python利用lxml读写xml格式的文件
之前在转换数据集格式的时候需要将json转换到xml文件，用lxml包进行操作非常方便。
1.写xml文件
a)用etree和objectify
fromlxmlimportetree,objectify
E=objectify.ElementMaker(annotate=False)
anno_tree=E.annotation(
E.folder('VOC2014_instance'),
E.filename("test.jpg"),
E.source(
E.database('COCO'),
E.annotation('COCO'),
E.image('COCO'),
E.url("http://test.jpg")
),
E.size(
E.width(800),
E.height(600),
E.depth(3)
),
E.segmented(0),
)
etree.ElementTree(anno_tree).write("text.xml",pretty_print=True)
输出的test.xml文件内容如下：
```
如果需要在anno_tree的基础上加其他标签的话用append即可:
E2=objectify.ElementMaker(annotate=False)
anno_tree2=E2.object(
E.name("person"),
E.bndbox(
E.xmin(100),
E.ymin(200),
E.xmax(300),
E.ymax(400)
),
E.difficult(0)
)
anno_tree.append(anno_tree2)
上面的输出就变成了:
VOC2014_instance/person test.jpg COCO COCO COCO http://test.jpg 800 600 3 0
b)用etree和SubElement
annotation=etree.Element("annotation")
etree.SubElement(annotation,"folder").text="VOC2014_instance"
etree.SubElement(annotation,"filename").text="test.jpg"
source=etree.SubElement(annotation,"source")
etree.SubElement(source,"database").text="COCO"
etree.SubElement(source,"annotation").text="COCO"
etree.SubElement(source,"image").text="COCO"
etree.SubElement(source,"url").text="http://test.jpg"
size=etree.SubElement(annotation,"size")
etree.SubElement(size,"width").text='800'#必须用string
etree.SubElement(size,"height").text='600'
etree.SubElement(size,"depth").text='3'
etree.SubElement(annotation,"segmented").text='0'
key_object=etree.SubElement(annotation,"object")
etree.SubElement(key_object,"name").text=“person”
bndbox=etree.SubElement(key_object,"bndbox")
etree.SubElement(bndbox,"xmin").text=str(100)
etree.SubElement(bndbox,"ymin").text=str(200)
etree.SubElement(bndbox,"xmax").text=str(300)
etree.SubElement(bndbox,"ymax").text=str(400)
etree.SubElement(key_object,"difficult").text='0'
doc=etree.ElementTree(annotation)
doc.write(open("test.xml","w"),pretty_print=True)
2.读xml
这里可以用xpath直接提取所需的元素的值。比如想要获取上面test.xml文件的x,y坐标：
tree=etree.parse("test.xml")
#getbbox
forbboxintree.xpath('//bndbox'):#获取bndbox元素的内容
forcornerinbbox.getchildren():#便利bndbox元素下的子元素
printcorner.text#string类型
参考
http://lxml.de/tutorial.html
https://stackoverflow.com/questions/12657043/parse-xml-with-lxml-extract-element-value
以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持毛票票。