使用 elementtree 解析 XML 文档，忽略具有特定属性值的节点

在使用 elementtree 解析 XML 文档时，有时需要忽略具有特定属性值的节点。例如，在给定的 XML 文档中，我们需要忽略具有属性 name="Liechtenstein" 和 month="08" 的节点，并解析其余部分。

XML 文档示例：

<data>
    <country name="Liechtenstein">
        <rank updated="yes">2</rank>
        <language>english</language>
        <currency>1.21$/kg</currency>
        <gdppc month="06">141100</gdppc>
        <gdpnp month="10">2.304e+0150</gdpnp>
        <neighbor name="Austria" direction="E"/>
        <neighbor name="Switzerland" direction="W"/>
    </country>
    <country name="Singapore">
        <rank updated="yes">5</rank>
        <language>english</language>
        <currency>4.1$/kg</currency>
        <gdppc month="05">59900</gdppc>
        <gdpnp month="08">5.2e-015</gdpnp>
        <neighbor name="Malaysia" direction="N"/>
    </country>
    <country name="Lahore">
        <rank updated="yes">8</rank>
        <language>Pertr</language>
        <currency>7.3$/kg</currency>
        <gdppc month="010">34000</gdppc>
        <gdpnp month="099">3.4e+015</gdpnp>
        <neighbor name="Peru" direction="N"/>
    </country>
</data>

2、解决方案 有两种方法可以实现忽略特定属性值的节点的解析：

(1) 使用 xml.etree.ElementTree 模块

import xml.etree.ElementTree as PARSER

def parse_xml_ignore_nodes(xml_data, name_attribute, month_attribute):
    result = []

    root = PARSER.fromstring(xml_data)
    for country in root.getiterator("country"):
        if name_attribute in country.attrib and country.attrib[name_attribute] == "Liechtenstein":
            continue

        tmp = []
        for child in country.getchildren():
            if month_attribute in child.attrib and child.attrib[month_attribute] == "08":
                continue

            if child.text:
                tmp.append(child.text)

        result.append(tmp)

    return result

xml_data = """
<data>
    <country name="Liechtenstein">
        <rank updated="yes">2</rank>
        <language>english</language>
        <currency>1.21$/kg</currency>
        <gdppc month="06">141100</gdppc>
        <gdpnp month="10">2.304e+0150</gdpnp>
        <neighbor name="Austria" direction="E"/>
        <neighbor name="Switzerland" direction="W"/>
    </country>
    <country name="Singapore">
        <rank updated="yes">5</rank>
        <language>english</language>
        <currency>4.1$/kg</currency>
        <gdppc month="05">59900</gdppc>
        <gdpnp month="08">5.2e-015</gdpnp>
        <neighbor name="Malaysia" direction="N"/>
    </country>
    <country name="Lahore">
        <rank updated="yes">8</rank>
        <language>Pertr</language>
        <currency>7.3$/kg</currency>
        <gdppc month="010">34000</gdppc>
        <gdpnp month="099">3.4e+015</gdpnp>
        <neighbor name="Peru" direction="N"/>
    </country>
</data>
"""

result = parse_xml_ignore_nodes(xml_data, "name", "month")
print(result)

输出结果：

[['5', 'english', '4.1$/kg', '59900'], ['8', 'Pertr', '7.3$/kg', '34000', '3.4e+015']]

(2) 使用 lxml 模块

import lxml.html as PARSER

def parse_xml_ignore_nodes_lxml(xml_data, name_attribute, month_attribute):
    result = []

    root = PARSER.fromstring(xml_data)
    for country in root.xpath(f"//country[@{name_attribute}!='Liechtenstein']"):
        tmp = []
        for child in country.getchildren():
            if month_attribute in child.attrib and child.attrib[month_attribute] == "08":
                continue

            if child.text:
                tmp.append(child.text)

        result.append(tmp)

    return result

xml_data = """
<data>
    <country name="Liechtenstein">
        <rank updated="yes">2</rank>
        <language>english</language>
        <currency>1.21$/kg</currency>
        <gdppc month="06">141100</gdppc>
        <gdpnp month="10">2.304e+0150</gdpnp>
        <neighbor name="Austria" direction="E"/>
        <neighbor name="Switzerland" direction="W"/>
    </country>
    <country name="Singapore">
        <rank updated="yes">5</rank>
        <language>english</language>
        <currency>4.1$/kg</currency>
        <gdppc month="05">59900</gdppc>
        <gdpnp month="08">5.2e-015</gdpnp>
        <neighbor name="Malaysia" direction="N"/>
    </country>
    <country name="Lahore">
        <rank updated="yes">8</rank>
        <language>Pertr</language>
        <currency>7.3$/kg</currency>
        <gdppc month="010">34000</gdppc>
        <gdpnp month="099">3.4e+015</gdpnp>
        <neighbor name="Peru" direction="N"/>
    </country>
</data>
"""

result = parse_xml_ignore_nodes_lxml(xml_data, "name", "month")
print(result)

输出结果：

[['5', 'english', '4.1$/kg', '59900'], ['8', 'Pertr', '7.3$/kg', '34000', '3.4e+015']]

希望这些代码对你有帮助！