用Python去解析XML报文 V1.1

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。

1. 1. <?xmlversion="1.0"encoding="iso8859-1"?>
   2. <viewid="CCBSA_v"msgType="1">
   3. <viewElemid="jrcfwq"dispName="集群">
   4. <viewElemid="fwqsl"dispName="服务器数量"value="1"/>
   5. <viewElemid="Master"dispName="主控节点"value="STAR"/>
   6. <viewElemid="Server">
   7. <viewElemid="SrvName"value="01"dispName="STAR">
   8. <viewElemid="Plat"dispName="平台信息">
   9. <viewElemid="PlatStat"dispName="平台状态">
   10. <viewElemid="MchPort"dispName="机器端口"value="12000"/>
   11. <viewElemid="MchState"dispName="机器状态"value="在线"/>
   12. <viewElemid="AllProc"dispName="总进程数"value="0"/>
   13. <viewElemid="EslProc"dispName="平台进程数"value="29"/>
   14. <viewElemid="SemNum"dispName="信号灯数"value="104"/>
   15. <viewElemid="DrqSem"dispName="DRQ使用信号灯"value="53"/>
   16. </viewElem>
   17. <viewElemid="CpuStat"dispName="CPU状态">
   18. <viewElemid="CpuIdle"dispName="idle"value="0"/>
   19. <viewElemid="CpuUser"dispName="user"value="0"/>
   20. <viewElemid="CpuNice"dispName="nice"value="0"/>
   21. <viewElemid="CpuSys"dispName="sys"value="0"/>
   22. <viewElemid="CpuWio"dispName="wio"value="0"/>
   23. </viewElem>
   24. <viewElemid="SysInfo"dispName="操作系统信息">
   25. <viewElemid="CpuNum"dispName="CPU颗数"value="0"/>
   26. <viewElemid="PhyMem"dispName="物理内存(K)"value="0"/>
   27. <viewElemid="VirtMem"dispName="虚拟内存(K)"value="0"/>
   28. <viewElemid="UsedMem"dispName="已用内存(K)"value="0"/>
   29. <viewElemid="exit_freeMem"dispName="可用内存(K)"value="0"/>
   30. <viewElemid="IFaceNum"dispName="网络接口数"value="0"/>
   31. </viewElem>
   32. <viewElemid="ProjInfo"dispName="项目信息">
   33. <viewElemid="ShmSize"dispName="部署共享内存大小(k)"value="15251168"/>
   34. <viewElemid="ShmKeep"dispName="部署共享内存剩余(k)"value="16769072"/>
   35. <viewElemid="BcbSize"dispName="交换共享内存大小(k)"value="6304"/>
   36. <viewElemid="BcbUsed"dispName="已用交换共享内存(k)"value="2208"/>
   37. <viewElemid="BcbMax"dispName="最大交换共享内存(k)"value="70816"/>
   38. <viewElemid="ChkNum"dispName="当前已用缓冲区段数"value="1"/>
   39. <viewElemid="DrqMsg"dispName="缓存消息数"value="0"/>
   40. <viewElemid="MsqNum"dispName="队列中的消息数"value="0"/>
   41. <viewElemid="TranNum"dispName="本机交易统计"value="322047"/>
   42. <viewElemid="DTAMPID"dispName="DTA管理服务进程号"value="3727372"/>
   43. <viewElemid="RCYCLPID"dispName="垃圾回收服务进程号"value="3739830"/>
   44. <viewElemid="SYNCPID"dispName="多机同步服务进程号"value="3670122"/>
   45. <viewElemid="ISSUEPID"dispName="多机发布服务进程号"value="2871348"/>
   46. <viewElemid="MACHSVRPID"dispName="多机交换服务进程号"value="0"/>
   47. <viewElemid="MONCPID"dispName="多机监控同步服务进程号"value="0"/>
   48. <viewElemid="MONSPID"dispName="多机监控发布服务进程号"value="0"/>
   49. <viewElemid="DTANUM"dispName="适配器个数"value="12"/>
   50. ....
   51. ....
   52. ......

1. fromxml.domimportminidom
2. fromsysimportstderr
3. fromos.pathimportjoin
5. __version__="V1.1"
7. """
8. Definitionfortypesandmaps
9. """
10. dataTypMap={"integer":0,"foat":1,"boolean":2,
11. "char":3,"string":4,"void":5,"double":6,
12. "long":7,"object":8,"datetime":9}
13. nodeTypMap={"LEAF":0,"NODE":2}
14. nodeImgMap={nodeTypMap["LEAF"]:"/images/leaf.gif",
15. nodeTypMap["NODE"]:"/images/node.gif"}
16. whoMap={"Views":0,"Nodes":1,
17. "NodeViews":2,"NodesRel":3}
19. classTIndicatorData:
21. def__init__(self,XML,dest):
22. self.__xmldoc=minidom.parse(XML.strip(""))
23. self.__root=self.__xmldoc.documentElement
24. self.__destPath=dest.strip("")
25. self.__gNodesList=[]#Storinguniquenodes
26. self.__hViews=None#Filehandleforisac_mnt_view
27. self.__hNodes=None#Filehandleforisac_mnt_basenode
28. self.__hNodeViews=None#Filehandleforisac_mnt_basenode_view
29. self.__hNodesRel=None#Filehandleforisac_mnt_basenode_rel
30. self.__outputData={"Views":"","Nodes":"","NodeViews":"","NodesRel":""}
31. #enddef
33. defGenIndicators(self):
34. self.__hViews=open(join(self.__destPath,"isac_mnt_view.txt"),"w+")
35. self.__hNodes=open(join(self.__destPath,"isac_mnt_basenode.txt"),"w+")
36. self.__hNodeViews=open(join(self.__destPath,"isac_mnt_basenode_view.txt"),"w+")
37. self.__hNodesRel=open(join(self.__destPath,"isac_mnt_basenode_rel.txt"),"w+")
38. try:
39. self.__retrieveIndViewData("Nodes")
40. self.__retrieveIndViewData("Views")
41. self.__retrieveIndViewData("NodeViews")
42. self.__retrieveIndViewData("NodesRel")
44. self.__write(self.__hNodes,"Nodes")
45. self.__write(self.__hViews,"Views")
46. self.__write(self.__hNodeViews,"NodeViews")
47. self.__write(self.__hNodesRel,"NodesRel")
48. finally:
49. self.__hViews.close()
50. self.__hNodes.close()
51. self.__hNodeViews.close()
52. self.__hNodesRel.close()
53. #enddef
55. def__write(self,fileHandle,outputDataName):
56. ifnotfileHandle:
57. stderr.write("Invalidfilehandlecorrespondingto%s"%outputDataName)
58. return
59. fileHandle.write(self.__outputData[outputDataName.strip("")].encode("GB2312"))
60. printfileHandle.name
62. def__retrieveIndViewData(self,whoMapKeyName):
63. self.__getNodes(self.__root,whoMap[whoMapKeyName])
64. self.__clearNodesList()
66. def__clearNodesList(self):
67. self.__gNodesList=[]
69. def__getNodePaths(self,ANode,isDynNode=True,initPath=""):
70. """
71. retrievesthevalueofstringofstaticnodesordynamicnodes
72. excluededleaf-nodes.
73. """
74. if(notANode)or(notANode.hasChildNodes()):
75. returninitPath
77. ifinitPath.strip("")=="":
78. initPath="/%s"%ANode.attributes["id"].value.strip("")
80. foreleminANode.childNodes:
81. if(notelem.localName)or(notelem.hasChildNodes()):
82. continue
84. idPath=""
85. ifisDynNodeandelem.hasAttribute("value"):
86. idPath="%s/%s"%(initPath,elem.attributes["value"].value.strip(""))
87. else:
88. idPath="%s/%s"%(initPath,elem.attributes["id"].value.strip(""))
90. printidPath
91. self.__getNodePaths(elem,isDynNode,idPath)
92. #endfor
93. #enddef
95. def__getNodeType(self,ANode):
96. ret=nodeTypMap["LEAF"]
97. ifANode.hasChildNodes():
98. ret=nodeTypMap["NODE"]
99. returnret
100. #enddef
102. def__outputNodes(self,ANode):
103. """
104. generatestherecordsofuniquenodesinXML
105. """
106. ifnotANode:
107. return
109. nodeType=self.__getNodeType(ANode)
110. dataType=dataTypMap["void"]
111. ifnodeType==nodeTypMap["LEAF"]andANode.hasAttribute("value"):
112. dataValue=ANode.attributes["value"].value.strip("")
113. ifdataValue.isdigit():
114. dataType=dataTypMap["integer"]
115. else:
116. try:
117. float(dataValue)
118. dataType=dataTypMap["float"]
119. except:
120. dataType=dataTypMap["string"]
122. dispName=ANode.attributes["id"].value.strip("")
123. ifANode.hasAttribute("dispName"):
124. dispName=ANode.attributes["dispName"].value.strip("")/
125. .encode("ISO8859").decode("GB2312")
127. ProcType=0
128. PrstType=1
129. UnitName=''
130. initValue='0'
131. updateTime=''
132. self.__outputData["Nodes"]+="%s|%s|%s|%s|%s|%s|%s|%s|%s|%s|%s|/n"%/
133. (ANode.attributes["id"].value.strip(""),
134. dispName,dispName,nodeImgMap[nodeType],
135. nodeType,dataType,ProcType,PrstType,
136. UnitName,initValue,updateTime)
137. #enddef
139. def__outputViews(self,ANode):
140. """
141. generatestherecordsofviews.
142. """
143. if(notANode)or(self.__getNodeType(ANode)!=nodeTypMap["NODE"]):
144. return
146. nodeID=ANode.attributes["id"].value.strip("")
147. viewName=nodeID
148. ifANode.hasAttribute("dispName"):
149. viewName=ANode.attributes["dispName"].value/
150. .encode("ISO8859").decode("GB2312")
152. self.__outputData["Views"]+="%s|%s|%s|/n"%(nodeID,viewName,nodeID)
154. #enddef
156. def__outputNodeViews(self,ANode):
157. ifnotANode:
158. return
160. ifself.__getNodeType(ANode)==nodeTypMap["NODE"]:
161. self.__outputData["NodeViews"]+=/
162. "%s|%s|/n"%/
163. (ANode.attributes["id"].value.strip(""),
164. ANode.attributes["id"].value.strip(""))
165. else:
166. self.__outputData["NodeViews"]+=/
167. "%s|%s|/n"%/
168. (ANode.attributes["id"].value.strip(""),
169. ANode.parentNode.attributes["id"].value.strip(""))
170. #enddef
172. def__outputNodesRel(self,ANode):
173. if(notANode)or(ANode.parentNode.nodeType==ANode.DOCUMENT_NODE):
174. return
176. self.__outputData["NodesRel"]+="%s|%s|/n"%/
177. (ANode.parentNode.attributes["id"].value.strip(""),
178. ANode.attributes["id"].value.strip(""))
179. #enddef
181. def__handleByType(self,ANode,Who):
182. """
183. Determinewhichkindofdatashouldbeoutput.
184. """
185. ifnotANode:
186. return
188. ifWho==whoMap["Nodes"]:
189. self.__outputNodes(ANode)
190. elifWho==whoMap["Views"]:
191. self.__outputViews(ANode)
192. elifWho==whoMap["NodeViews"]:
193. self.__outputNodeViews(ANode)
194. elifWho==whoMap["NodesRel"]:
195. self.__outputNodesRel(ANode)
196. #enddef
198. def__getNodes(self,ANode,Who):
199. """retrievesallstaticnodes"""
200. ifnotANode:
201. return
203. ifANode.parentNode.nodeType==ANode.DOCUMENT_NODE:
204. self.__handleByType(ANode,Who)
206. foreleminANode.childNodes:
207. ifnotelem.localName:
208. continue
210. ifnotelem.hasAttribute("id"):
211. stderr.write("Invalidtagwithoutanattributenamed'id'FOUND!")
212. continue
214. tagID=elem.attributes["id"].value.strip("")
215. try:
216. self.__gNodesList.index(tagID)
217. continue
218. exceptValueError:
219. #NOTFOUND
220. self.__gNodesList.append(tagID)
222. self.__handleByType(elem,Who)
223. self.__getNodes(elem,Who)
224. #enddef
225. #endclass
227. if__name__=="__main__":
228. """
229. CAUTION:PleasesetencodingbyISO8859inXMLhead!
230. """
231. ind=TIndicatorData(
232. r"D:/Documents/Construction_Bank/SH/CCBSA/Design/ccbsa_ind21.xml",
233. r"D:/Temp")
234. ind.GenIndicators()
235. print"/nMISSIONCOMPLETED."
238. #ENDOFFILE.