13518219792
本篇文章给大家分享的是有关如何在Python中读取xml数据，小编觉得挺实用的，因此分享给大家学习，希望大家阅读完这篇文章后可以有所收获，话不多说，跟着小编一起来看看吧。
1、云计算，典型应用OpenStack。2、WEB前端开发，众多大型网站均为Python开发。3.人工智能应用，基于大数据分析和深度学习而发展出来的人工智能本质上已经无法离开python。4、系统运维工程项目，自动化运维的标配就是python+Django/flask。5、金融理财分析，量化交易，金融分析。6、大数据分析。
from __future__ import division
import os
from PIL import Image
import xml.dom.minidom
import numpy as np
ImgPath = 'C:/Users/Desktop/XML_try/img/'
AnnoPath = 'C:/Users/Desktop/XML_try/xml/'
ProcessedPath = 'C:/Users/Desktop/CropedVOC/'
imagelist = os.listdir(ImgPath)
for image in imagelist:
image_pre, ext = os.path.splitext(image)
imgfile = ImgPath + image
xmlfile = AnnoPath + image_pre + '.xml'
DomTree = xml.dom.minidom.parse(xmlfile)
annotation = DomTree.documentElement
filenamelist = annotation.getElementsByTagName('filename') #[]
filename = filenamelist[0].childNodes[0].data
objectlist = annotation.getElementsByTagName('object')
i = 1
for objects in objectlist:
namelist = objects.getElementsByTagName('name')
objectname = namelist[0].childNodes[0].data
savepath = ProcessedPath + objectname
if not os.path.exists(savepath):
os.makedirs(savepath)
bndbox = objects.getElementsByTagName('bndbox')
cropboxes = []
for box in bndbox:
x1_list = box.getElementsByTagName('xmin')
x1 = int(x1_list[0].childNodes[0].data)
y1_list = box.getElementsByTagName('ymin')
y1 = int(y1_list[0].childNodes[0].data)
x2_list = box.getElementsByTagName('xmax')
x2 = int(x2_list[0].childNodes[0].data)
y2_list = box.getElementsByTagName('ymax')
y2 = int(y2_list[0].childNodes[0].data)
w = x2 - x1
h = y2 - y1
obj = np.array([x1,y1,x2,y2])
shift = np.array([[0.8,0.8,1.2,1.2],[0.9,0.9,1.1,1.1],[1,1,1,1],[0.7,0.7,1,1],[1,1,1.2,1.2],\
[0.7,1,1,1.2],[1,0.7,1.2,1],[(x1+w*1/3)/x1,(y1+h*1/3)/y1,(x2+w*1/3)/x2,(y2+h*1/3)/y2],\
[(x1-w*1/3)/x1,(y1-h*1/3)/y1,(x2-w*1/3)/x2,(y2-h*1/3)/y2]])
XYmatrix = np.tile(obj,(9,1))
cropboxes = XYmatrix * shift
img = Image.open(imgfile)
for cropbox in cropboxes:
cropedimg = img.crop(cropbox)
cropedimg.save(savepath + '/' + image_pre + '_' + str(i) + '.jpg')
i += 1 补充知识：python-----截取xml文件画框的图片并保存
from __future__ import division
import os
from PIL import Image
import xml.dom.minidom
import numpy as np
ImgPath = r'D:\tmp\video_wang_mod\01\00022_8253_0021_3\output/'
AnnoPath = r'D:\tmp\video_wang_mod\01\00022_8253_0021_3\Annotations/'
ProcessedPath = r'D:\tmp\video_wang_mod\01\00022_8253_0021_3\cut/'
imagelist = os.listdir(ImgPath)
for image in imagelist:
image_pre, ext = os.path.splitext(image)
imgfile = ImgPath + image
print(imgfile)
if not os.path.exists(AnnoPath + image_pre + '.xml' ):
continue
xmlfile = AnnoPath + image_pre + '.xml'
DomTree = xml.dom.minidom.parse(xmlfile)
annotation = DomTree.documentElement
filenamelist = annotation.getElementsByTagName('filename')
filename = filenamelist[0].childNodes[0].data
objectlist = annotation.getElementsByTagName('object')
i = 1
for objects in objectlist:
namelist = objects.getElementsByTagName('name')
objectname = namelist[0].childNodes[0].data
savepath = ProcessedPath + objectname
if not os.path.exists(savepath):
os.makedirs(savepath)
bndbox = objects.getElementsByTagName('bndbox')
cropboxes = []
for box in bndbox:
x1_list = box.getElementsByTagName('xmin')
x1 = int(x1_list[0].childNodes[0].data)
y1_list = box.getElementsByTagName('ymin')
y1 = int(y1_list[0].childNodes[0].data)
x2_list = box.getElementsByTagName('xmax')
x2 = int(x2_list[0].childNodes[0].data)
y2_list = box.getElementsByTagName('ymax')
y2 = int(y2_list[0].childNodes[0].data)
w = x2 - x1
h = y2 - y1
obj = np.array([x1,y1,x2,y2])
shift = np.array([[1,1,1,1]])
XYmatrix = np.tile(obj,(1,1))
cropboxes = XYmatrix * shift
img = Image.open(imgfile)
for cropbox in cropboxes:
cropedimg = img.crop(cropbox)
cropedimg.save(savepath + '/' + image_pre + '_' + str(i) + '.jpg')
i += 1以上就是如何在Python中读取xml数据，小编相信有部分知识点可能是我们日常工作会见到或用到的。希望你能通过这篇文章学到更多知识。更多详情敬请关注创新互联成都网站设计公司行业资讯频道。
另外有需要云服务器可以了解下创新互联scvps.cn，海内外云服务器15元起步，三天无理由+7*72小时售后在线，公司持有idc许可证，提供“云服务器、裸金属服务器、高防服务器、香港服务器、美国服务器、虚拟主机、免备案服务器”等云主机租用服务以及企业上云的综合解决方案，具有“安全稳定、简单易用、服务可用性高、性价比高”等特点与优势，专为企业上云打造定制，能够满足用户丰富、多元化的应用场景需求。
