2021-03-24

python读取xml文件固定标签，并写入txt文件

# 读取XML文件里的图片标签

import xml.dom.minidom
class TXT_W:
    def __init__(self,path,paths_name):
        self.path = path
        self.paths_name = paths_name

    def __call__(self):
        try:
            fh = open(self.path, "w")
            for i in range(len(self.paths_name)):
                dom = xml.dom.minidom.parse(self.paths_name[i])
                root = dom.documentElement
                cc=dom.getElementsByTagName('name')
                bb=dom.getElementsByTagName('filename')
                c1=cc[0]
                b1=bb[0]
                c2=c1.firstChild.data
                b2=b1.firstChild.data
                if c2 in 'zhengface':
                    fh.write('JPEGImages/'+b2+'.jpg'+' '+'0'+'\n')
                else:
                    fh.write('JPEGImages/'+b2+'.jpg'+' '+'1'+'\n')
                # print(c2)
                # print(b2+'.jpg')
        except IOError:
            print('Error: 没有找到文件或读取文件失败')
        else:
            print ('内容写入文件成功')
            fh.close()

XML文件样式

<annotation verified="no">
  <folder>JPEGImages</folder>
  <filename>000003</filename>
  <path>D:\SSD&#31639;&#27861;&#25913;&#36827;\SSD-Tensorflow-master\VOC2007\JPEGImages\000003.jpg</path>
  <source>
    <database>Unknown</database>
  </source>
  <size>
    <width>267</width>
    <height>410</height>
    <depth>3</depth>
  </size>
  <segmented>0</segmented>
  <object>
    <name>zhengface</name>
    <pose>Unspecified</pose>
    <truncated>0</truncated>
    <Difficult>0</Difficult>
    <bndbox>
      <xmin>38</xmin>
      <ymin>67</ymin>
      <xmax>259</xmax>
      <ymax>376</ymax>
    </bndbox>
  </object>
</annotation>

python读取xml文件和标签的内容