xml解析

xml文檔

<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>

code

from xml.etree.ElementTree import parse
with open('demo.xml', 'r') as f:
    et = parse(f)
    print(et)
    root = et.getroot()
    print(root, root.tag, root.attrib, root.text.strip())

    # 查找root下面的子元素证薇，注意孫子元素是無(wú)法找到的
    print(root.findall('country'))   # list -> [<Element 'country' at 0x0071E120>, <Element 'country' at 0x0071E270>, <Element 'country' at 0x0071E360>]
    print(root.iterfind('country'))  # <generator object prepare_child.<locals>.select at 0x00707D20>

    print('*' * 80)

    for child in root:
        print(child, child.get('name'))

    print('*'*80)

    for child in root.iter():
        print(child)  # 打印所有的元素結(jié)點(diǎn)

    # * : 找到元素的子結(jié)點(diǎn)
    # . : 當(dāng)前的路徑
    # // ：找到任意層次下的子元素
    # .. ：找到它的父對(duì)象
    # [@attrib="value"]：找到屬性值attrib為"value"的元素  <country name="Liechtenstein">
    # [tag]
    # [tag = 'text']：找到標(biāo)簽tag的值為text的元素
    # position：root.findall('country[1]')

    print(root.findall('country/*'))
    print(root.findall('.//rank/..'))  # 在當(dāng)前結(jié)點(diǎn)下（root），找到其下面任意層的子元素（rank）匆篓，的父元素（country）浑度，所以打印的是country元素，并且是一個(gè)list
    print(root.findall('country[@name="Singapore"]'))
    print(root.findall('country[rank]'))

    print('*' * 80)

    # position
    # [<Element 'country' at 0x00A6E150>, <Element 'country' at 0x00A6E2A0>, <Element 'country' at 0x00A6E390>]
    print(root.findall('country[1]'))  # 找到第1個(gè)country元素
    print(root.findall('country[2]'))   # 找到第2個(gè)country元素
    print(root.findall('country[last()]'))  # 找到最后一個(gè)country元素
    print(root.findall('country[last()-1]'))    # 找到倒數(shù)第2個(gè)country元素

構(gòu)建xml文檔

簡(jiǎn)單使用

from xml.etree.ElementTree import Element, ElementTree
from xml.etree.ElementTree import tostring

e = Element('Data')  # 創(chuàng)建一個(gè)元素
e.set('name', 'abc')  # 為元素添加name屬性奕删，并指定name屬性值為'abc'
e.text = '123'  # 為元素添加文本內(nèi)容

print(tostring(e))  # 將xml轉(zhuǎn)化為字符串文本俺泣，但是不含'\n''\t'：b'<Data name="abc">123</Data>'，導(dǎo)致大文本的xml可讀性差

e2 = Element('Row')
e3 = Element('Open')
e3.text = '8.80'
e2.append(e3)  # 將e3添加到e2的子元素
e.append(e2)  # 將e2添加到e的子元素

print(tostring(e))

et = ElementTree(e)  # 生成ElementTree樹(shù)結(jié)構(gòu)完残，只需傳入根節(jié)點(diǎn)即可
et.write('demo02.xml')  # 將樹(shù)結(jié)構(gòu)寫(xiě)文件即可

code

import csv
from xml.etree.ElementTree import ElementTree, Element


def csvtoxml(fname):
    with open(fname, 'r') as f:
        reader = csv.reader(f)
        header = next(reader)
        root = Element('Data')
        for row in reader:
            erow = Element('Row')
            root.append(erow)
            for tag, text in zip(header, row):
                e = Element(tag)
                e.text = text
                erow.append(e)
    pretty(root)
    return ElementTree(root)

# 美化xml格式
def pretty(e, level=0):
    if len(e) > 0:
        e.text = '\n' + '\t' * (level+1)
        for child in e:
            pretty(child, level+1)
        child.tail = child.tail[:-1]
    e.tail = '\n' + '\t' * level

et = csvtoxml('pingan.csv')
et.write('pingan.xml')