xml文件格式相关操作

[可扩展标记语言](https://baike.baidu.com/item/可扩展标记语言/2885849)，是一种简单的数据存储语言，XML 被设计用来传输和存储数据。

• 存储，可用来存放配置文件，例如：java的配置文件。
• 传输，网络传输时以这种格式存在，例如：早期ajax传输的数据、soap协议等。

<data>
    <country name="Liechtenstein">
        <rank updated="yes">2</rank>
        <year>2023</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
    <country name="Singapore">
        <rank updated="yes">5</rank>
        <year>2026</year>
        <gdppc>59900</gdppc>
        <neighbor direction="N" name="Malaysia" />
    </country>
    <country name="Panama">
        <rank updated="yes">69</rank>
        <year>2026</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>

注意：在Python开发中用的相对来比较少，大家作为了解即可（后期课程在讲解微信支付、微信公众号消息处理 时会用到基于xml传输数据）。

例如：https://developers.weixin.qq.com/doc/offiaccount/Message_Management/Receiving_standard_messages.html

• 读取文件和内容

from xml.etree import ElementTree as ET

# ET去打开xml文件
tree = ET.parse("files/xo.xml")

# 获取根标签
root = tree.getroot()

print(root) # <Element 'data' at 0x7f94e02763b0>

from xml.etree import ElementTree as ET

content = """
<data>
    <country name="Liechtenstein">
        <rank updated="yes">2</rank>
        <year>2023</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
     <country name="Panama">
        <rank updated="yes">69</rank>
        <year>2026</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>
"""

root = ET.XML(content)
print(root)  # <Element 'data' at 0x7fdaa019cea0>

• 读取节点数据

from xml.etree import ElementTree as ET

content = """
<data>
    <country name="Liechtenstein" id="999" >
        <rank>2</rank>
        <year>2023</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
     <country name="Panama">
        <rank>69</rank>
        <year>2026</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>
"""

# 获取根标签 data
root = ET.XML(content)

country_object = root.find("country")
print(country_object.tag, country_object.attrib)
gdppc_object = country_object.find("gdppc")
print(gdppc_object.tag,gdppc_object.attrib,gdppc_object.text)

from xml.etree import ElementTree as ET

content = """
<data>
    <country name="Liechtenstein">
        <rank>2</rank>
        <year>2023</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
     <country name="Panama">
        <rank>69</rank>
        <year>2026</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>
"""

# 获取根标签 data
root = ET.XML(content)

# 获取data标签的孩子标签
for child in root:
    # child.tag = conntry
    # child.attrib = {"name":"Liechtenstein"}
    print(child.tag, child.attrib)
    for node in child:
        print(node.tag, node.attrib, node.text)

from xml.etree import ElementTree as ET

content = """
<data>
    <country name="Liechtenstein">
        <rank>2</rank>
        <year>2023</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
     <country name="Panama">
        <rank>69</rank>
        <year>2026</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>
"""

root = ET.XML(content)

for child in root.iter('year'):
    print(child.tag, child.text)

from xml.etree import ElementTree as ET

content = """
<data>
    <country name="Liechtenstein">
        <rank>2</rank>
        <year>2023</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
     <country name="Panama">
        <rank>69</rank>
        <year>2026</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>
"""

root = ET.XML(content)
v1 = root.findall('country')
print(v1)

v2 = root.find('country').find('rank')
print(v2.text)

• 修改和删除节点

from xml.etree import ElementTree as ET

content = """
<data>
    <country name="Liechtenstein">
        <rank>2</rank>
        <year>2023</year>
        <gdppc>141100</gdppc>
        <neighbor direction="E" name="Austria" />
        <neighbor direction="W" name="Switzerland" />
    </country>
     <country name="Panama">
        <rank>69</rank>
        <year>2026</year>
        <gdppc>13600</gdppc>
        <neighbor direction="W" name="Costa Rica" />
        <neighbor direction="E" name="Colombia" />
    </country>
</data>
"""

root = ET.XML(content)

# 修改节点内容和属性
rank = root.find('country').find('rank')
print(rank.text)
rank.text = "999"
rank.set('update', '2020-11-11')
print(rank.text, rank.attrib)
############ 保存文件 ############
tree = ET.ElementTree(root)
tree.write("new.xml", encoding='utf-8')


# 删除节点
root.remove( root.find('country') )
print(root.findall('country'))

############ 保存文件 ############
tree = ET.ElementTree(root)
tree.write("newnew.xml", encoding='utf-8')

• 构建文档

<home>
    <son name="儿1">
        <grandson name="儿11"></grandson>
        <grandson name="儿12"></grandson>
    </son>
    <son name="儿2"></son>
</home>

from xml.etree import ElementTree as ET

# 创建根标签
root = ET.Element("home")

# 创建节点大儿子
son1 = ET.Element('son', {'name': '儿1'})
# 创建小儿子
son2 = ET.Element('son', {"name": '儿2'})

# 在大儿子中创建两个孙子
grandson1 = ET.Element('grandson', {'name': '儿11'})
grandson2 = ET.Element('grandson', {'name': '儿12'})
son1.append(grandson1)
son1.append(grandson2)

# 把儿子添加到根节点中
root.append(son1)
root.append(son2)

tree = ET.ElementTree(root)
tree.write('oooo.xml', encoding='utf-8', short_empty_elements=False)

<famliy>
    <son name="儿1">
        <grandson name="儿11"></grandson>
        <grandson name="儿12"></grandson>
    </son>
    <son name="儿2"></son>
</famliy>

from xml.etree import ElementTree as ET

# 创建根节点
root = ET.Element("famliy")


# 创建大儿子
son1 = root.makeelement('son', {'name': '儿1'})
# 创建小儿子
son2 = root.makeelement('son', {"name": '儿2'})

# 在大儿子中创建两个孙子
grandson1 = son1.makeelement('grandson', {'name': '儿11'})
grandson2 = son1.makeelement('grandson', {'name': '儿12'})

son1.append(grandson1)
son1.append(grandson2)


# 把儿子添加到根节点中
root.append(son1)
root.append(son2)

tree = ET.ElementTree(root)
tree.write('oooo.xml',encoding='utf-8')

<famliy>
    <son name="儿1">
        <age name="儿11">孙子</age>
    </son>
    <son name="儿2"></son>
</famliy>

from xml.etree import ElementTree as ET


# 创建根节点
root = ET.Element("famliy")


# 创建节点大儿子
son1 = ET.SubElement(root, "son", attrib={'name': '儿1'})
# 创建小儿子
son2 = ET.SubElement(root, "son", attrib={"name": "儿2"})

# 在大儿子中创建一个孙子
grandson1 = ET.SubElement(son1, "age", attrib={'name': '儿11'})
grandson1.text = '孙子'


et = ET.ElementTree(root)  #生成文档对象
et.write("test.xml", encoding="utf-8")

<user><![CDATA[你好呀]]</user>

from xml.etree import ElementTree as ET

# 创建根节点
root = ET.Element("user")
root.text = "<![CDATA[你好呀]]"

et = ET.ElementTree(root)  # 生成文档对象
et.write("test.xml", encoding="utf-8")

案例：

content = """<xml>
    <ToUserName><![CDATA[gh_7f083739789a]]></ToUserName>
    <FromUserName><![CDATA[oia2TjuEGTNoeX76QEjQNrcURxG8]]></FromUserName>
    <CreateTime>1395658920</CreateTime>
    <MsgType><![CDATA[event]]></MsgType>
    <Event><![CDATA[TEMPLATESENDJOBFINISH]]></Event>
    <MsgID>200163836</MsgID>
    <Status><![CDATA[success]]></Status>
</xml>"""

from xml.etree import ElementTree as ET

info = {}
root = ET.XML(content)
for node in root:
    # print(node.tag,node.text)
    info[node.tag] = node.text
print(info)

示例：

# ############### 2. 实现去网上获取指定地区的天气信息，并写入到Excel中。 #############

import os
import requests
from xml.etree import ElementTree as ET
from openpyxl import workbook


# 处理文件路径
base_dir = os.path.dirname(os.path.abspath(__file__))
target_excel_file_path = os.path.join(base_dir, 'weather.xlsx')

# 创建excel且默认会创建一个sheet（名称为Sheet）
wb = workbook.Workbook()
del wb['Sheet']

while True:
    # 用户输入城市，并获取该城市的天气信息
    city = input("请输入城市（Q/q退出）：")
    if city.upper() == "Q":
        break
    url = "http://ws.webxml.com.cn//WebServices/WeatherWebService.asmx/getWeatherbyCityName?theCityName={}".format(city)
    res = requests.get(url=url)

    # 1.提取XML格式中的数据
    root = ET.XML(res.text)

    # 2.为每个城市创建一个sheet，并将获取的xml格式中的数据写入到excel中。
    sheet = wb.create_sheet(city)



    for row_index, node in enumerate(root, 1):
        text = node.text
        cell = sheet.cell(row_index, 1)
        cell.value = text

wb.save(target_excel_file_path)