用Python去解析XML报文 V1.1

candy

演示如何用Python解析XML。
如下分别是待解析的XML报文，尾部是Python 源码。

• 
  
  • <?xmlversion="1.0"encoding="iso8859-1"?>
    
  • <viewid="CCBSA_v"msgType="1">
    
  • <viewElemid="jrcfwq"dispName="集群">
    
  • <viewElemid="fwqsl"dispName="服务器数量"value="1"/>
    
  • <viewElemid="Master"dispName="主控节点"value="STAR"/>
    
  • <viewElemid="Server">
    
  • <viewElemid="SrvName"value="01"dispName="STAR">
    
  • <viewElemid="Plat"dispName="平台信息">
    
  • <viewElemid="PlatStat"dispName="平台状态">
    
  • <viewElemid="MchPort"dispName="机器端口"value="12000"/>
    
  • <viewElemid="MchState"dispName="机器状态"value="在线"/>
    
  • <viewElemid="AllProc"dispName="总进程数"value="0"/>
    
  • <viewElemid="EslProc"dispName="平台进程数"value="29"/>
    
  • <viewElemid="SemNum"dispName="信号灯数"value="104"/>
    
  • <viewElemid="DrqSem"dispName="DRQ使用信号灯"value="53"/>
    
  • </viewElem>
    
  • <viewElemid="CpuStat"dispName="CPU状态">
    
  • <viewElemid="CpuIdle"dispName="idle"value="0"/>
    
  • <viewElemid="CpuUser"dispName="user"value="0"/>
    
  • <viewElemid="CpuNice"dispName="nice"value="0"/>
    
  • <viewElemid="CpuSys"dispName="sys"value="0"/>
    
  • <viewElemid="CpuWio"dispName="wio"value="0"/>
    
  • </viewElem>
    
  • <viewElemid="SysInfo"dispName="操作系统信息">
    
  • <viewElemid="CpuNum"dispName="CPU颗数"value="0"/>
    
  • <viewElemid="PhyMem"dispName="物理内存(K)"value="0"/>
    
  • <viewElemid="VirtMem"dispName="虚拟内存(K)"value="0"/>
    
  • <viewElemid="UsedMem"dispName="已用内存(K)"value="0"/>
    
  • <viewElemid="exit_freeMem"dispName="可用内存(K)"value="0"/>
    
  • <viewElemid="IFaceNum"dispName="网络接口数"value="0"/>
    
  • </viewElem>
    
  • <viewElemid="ProjInfo"dispName="项目信息">
    
  • <viewElemid="ShmSize"dispName="部署共享内存大小(k)"value="15251168"/>
    
  • <viewElemid="ShmKeep"dispName="部署共享内存剩余(k)"value="16769072"/>
    
  • <viewElemid="BcbSize"dispName="交换共享内存大小(k)"value="6304"/>
    
  • <viewElemid="BcbUsed"dispName="已用交换共享内存(k)"value="2208"/>
    
  • <viewElemid="BcbMax"dispName="最大交换共享内存(k)"value="70816"/>
    
  • <viewElemid="ChkNum"dispName="当前已用缓冲区段数"value="1"/>
    
  • <viewElemid="DrqMsg"dispName="缓存消息数"value="0"/>
    
  • <viewElemid="MsqNum"dispName="队列中的消息数"value="0"/>
    
  • <viewElemid="TranNum"dispName="本机交易统计"value="322047"/>
    
  • <viewElemid="DTAMPID"dispName="DTA管理服务进程号"value="3727372"/>
    
  • <viewElemid="RCYCLPID"dispName="垃圾回收服务进程号"value="3739830"/>
    
  • <viewElemid="SYNCPID"dispName="多机同步服务进程号"value="3670122"/>
    
  • <viewElemid="ISSUEPID"dispName="多机发布服务进程号"value="2871348"/>
    
  • <viewElemid="MACHSVRPID"dispName="多机交换服务进程号"value="0"/>
    
  • <viewElemid="MONCPID"dispName="多机监控同步服务进程号"value="0"/>
    
  • <viewElemid="MONSPID"dispName="多机监控发布服务进程号"value="0"/>
    
  • <viewElemid="DTANUM"dispName="适配器个数"value="12"/>
    
  • ....
    
  • ....
    
  • ......
    
  
  
  

　　
　　
　　

• fromxml.domimportminidom
  
• fromsysimportstderr
  
• fromos.pathimportjoin
  
• 
  
• __version__="V1.1"
  
• 
  
• """
  
• Definitionfortypesandmaps
  
• """
  
• dataTypMap={"integer":0,"foat":1,"boolean":2,
  
• "char":3,"string":4,"void":5,"double":6,
  
• "long":7,"object":8,"datetime":9}
  
• nodeTypMap={"LEAF":0,"NODE":2}
  
• nodeImgMap={nodeTypMap["LEAF"]:"/images/leaf.gif",
  
• nodeTypMap["NODE"]:"/images/node.gif"}
  
• whoMap={"Views":0,"Nodes":1,
  
• "NodeViews":2,"NodesRel":3}
  
• 
  
• classTIndicatorData:
  
• 
  
• def__init__(self,XML,dest):
  
• self.__xmldoc=minidom.parse(XML.strip(""))
  
• self.__root=self.__xmldoc.documentElement
  
• self.__destPath=dest.strip("")
  
• self.__gNodesList=[]#Storinguniquenodes
  
• self.__hViews=None#Filehandleforisac_mnt_view
  
• self.__hNodes=None#Filehandleforisac_mnt_basenode
  
• self.__hNodeViews=None#Filehandleforisac_mnt_basenode_view
  
• self.__hNodesRel=None#Filehandleforisac_mnt_basenode_rel
  
• self.__outputData={"Views":"","Nodes":"","NodeViews":"","NodesRel":""}
  
• #enddef
  
• 
  
• defGenIndicators(self):
  
• self.__hViews=open(join(self.__destPath,"isac_mnt_view.txt"),"w+")
  
• self.__hNodes=open(join(self.__destPath,"isac_mnt_basenode.txt"),"w+")
  
• self.__hNodeViews=open(join(self.__destPath,"isac_mnt_basenode_view.txt"),"w+")
  
• self.__hNodesRel=open(join(self.__destPath,"isac_mnt_basenode_rel.txt"),"w+")
  
• try:
  
• self.__retrieveIndViewData("Nodes")
  
• self.__retrieveIndViewData("Views")
  
• self.__retrieveIndViewData("NodeViews")
  
• self.__retrieveIndViewData("NodesRel")
  
• 
  
• self.__write(self.__hNodes,"Nodes")
  
• self.__write(self.__hViews,"Views")
  
• self.__write(self.__hNodeViews,"NodeViews")
  
• self.__write(self.__hNodesRel,"NodesRel")
  
• finally:
  
• self.__hViews.close()
  
• self.__hNodes.close()
  
• self.__hNodeViews.close()
  
• self.__hNodesRel.close()
  
• #enddef
  
• 
  
• def__write(self,fileHandle,outputDataName):
  
• ifnotfileHandle:
  
• stderr.write("Invalidfilehandlecorrespondingto%s"%outputDataName)
  
• return
  
• fileHandle.write(self.__outputData[outputDataName.strip("")].encode("GB2312"))
  
• printfileHandle.name
  
• 
  
• def__retrieveIndViewData(self,whoMapKeyName):
  
• self.__getNodes(self.__root,whoMap[whoMapKeyName])
  
• self.__clearNodesList()
  
• 
  
• def__clearNodesList(self):
  
• self.__gNodesList=[]
  
• 
  
• def__getNodePaths(self,ANode,isDynNode=True,initPath=""):
  
• """
  
• retrievesthevalueofstringofstaticnodesordynamicnodes
  
• excluededleaf-nodes.
  
• """
  
• if(notANode)or(notANode.hasChildNodes()):
  
• returninitPath
  
• 
  
• ifinitPath.strip("")=="":
  
• initPath="/%s"%ANode.attributes["id"].value.strip("")
  
• 
  
• foreleminANode.childNodes:
  
• if(notelem.localName)or(notelem.hasChildNodes()):
  
• continue
  
• 
  
• idPath=""
  
• ifisDynNodeandelem.hasAttribute("value"):
  
• idPath="%s/%s"%(initPath,elem.attributes["value"].value.strip(""))
  
• else:
  
• idPath="%s/%s"%(initPath,elem.attributes["id"].value.strip(""))
  
• 
  
• printidPath
  
• self.__getNodePaths(elem,isDynNode,idPath)
  
• #endfor
  
• #enddef
  
• 
  
• def__getNodeType(self,ANode):
  
• ret=nodeTypMap["LEAF"]
  
• ifANode.hasChildNodes():
  
• ret=nodeTypMap["NODE"]
  
• returnret
  
• #enddef
  
• 
  
• def__outputNodes(self,ANode):
  
• """
  
• generatestherecordsofuniquenodesinXML
  
• """
  
• ifnotANode:
  
• return
  
• 
  
• nodeType=self.__getNodeType(ANode)
  
• dataType=dataTypMap["void"]
  
• ifnodeType==nodeTypMap["LEAF"]andANode.hasAttribute("value"):
  
• dataValue=ANode.attributes["value"].value.strip("")
  
• ifdataValue.isdigit():
  
• dataType=dataTypMap["integer"]
  
• else:
  
• try:
  
• float(dataValue)
  
• dataType=dataTypMap["float"]
  
• except:
  
• dataType=dataTypMap["string"]
  
• 
  
• dispName=ANode.attributes["id"].value.strip("")
  
• ifANode.hasAttribute("dispName"):
  
• dispName=ANode.attributes["dispName"].value.strip("")/
  
• .encode("ISO8859").decode("GB2312")
  
• 
  
• ProcType=0
  
• PrstType=1
  
• UnitName=''
  
• initValue='0'
  
• updateTime=''
  
• self.__outputData["Nodes"]+="%s|%s|%s|%s|%s|%s|%s|%s|%s|%s|%s|/n"%/
  
• (ANode.attributes["id"].value.strip(""),
  
• dispName,dispName,nodeImgMap[nodeType],
  
• nodeType,dataType,ProcType,PrstType,
  
• UnitName,initValue,updateTime)
  
• #enddef
  
• 
  
• def__outputViews(self,ANode):
  
• """
  
• generatestherecordsofviews.
  
• """
  
• if(notANode)or(self.__getNodeType(ANode)!=nodeTypMap["NODE"]):
  
• return
  
• 
  
• nodeID=ANode.attributes["id"].value.strip("")
  
• viewName=nodeID
  
• ifANode.hasAttribute("dispName"):
  
• viewName=ANode.attributes["dispName"].value/
  
• .encode("ISO8859").decode("GB2312")
  
• 
  
• self.__outputData["Views"]+="%s|%s|%s|/n"%(nodeID,viewName,nodeID)
  
• 
  
• #enddef
  
• 
  
• def__outputNodeViews(self,ANode):
  
• ifnotANode:
  
• return
  
• 
  
• ifself.__getNodeType(ANode)==nodeTypMap["NODE"]:
  
• self.__outputData["NodeViews"]+=/
  
• "%s|%s|/n"%/
  
• (ANode.attributes["id"].value.strip(""),
  
• ANode.attributes["id"].value.strip(""))
  
• else:
  
• self.__outputData["NodeViews"]+=/
  
• "%s|%s|/n"%/
  
• (ANode.attributes["id"].value.strip(""),
  
• ANode.parentNode.attributes["id"].value.strip(""))
  
• #enddef
  
• 
  
• def__outputNodesRel(self,ANode):
  
• if(notANode)or(ANode.parentNode.nodeType==ANode.DOCUMENT_NODE):
  
• return
  
• 
  
• self.__outputData["NodesRel"]+="%s|%s|/n"%/
  
• (ANode.parentNode.attributes["id"].value.strip(""),
  
• ANode.attributes["id"].value.strip(""))
  
• #enddef
  
• 
  
• def__handleByType(self,ANode,Who):
  
• """
  
• Determinewhichkindofdatashouldbeoutput.
  
• """
  
• ifnotANode:
  
• return
  
• 
  
• ifWho==whoMap["Nodes"]:
  
• self.__outputNodes(ANode)
  
• elifWho==whoMap["Views"]:
  
• self.__outputViews(ANode)
  
• elifWho==whoMap["NodeViews"]:
  
• self.__outputNodeViews(ANode)
  
• elifWho==whoMap["NodesRel"]:
  
• self.__outputNodesRel(ANode)
  
• #enddef
  
• 
  
• def__getNodes(self,ANode,Who):
  
• """retrievesallstaticnodes"""
  
• ifnotANode:
  
• return
  
• 
  
• ifANode.parentNode.nodeType==ANode.DOCUMENT_NODE:
  
• self.__handleByType(ANode,Who)
  
• 
  
• foreleminANode.childNodes:
  
• ifnotelem.localName:
  
• continue
  
• 
  
• ifnotelem.hasAttribute("id"):
  
• stderr.write("Invalidtagwithoutanattributenamed'id'FOUND!")
  
• continue
  
• 
  
• tagID=elem.attributes["id"].value.strip("")
  
• try:
  
• self.__gNodesList.index(tagID)
  
• continue
  
• exceptValueError:
  
• #NOTFOUND
  
• self.__gNodesList.append(tagID)
  
• 
  
• self.__handleByType(elem,Who)
  
• self.__getNodes(elem,Who)
  
• #enddef
  
• #endclass
  
• 
  
• if__name__=="__main__":
  
• """
  
• CAUTION:PleasesetencodingbyISO8859inXMLhead!
  
• """
  
• ind=TIndicatorData(
  
• r"D:/Documents/Construction_Bank/SH/CCBSA/Design/ccbsa_ind21.xml",
  
• r"D:/Temp")
  
• ind.GenIndicators()
  
• print"/nMISSIONCOMPLETED."
  
• 
  
• 
  
• #ENDOFFILE.
  
•