python模块之xml

xml是实现不同语言或程序之间进行数据交换的协议，跟json差不多，但json使用起来更简单，不过，古时候，在json还没诞生的黑暗年代，
大家只能选择用xml呀，至今很多传统公司如金融行业的很多系统的接口还主要是xml。

# test.xml
<?xml version="1.0"?>
<data>
    <country name="Liechtenstein">
        <rank updated="yes">2</rank>
        <year>2008</year>
        <gdppc>141100</gdppc>
        <neighbor name="Austria" direction="E"/>
        <neighbor name="Switzerland" direction="W"/>
    </country>
    <country name="Singapore">
        <rank updated="yes">5</rank>
        <year>2011</year>
        <gdppc>59900</gdppc>
        <neighbor name="Malaysia" direction="N"/>
    </country>
    <country name="Panama">
        <rank updated="yes">69</rank>
        <year>2011</year>
        <gdppc>13600</gdppc>
        <neighbor name="Costa Rica" direction="W"/>
        <neighbor name="Colombia" direction="E"/>
    </country>
</data>

xml数据

xml文件

 

# import xml.etree.ElementTree as ET

# 在进行操作之前，都应该进行下面两步：
# tree = ET.parse("test.xml")   # 形成树形结构
# root = tree.getroot()   # 得到树的根系

# print(root)   # <Element 'data' at 0x000002043F6B5868>

# 循环打印
# for i in root:
#     print(i)    # <Element 'country' at 0x00000261CF835958>   # <Element 'country' at 0x00000261CFB33D68>  # <Element 'country' at 0x00000261CFB33EF8>

# 所有的增删改查都是基于这个root根系去操作

# 查
# 1. 全文搜索year将所有的year标签全部找到
# print(root.iter("year"))   # <_elementtree._element_iterator object at 0x00000133E8B6EBA0>
# print([i for i in root.iter("year")])   # [<Element 'year' at 0x000001E227DB0548>, <Element 'year' at 0x000001E227DC4E08>, <Element 'year' at 0x000001E227DC4F98>]

# 2. 只找第一个，找到就返回
# print(root.find("country"))   # <Element 'country' at 0x00000228C9BF5958>

# 3. 子啊root的子节点里找，找所有的
# print(root.findall("country"))   # [<Element 'country' at 0x00000179E6BD5958>, <Element 'country' at 0x00000179E6ED3DB8>, <Element 'country' at 0x00000179E6ED3F48>]

# 练习
# 1. 找所有的rank标签，以及attrib和text
# print([i.attrib for i in root.iter("rank")])   # [{'updated': 'yes'}, {'updated': 'yes'}, {'updated': 'yes'}]
# print([i.text for i in root.iter("rank")])    # ['2', '5', '69']

# 2. 找到第二个country的neighor标签以及它的属性
# print([tag for tag in root.findall("country")][1].find("neighbor").attrib)   # {'name': 'Malaysia', 'direction': 'N'}


# 增 append

# import xml.etree.ElementTree as ET
# tree = ET.parse("test.xml")
# root = tree.getroot()
#
# # 给year所有大于2010年的标签下面添加一个month标签，属性为name:month  内容为30days
# for country in root.findall("country"):
#     for year in country.findall("year"):
#         if int(year.text) > 2010:
#             month = ET.Element("month")
#             month.text = "30days"
#             month.attrib = {"name": "month"}
#             country.append(month)
# tree.write("test.xml")


# 改
# import xml.etree.ElementTree as ET
# tree = ET.parse("test.xml")   # 形成属性结构
# root = tree.getroot()    # 得到树的根系
#
# # 对所有的year属性以及值进行修改
# for node in root.iter("year"):
#     new_year = int(node.text) + 1   # year+1
#     node.text = str(new_year)
#     # node.set("updated", "yes")
#     # node.set("version", "1.0")
# tree.write("test.xml")


# 删
# import xml.etree.ElementTree as ET
# tree = ET.parse("test.xml")    # 形成属性结构
# root = tree.getroot()   # 得到树的根系
#
# # 将rank值大于50的country标签删除
# for country in root.findall("country"):
#     rank = int(country.find("rank").text)
#     if rank > 50:
#         root.remove(country)
# tree.write("test1.xml")   # 将更改后的内容写到test1.xml中

# 创建xml文档
import xml.etree.ElementTree as ET
new_xml = ET.Element("namelist")
name = ET.SubElement(new_xml, "name", attrib={"enrolled": "yes"})
age = ET.SubElement(name, "age", attrib={"checked": "no"})
sex = ET.SubElement(name, "sex")
sex.text = "33"
name2 = ET.SubElement(new_xml, "name", attrib={"enrolled": "no"})
age2 = ET.SubElement(name2, "age")
age2.text = "19"

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

ET.dump(new_xml)   # 打印生成的格式