python

python xml

by · 2019年10月31日 · 747 Words · ~2min reading time | Improve on

原文链接： python xml

ET读取xml
try:
import xml.etree.cElementTree as ET C实现速度快一点的xml.etree.cElementTree
except ImportError:
import xml.etree.ElementTree as ET

import xml.etree.ElementTree as ET----------导入xml模块
root = ET.parse('GHO.xml')------------------分析指定xml文件
tree = root.getroot()-----------------------获取第一标签
data = tree.find('Data')--------------------查找第一标签中'Data'标签
for obs in data:----------------------------历遍'Data'中的所有标签

for item in obs:------------------------历遍'Data'中的'obs'标签下的所有标签
    key = item.attrib()-----------------提取key值参数
    print(list(key))--------------------输出key值

try: 
  import xml.etree.cElementTree as ET 
except ImportError: 
  import xml.etree.ElementTree as ET 
import sys 
  
try: 
  tree = ET.parse("country.xml")     #打开xml文档 
  #root = ET.fromstring(country_string) #从字符串传递xml 
  root = tree.getroot()         #获得root节点  
except Exception, e: 
  print "Error:cannot parse file:country.xml."
  sys.exit(1) 
print root.tag, "---", root.attrib  
for child in root: 
  print child.tag, "---", child.attrib 
  
print "*"*10
print root[0][1].text   #通过下标访问 
print root[0].tag, root[0].text 
print "*"*10
  
for country in root.findall('country'): #找到root节点下的所有country节点 
  rank = country.find('rank').text   #子节点下节点rank的值 
  name = country.get('name')      #子节点下属性name的值 
  print name, rank 
     
#修改xml文件 
for country in root.findall('country'): 
  rank = int(country.find('rank').text) 
  if rank > 50: 
    root.remove(country) 
  
tree.write('output.xml')

voc2yolo 格式转换

import xml.etree.ElementTree as ET
import os
from os import getcwd

sets=[('2017', 'train'),('2017', 'val')]
format = 'png'
classes = ['banana', 'monkey', 'panda']


def convert(size, box):
    dw = 1./size[0]
    dh = 1./size[1]
    x = (box[0] + box[1])/2.0
    y = (box[2] + box[3])/2.0
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x*dw
    w = w*dw
    y = y*dh
    h = h*dh
    return (x,y,w,h)


def convert_annotation(year, image_id):
    in_file = open('devkit/%s/Annotations/%s.xml'%(year, image_id))
    out_file = open('devkit/%s/labels/%s.txt'%(year, image_id), 'w')
    tree=ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
        bb = convert((w,h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

wd = getcwd()

for year, image_set in sets:
    if not os.path.exists('devkit/%s/labels/'%(year)):
        os.makedirs('devkit/%s/labels/'%(year))
    image_ids = open('devkit/%s/ImageSets/%s.txt'%(year, image_set)).read().strip().split()
    list_file = open('%s_%s.txt'%(year, image_set), 'w')
    for image_id in image_ids:
        list_file.write('%s/devkit/%s/Images/%s.%s\n'%(wd, year, image_id, format))
        convert_annotation(year, image_id)
    list_file.close()

Tags: python

`