针对训练数据xml中获取需要的某一类或几类

针对训练数据xml中获取需要的某一类或几类，主要是这段时间自己处理数据需要用到的一些工具，做下笔记，若能帮助到需要的你，非常高兴！

import os  
import os.path  
import shutil  

#fileDir_ann = "F:\\work\\python_data\\"  
fileDir_ann = "F:\\work\\python_data\\Annotations\\"  //xml路径
fileDir_img = "F:\\work\\python_data\\JPEGImages\\"  //image路径
saveDir_img = "F:\\work\\python_data\\JPEGImages_ssd\\"  //筛选后的image保存路径
  
if not os.path.exists(saveDir_img):  
    os.mkdir(saveDir_img)  
  
names = locals() 
for files in os.walk(fileDir_ann):
     print('hello python! for')
print('hello python!')
for files in os.walk(fileDir_ann):  
    #print('hello python!')
    for file in files[2]:  
        print file + "-->start!"  
  
        saveDir_ann = "F:\\work\\python_data\\Annotations_ssd\\"  //筛选后的xml保存路径
        if not os.path.exists(saveDir_ann):  
            os.mkdir(saveDir_ann)  
  
        fp = open(fileDir_ann + '\\' + file)          
        saveDir_ann = saveDir_ann + file  
        fp_w = open(saveDir_ann, 'w')  

        classes = ["PEOPLE","CAR","motorake","baus","cat"]; #必须是涵盖原始xml中所有类别
        lines = fp.readlines()  
  
        ind_start = []  
        ind_end = []  
        lines_id_start = lines[:]  
        lines_id_end = lines[:]  
          
        while "\t<object>\n" in lines_id_start:  
            a = lines_id_start.index("\t<object>\n")  
            ind_start.append(a)  
            lines_id_start[a] = "delete"  
  
        while "\t</object>\n" in lines_id_end:  
            b = lines_id_end.index("\t</object>\n")  
            ind_end.append(b)  
            lines_id_end[b] = "delete"  
          
        i = 0  
        for k in range(0,len(ind_start)):  
            for j in range(0,len(classes)):  
                if classes[j] in lines[ind_start[i]+1]:  
                    a = ind_start[i]  
                    names['block%d'%k] = [lines[a],lines[a+1],lines[a+2],lines[a+3],lines[a+4],lines[a+5],lines[a+6],lines[a+7],lines[a+8],lines[a+9],lines[a+10],lines[ind_end[i]]]  
                    break  
            i += 1  
  
        classes1 = '\t\t<name>PEOPLE</name>\n'  
        #classes2 = '\t\t<name>motorake</name>\n'  
        #classes3 = '\t\t<name>baus</name>\n'  
        #classes4 = '\t\t<name>cat</name>\n'  
        print(len(ind_start))
        string_start = lines[0:ind_start[0]]  
        string_end = [lines[len(lines)-1]]  
          
        a = 0  
        for k in range(0,len(ind_start)):   
            if classes1 in names['block%d'%k]:  
                a += 1  
                string_start += names['block%d'%k]  
            #if classes2 in names['block%d'%k]:  
                #a += 1  
                #string_start += names['block%d'%k]  
            #if classes3 in names['block%d'%k]:  
                #a += 1  
                #string_start += names['block%d'%k]  
            #if classes4 in names['block%d'%k]:  
                #a += 1  
                #string_start += names['block%d'%k]
  
        string_start += string_end   
        for c in range(0,len(string_start)):  
            fp_w.write(string_start[c])  
        fp_w.close()  
  
        if a == 0:  
            os.remove(saveDir_ann)  
        else:  
            name_img = fileDir_img + os.path.splitext(file)[0]# + ".png" //根据自己的图片类型进行设置
            shutil.copy(name_img,saveDir_img)  
        fp.close()