire conversion process.