python 生成xml文件,以及美化的實例代碼

# -*- coding:utf-8 -*- 
import os
import json
import numpy as np 
#from xml.etree import ElementTree as  etree
from xml.etree.ElementTree import Element
from xml.etree.ElementTree import SubElement
from xml.etree.ElementTree import ElementTree
 
imagePath = r'E:\Desktop\SteelCoilsDetection\test\images'
jsonPath = r'E:\Desktop\SteelCoilsDetection\test\json'
savePath = r'E:\Desktop\SteelCoilsDetection\test\xml'
 
jsonList = os.listdir(jsonPath)
for jsonName in jsonList:
    print(jsonName)
    readPath = os.path.join(jsonPath, jsonName)
 
    # 打開json文件
    with open(readPath, 'r') as file_loader:
        jsonDic = json.load(file_loader)
 
    # print(jsonDic.keys())
    # dict_keys(['version', 'flags', 'shapes', 'imagePath', 'imageData', 'imageHeight', 'imageWidth'])
    
    # 生成xml文件
    annotation = Element('annotation')
 
    folder = SubElement(annotation, 'folder')
    folder.text = "images"
 
    filename = SubElement(annotation, 'filename')
    filename.text = jsonName.split('.')[0]
 
    path = SubElement(annotation, 'path')
    path.text = imagePath + jsonName.split('.')[0]
 
    source = SubElement(annotation, 'source')
    database = SubElement(source, 'database')
    database.text = "Unknown"
 
    size = SubElement(annotation, 'size')
    width = SubElement(size, 'width')
    width.text = str(jsonDic['imageWidth'])
    height = SubElement(size, 'height')
    height.text = str(jsonDic['imageHeight'])
    depth = SubElement(size, 'depth')
    depth.text = "3"
 
    segmented = SubElement(annotation, 'segmented')
    segmented.text = "0" 
    for shape in jsonDic['shapes']: 
        if shape["label"] == 'a':
            continue        
 
        object = SubElement(annotation, 'object') 
        name = SubElement(object, 'name')
        name.text = shape["label"]
 
        pose = SubElement(object, 'pose')
        pose.text = 'Unspecified'
 
        truncated = SubElement(object, 'truncated')
        truncated.text = str(0)
 
        difficult = SubElement(object, 'difficult')
        difficult.text = str(0)        
 
        points = shape['points']
        mritx = np.array(points)
        xxmin = min(mritx[:, 0])
        xxmax = max(mritx[:, 0])
        yymin = min(mritx[:, 1])
        yymax = max(mritx[:, 1])
 
        bndbox = SubElement(object, 'bndbox')
        xmin = SubElement(bndbox, 'xmin')
        xmin.text = str(int(xxmin))
        ymin = SubElement(bndbox, 'ymin')
        ymin.text = str(int(yymin))
        xmax = SubElement(bndbox, 'xmax')
        xmax.text = str(int(xxmax))
        ymax = SubElement(bndbox, 'ymax')
        ymax.text = str(int(yymax)) 
    tree = ElementTree(annotation)
    tree.write(os.path.join(savePath, jsonName.split('.')[0]+'.xml'), encoding = 'utf-8')

# -*- coding:utf-8 -*- 
import os
from xml.etree import ElementTree      # 導入ElementTree模塊  
# elemnt為傳進來的Elment類，參數indent用於縮進，newline用於換行
def prettyXml(element, indent, newline, level = 0):
 
    # 判斷element是否有子元素
    if element:
 
        # 如果element的text沒有內容
        if element.text == None or element.text.isspace():
            element.text = newline + indent * (level + 1)
        else:
            element.text = newline + indent * (level + 1) + element.text.strip() + newline + indent * (level + 1)
 
    # 此處兩行如果把註釋去掉，Element的text也會另起一行 
    #else:
        #element.text = newline + indent * (level + 1) + element.text.strip() + newline + indent * level
 
    temp = list(element) # 將elemnt轉成list
    for subelement in temp:
        # 如果不是list的最後一個元素，說明下一個行是同級別元素的起始，縮進應一致
        if temp.index(subelement) < (len(temp) - 1):
            subelement.tail = newline + indent * (level + 1)
        else:  # 如果是list的最後一個元素， 說明下一行是母元素的結束，縮進應該少一個
            subelement.tail = newline + indent * level   
 
        # 對子元素進行遞歸操作 
        prettyXml(subelement, indent, newline, level = level + 1)  
 
dir = r'E:\Desktop\SteelCoilsDetection\test\xml'
for fileName in os.listdir(dir):
    print(fileName)
    tree = ElementTree.parse(os.path.join(dir, fileName))   #解析test.xml這個文件，該文件內容如上文
    root = tree.getroot()                                   #得到根元素，Element類
    prettyXml(root, '\t', '\n')                             # 執行美化方法
 
    #ElementTree.dump(root)                                 #顯示出美化後的XML內容
    tree.write(os.path.join(dir, fileName), encoding = 'utf-8')

<?xml version="1.0"?>
<bookstore>
	<book name="西遊記">
		<author>吳承恩</author>
		<dynasty>明朝</dynasty>
		<similar name="封神演義" author="許仲琳"/>
	</book>
	<book name="紅樓夢">
		<author>曹雪芹</author>
		<dynasty>清朝</dynasty>
	</book>
	<book name="三國演義">
		<author>羅貫中</author>
		<dynasty>明末清初</dynasty>
		<similar name="三國志" author="陳壽"/>
	</book>
</bookstore>

import xml.etree.ElementTree as ET
tree = ET.parse("./book.xml")
root = tree.getroot()

with open("./book.xml") as fp:
    root = ET.fromstring(fp.read())

# 遍歷直接子節點
for book in root:
    print(book.tag, book.attrib, book.get("name"))
# 訪問根節點下的第2個子節點, 再向下訪問第1個子節點的文本, 也就是 "<author>曹雪芹</author>"
author = root[1][0].text
print(type(author), author)

# 遞歸選擇所有標簽名為 "similar" 的節點
for book in root.iter("similar"):
    print(book.attrib)

# . 表示 bookstore 節點
author_1 = tree.find("./book[@name='紅樓夢']/author").text
author_2 = tree.findtext("./book[@name='紅樓夢']/author")
print("紅樓夢作者:", author_1, author_2)
author_3 = root.find("./book/similar[@name='三國志']").get("author")
print("三國志作者:", author_3)

books_1 = root.findall("./book[similar]")
# 對於直接子節點, 可以省略 ./
books_2 = root.findall("book[similar]")
print(books_1 == books_2)
for book in books_1:
    print(book[0].text, book[1].text)