删除xml中指定标签，判断xml中标签是否为空，并移动xml和相应图片到指定路径

python脚本分为两个：1、删除xml中指定标签2、判断xml中标签是否为空，并移动xml和相应图片到指定路径。可以整合到一个python文件中，太懒就不弄了。

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
 
import os
import xml.etree.ElementTree as ET

#删除xml中指定的标签信息
origin_ann_dir = '/home/data_1/project/big-obj/RefineDet.PyTorch/data/VOCdevkit/VOC2007/Annotations/'# 设置原始标签路径为 Annos
new_ann_dir = '/home/data_1/project/big-obj/RefineDet.PyTorch/data/VOCdevkit/VOC2007/Annotations-erased/'# 设置新标签路径 Annotations
k=0
for dirpaths, dirnames, filenames in os.walk(origin_ann_dir):   # os.walk游走遍历目录名
  for filename in filenames:
    print("process...")
    k=k+1
    print(k)
    if os.path.isfile(r'%s%s' %(origin_ann_dir, filename)):   # 获取原始xml文件绝对路径，isfile()检测是否为文件 isdir检测是否为目录
      origin_ann_path = os.path.join(r'%s%s' %(origin_ann_dir, filename))   # 如果是，获取绝对路径（重复代码）
      new_ann_path = os.path.join(r'%s%s' %(new_ann_dir, filename))
      tree = ET.parse(origin_ann_path)  # ET是一个xml文件解析库，ET.parse（）打开xml文件。parse--"解析"
      root = tree.getroot()   # 获取根节点
      for object in root.findall('object'):   # 找到根节点下所有“object”节点
        name = str(object.find('name').text)  # 找到object节点下name子节点的值（字符串）
    # 如果name等于str，则删除该节点
        if (name in ["jianyanbaogao"]):
          root.remove(object)
        if (name in ["jianyanbaogao-yiqi"]):
          root.remove(object)

      tree.write(new_ann_path)#tree为文件，write写入新的文件中。

 

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
 
#移动标签为空的xml，并同步移动相应图片
import os
import xml.etree.ElementTree as ET
import shutil

origin_ann_dir = '/home/data_1/project/big-obj/RefineDet.PyTorch/data/VOCdevkit/VOC2007/Annotations/'# 设置原始标签路径为 Annos
new_ann_dir = '/home/data_1/project/big-obj/RefineDet.PyTorch/data/VOCdevkit/VOC2007/xml-save/'# 设置新标签路径 Annotations
origin_pic_dir = '/home/data_1/project/big-obj/RefineDet.PyTorch/data/VOCdevkit/VOC2007/JPEGImages/'
new_pic_dir = '/home/data_1/project/big-obj/RefineDet.PyTorch/data/VOCdevkit/VOC2007/pic-save/'
k=0
p=0
q=0
for dirpaths, dirnames, filenames in os.walk(origin_ann_dir):   # os.walk游走遍历目录名
  for filename in filenames:
    print("process...")
    k=k+1
    print(k)
    if os.path.isfile(r'%s%s' %(origin_ann_dir, filename)):   # 获取原始xml文件绝对路径，isfile()检测是否为文件 isdir检测是否为目录
      origin_ann_path = os.path.join(r'%s%s' %(origin_ann_dir, filename))   # 如果是，获取绝对路径（重复代码）
      new_ann_path = os.path.join(r'%s%s' %(new_ann_dir, filename))
      tree = ET.parse(origin_ann_path)  # ET是一个xml文件解析库，ET.parse（）打开xml文件。parse--"解析"
      root = tree.getroot()   # 获取根节点
      if len(root.findall('object')):
        p=p+1
      else:
        print(filename)
        old_xml = origin_ann_dir + filename
        new_xml = new_ann_dir + filename
        old_pic = origin_pic_dir + filename.replace("xml","jpg")
        new_pic = new_pic_dir + filename.replace("xml","jpg")
        q=q+1
        shutil.move(old_pic, new_pic)
        shutil.move(old_xml, new_xml)
print("ok, ",p)
print("empty, ",q)