xml文件_解析示例_python实现
注:文中代码的目的为解析xml 文件中的内容,输出xml 文件中的数据。
最原始的目的是为了统计数据集中图片标签的类别数。
xml文件内容展示
<annotation> <folder>images</folder> <filename>Czech_000022.jpg</filename> <size> <depth>3</depth> <width>600</width> <height>600</height> </size> <object> <name>D00</name> <bndbox> <xmin>182</xmin> <ymin>471</ymin> <xmax>229</xmax> <ymax>512</ymax> </bndbox> </object> </annotation>
读取并解析 xml 文件的 python 代码(代码不具有通用性,但是一种可实现的方式)
1 import os 2 import xml.etree.ElementTree as ET 3 4 def fun(xml_root_path, txt_save_path): 5 xml_files = os.listdir(xml_root_path) 6 print(type(xml_files), len(xml_files), xml_files[0]) 7 8 for xml_file in xml_files: 9 xml_path = os.path.join(xml_root_path, xml_file) 10 print('xml路径:', xml_path) 11 12 ### 解析xml 13 tree = ET.parse(xml_path) 14 root = tree.getroot() #获取根结点 15 print(type(root), len(root), root, '\n') 16 17 # 子标签:文件夹名称 18 folder_name = root[0].text 19 print('folder_name: \t', folder_name) 20 21 # 子标签:文件名称 22 file_name = root[1].text 23 print('file_name: \t', file_name) 24 25 # 子标签: 图像尺寸 26 size_name = root[2] 27 # print( len(size_name) ) # 3 28 size_depth = size_name[0].text 29 print('size_depth: \t', size_depth) 30 size_width = size_name[1].text 31 print('size_width: \t', size_width) 32 size_height = size_name[2].text 33 print('size_height: \t', size_height) 34 35 # 子标签: 标记框信息 36 object_name = root[3] 37 # print(len(object_name)) # 2 38 label_name = object_name[0].text 39 print('label_name:\t', label_name) ####### 标签名称,主要统计的是这个 40 # bbox 41 bndbox = object_name[1] 42 # print(len(bndbox)) # 4 43 bbox = [bndbox[0].text, bndbox[1].text, bndbox[2].text, bndbox[3].text ] 44 print(bbox) 45 46 47 temp_path = '../data/JanpanRoad' 48 txt_save_path = './temp.txt' 49 50 fun(temp_path, txt_save_path)
输出结果
1 <class 'list'> 1 Czech_000022.xml 2 xml路径: ../data/JanpanRoad\Czech_000022.xml 3 <class 'xml.etree.ElementTree.Element'> 4 <Element 'annotation' at 0x00000281DA735368> 4 5 folder_name: images 6 file_name: Czech_000022.jpg 7 size_depth: 3 8 size_width: 600 9 size_height: 600 10 label_name: D00 11 ['182', '471', '229', '512']
可通用性代码:
1 import os 2 import xml.dom.minidom 3 4 def xml_label_names(xml_root_path): 5 xml_files = os.listdir(xml_root_path) 6 for xml_file in xml_files: 7 xml_path = os.path.join(xml_root_path, xml_file) 8 # 打开xml文档 9 DOMTree = xml.dom.minidom.parse(xml_path) 10 # 得到文档元素对象 11 collection = DOMTree.documentElement 12 ### 获取文件名 13 filenamelist = collection.getElementsByTagName("filename") 14 filename = filenamelist[0].childNodes[0].data 15 print('\n', len(filenamelist), filename) 16 ### 得到标签名为object的信息 17 objectlist = collection.getElementsByTagName("object") 18 for objects in objectlist: 19 ### 每个 object 中得到子标签名为 name 的信息 20 namelist = objects.getElementsByTagName('name') 21 ### 获得标记框的标签名 22 objectname = namelist[0].childNodes[0].data 23 # print('类别名为: ', objectname) ########### 索要统计的信息 24 25 bndbox = objects.getElementsByTagName('bndbox') 26 for box in bndbox: 27 x1_list = box.getElementsByTagName('xmin') 28 x1 = int(x1_list[0].childNodes[0].data) 29 y1_list = box.getElementsByTagName('ymin') 30 y1 = int(y1_list[0].childNodes[0].data) 31 x2_list = box.getElementsByTagName('xmax') # 注意坐标,看是否需要转换 32 x2 = int(x2_list[0].childNodes[0].data) 33 y2_list = box.getElementsByTagName('ymax') 34 y2 = int(y2_list[0].childNodes[0].data) 35 bbox = [x1, y1, x2, y2] 36 print('文件名:', filename, ' ,标签名:', objectname, ' ,标记框:' , bbox) 37 38 xml_root_path = '../data/JanpanRoad' 39 xml_label_names(xml_root_path)
输出结果:
1 1 Czech_000022.jpg 2 文件名: Czech_000022.jpg ,标签名: D00 ,标记框: [182, 471, 229, 512] 3 4 1 Czech_000031.jpg 5 文件名: Czech_000031.jpg ,标签名: D20 ,标记框: [273, 442, 343, 488] 6 文件名: Czech_000031.jpg ,标签名: D20 ,标记框: [262, 395, 307, 439] 7 文件名: Czech_000031.jpg ,标签名: D00 ,标记框: [155, 396, 194, 437]