Python が XML を解析するいくつかの方法を分析する

  print("文件计数：%d/%d." % (gz_cnt,paser_num))
  str_s,cnt = dom_parser(gz)
  #str_s,cnt = sax_parser(gz)
  #str_s,cnt = ET_parser(gz)
  #str_s,cnt = ET_parser_iter(gz)
  output.write(str_s)
  vs_cnt += cnt

def dom_parser(gz):
  import gzip,cStringIO
  import xml.dom.minidom
  
  vs_cnt = 0
  str_s = ''
  file_io = cStringIO.StringIO()
  xm = gzip.open(gz,'rb')
  print("已读入：%s.\n解析中：" % (os.path.abspath(gz)))
  doc = xml.dom.minidom.parseString(xm.read())
  bulkPmMrDataFile = doc.documentElement
  #读入子元素
  enbs = bulkPmMrDataFile.getElementsByTagName("eNB")
  measurements = enbs[0].getElementsByTagName("measurement")
  objects = measurements[0].getElementsByTagName("object")
  #写入csv文件
  for object in objects:
    vs = object.getElementsByTagName("v")
    vs_cnt += len(vs)
    for v in vs:
      file_io.write(enbs[0].getAttribute("id")+' '+object.getAttribute("id")+' '+\
      object.getAttribute("MmeUeS1apId")+' '+object.getAttribute("MmeGroupId")+' '+object.getAttribute("MmeCode")+' '+\
      object.getAttribute("TimeStamp")+' '+v.childNodes[0].data+'\n') #获取文本值
  str_s = (((file_io.getvalue().replace(' \n','\r\n')).replace(' ',',')).replace('T',' ')).replace('NIL','')
  xm.close()
  file_io.close()
  return (str_s,vs_cnt)

def sax_parser(gz):
  import os,gzip,cStringIO
  from xml.parsers.expat import ParserCreate
  #变量声明
  d_eNB = {}
  d_obj = {}
  s = ''
  global flag 
  flag = False
  file_io = cStringIO.StringIO()
  
  #Sax解析类
  class DefaultSaxHandler(object):
    #处理开始标签
    def start_element(self, name, attrs):
      global d_eNB
      global d_obj
      global vs_cnt
      if name == 'eNB':
        d_eNB = attrs
      elif name == 'object':
        d_obj = attrs
      elif name == 'v':
        file_io.write(d_eNB['id']+' '+ d_obj['id']+' '+d_obj['MmeUeS1apId']+' '+d_obj['MmeGroupId']+' '+d_obj['MmeCode']+' '+d_obj['TimeStamp']+' ')
        vs_cnt += 1
      else:
        pass
    #处理中间文本
    def char_data(self, text):
      global d_eNB
      global d_obj
      global flag
      if text[0:1].isnumeric():
        file_io.write(text)
      elif text[0:17] == 'MR.LteScPlrULQci1':
        flag = True
        #print(text,flag)
      else:
        pass
    #处理结束标签
    def end_element(self, name):
      global d_eNB
      global d_obj
      if name == 'v':
        file_io.write('\n')
      else:
        pass
  
  #Sax解析调用
  handler = DefaultSaxHandler()
  parser = ParserCreate()
  parser.StartElementHandler = handler.start_element
  parser.EndElementHandler = handler.end_element
  parser.CharacterDataHandler = handler.char_data
  vs_cnt = 0
  str_s = ''
  xm = gzip.open(gz,'rb')
  print("已读入：%s.\n解析中：" % (os.path.abspath(gz)))
  for line in xm.readlines():
    parser.Parse(line) #解析xml文件内容
    if flag:
      break
  str_s = file_io.getvalue().replace(' \n','\r\n').replace(' ',',').replace('T',' ').replace('NIL','')  #写入解析后内容
  xm.close()
  file_io.close()
  return (str_s,vs_cnt)

def ET_parser(gz):
  import os,gzip,cStringIO
  import xml.etree.cElementTree as ET
  vs_cnt = 0
  str_s = ''
  file_io = cStringIO.StringIO()
  xm = gzip.open(gz,'rb')
  print("已读入：%s.\n解析中：" % (os.path.abspath(gz)))
  tree = ET.ElementTree(file=xm)
  root = tree.getroot()
  for elem in root[1][0].findall('object'):
      for v in elem.findall('v'):
          file_io.write(root[1].attrib['id']+' '+elem.attrib['TimeStamp']+' '+elem.attrib['MmeCode']+' '+\
          elem.attrib['id']+' '+ elem.attrib['MmeUeS1apId']+' '+ elem.attrib['MmeGroupId']+' '+ v.text+'\n')
      vs_cnt += 1
  str_s = file_io.getvalue().replace(' \n','\r\n').replace(' ',',').replace('T',' ').replace('NIL','')  #写入解析后内容
  xm.close()
  file_io.close()
  return (str_s,vs_cnt)

def ET_parser_iter(gz):
  import os,gzip,cStringIO
  import xml.etree.cElementTree as ET
  vs_cnt = 0
  str_s = ''
  file_io = cStringIO.StringIO()
  xm = gzip.open(gz,'rb')
  print("已读入：%s.\n解析中：" % (os.path.abspath(gz)))
  d_eNB = {}
  d_obj = {}
  i = 0
  for event,elem in ET.iterparse(xm,events=('start','end')):
    if i >= 2:
      break    
    elif event == 'start':
          if elem.tag == 'eNB':
              d_eNB = elem.attrib
          elif elem.tag == 'object':
        d_obj = elem.attrib
      elif event == 'end' and elem.tag == 'smr':
      i += 1
    elif event == 'end' and elem.tag == 'v':
      file_io.write(d_eNB['id']+' '+d_obj['TimeStamp']+' '+d_obj['MmeCode']+' '+d_obj['id']+' '+\
      d_obj['MmeUeS1apId']+' '+ d_obj['MmeGroupId']+' '+str(elem.text)+'\n')
          vs_cnt += 1
      elem.clear()
  str_s = file_io.getvalue().replace(' \n','\r\n').replace(' ',',').replace('T',' ').replace('NIL','')  #写入解析后内容
  xm.close()
  file_io.close()
  return (str_s,vs_cnt)