python解析xml文件

from xml.dom import minidom
# 打开文件
DomTree = minidom.parse('path')
# 获取xml对象
annotation = DomTree.documentElement
# 获取一级节点 列表返回
folder=annotation.getElementsByTagName("folder")
filename=annotation.getElementsByTagName("filename")
source=annotation.getElementsByTagName("source")
size=annotation.getElementsByTagName("size")
segmented=annotation.getElementsByTagName("segmented")
obj=annotation.getElementsByTagName("object")
# 在obj列表的第一个对象中查找part
part = obj[0].getElementsByTagName("part")
for i in part:
    name=i.getElementsByTagName("name")[0].childNodes[0]
    bndbox=i.getElementsByTagName("bndbox")[0]
    # 例：dom(a标签).childNodes[0] 获取的是<a><x>之间的飞标签字符，包含换行，或其他字符
    # dom(a标签).childNodes[1] 即可得到<x></x>标签
    """
    <a>
        <x></x>
    </a>
    """
    # dom.getAttribute("id") 可获取属性值
    xmin = bndbox.getElementsByTagName("xmin")[0].childNodes[0].data
    ymin = bndbox.getElementsByTagName("ymin")[0].childNodes[0].data
    xmax = bndbox.getElementsByTagName("xmax")[0].childNodes[0].data
    ymax = bndbox.getElementsByTagName("ymax")[0].childNodes[0].data
    print(name,bndbox,xmin,ymin,xmax,ymax,type(bndbox.getElementsByTagName("xmin")[0]))

import xml.sax
class AnnotationHandler(xml.sax.ContentHandler):
    def ___init__(self):
        self.firstAttr=""
        self.secAttr=""
    def startElement(self,tag,attribute):
        pass
    def characters(self,content):
        pass
    def endElement(self,tag):
        pass
parser = xml.sax.make_parser()
# 关闭namespaces
parser.setFeature(xml.sax.handler.feature_namespaces,0)
parser.setContentHandler(AnnotationHandler())
parser.parse("path")

import xml.etree.ElementTree as et
tree = et.parse('path')
root=tree.getroot() # 获取根节点
print(root.tag,root.attrib)  # annotation 标签名 , 获取属性
for i in root: # 找到root的一级字标签 也可以root[n] 获取
    print(i.tag,i.text)
    # i.txt 表示i标签中的非标签值
    """
    <i>xx</i>  i.text=xx
    <i>
    <x></x> i.text=换行
    </i>
    <i><x></x> i.text=None
    </i>
    """

<annotation>
	<folder>VOC2012</folder>
	<filename>2007_000027.jpg</filename>
	<source>
		<database>The VOC2007 Database</database>
		<annotation>PASCAL VOC2007</annotation>
		<image>flickr</image>
	</source>
	<size>
		<width>486</width>
		<height>500</height>
		<depth>3</depth>
	</size>
	<segmented>0</segmented>
	<object>
		<name>person</name>
		<pose>Unspecified</pose>
		<truncated>0</truncated>
		<difficult>0</difficult>
		<bndbox>
			<xmin>174</xmin>
			<ymin>101</ymin>
			<xmax>349</xmax>
			<ymax>351</ymax>
		</bndbox>
		<part>
			<name>head</name>
			<bndbox>12
				<xmin>169</xmin>
				<ymin>104</ymin>
				<xmax>209</xmax>
				<ymax>146</ymax>
			</bndbox>
		</part>
		<part>
			<name>hand</name>
			<bndbox>
				<xmin>278 asd</xmin>
				<ymin>210</ymin>
				<xmax>297</xmax>
				<ymax>233</ymax>
			</bndbox>
		</part>
		<part>
			<name>foot</name>
			<bndbox>
				<xmin>273</xmin>
				<ymin>333</ymin>
				<xmax>297</xmax>
				<ymax>354</ymax>
			</bndbox>
		</part>
		<part>
			<name>foot</name>
			<bndbox>
				<xmin>319</xmin>
				<ymin>307</ymin>
				<xmax>340</xmax>
				<ymax>326</ymax>
			</bndbox>
		</part>
	</object>
</annotation>