Question

鉴于这一xml文档,我谨从中提取数据。然而,在<代码>和“LandmarkPointListXml>”上提取数据有困难;。

<>XML文档:

  <?xml version="1.0" encoding="utf-8"?>
  <Map xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema">
  <MapName>er</MapName>
  <MapURL>er.gif</MapURL>
  <Name>er</Name>
  <URL>er.gif</URL>
  <LandmarkPointListXml>
    <anyType xsi:type="LandmarkPointProperty">
      <LandmarkPointX>400</LandmarkPointX>
      <LandmarkPointY>292</LandmarkPointY>
      <LandmarkDesc>my room door</LandmarkDesc>
    </anyType>
    <anyType xsi:type="LandmarkPointProperty">
      <LandmarkPointX>399</LandmarkPointX>
      <LandmarkPointY>219</LandmarkPointY>
      <LandmarkDesc>bro room door</LandmarkDesc>
    </anyType>
  </LandmarkPointListXml>
  <RegionPointListXml />
</Map>

www.un.org/Depts/DGACM/index_spanish.htm 粉碎计划:

    def GetMapData(self):
        result = ""
        haha = self.XMLdoc.firstChild #root node
        for child in haha.childNodes:
            if (cmp(child.nodeName, LandmarkPointListXml )==0):
                result = result +  |  + self.loopLandmark(child.childNodes) +  | 
            else:
                result = result + child.firstChild.nodeValue +  , 
        return result

    def loopLandmark(self, landmarks):
        result=""
        haha=landmarks.getElementsByTagName( anyType )
        for child in haha.childNodes:
            if (cmp(haha.firstChild.nodeName, LandmarkPointX ) == 0):
                result=result+child.firstChild.nodeValue+ , 
                ChildNode = ChildNode.nextSibling
                result=result+child.firstChild.nodeValue+ , 
                ChildNode = ChildNode.nextSibling
                result=result+child.firstChild.nodeValue
        return result

我得以检索结果,即“er,er.gif,er,er.gif”,直到方案达到<LandmarkPointListXml>。

Answer 1

该法典非常脆弱。它对XML的投入作了有力的假设,如果对XML进行有效修改(如在......之后不立即修改),则会失败。

我建议使用一个标准图书馆,以划分XML,例如,Element 树木()或 lxml(<<<<<<<<>>><<<<<<<<<<>>>>>>><>>>>><<<<<<<<<<<<>>>>>><<<<<<<>>>>>>><<<<<<

下面的I m 书写法使用了Element 树,并用你的XML投入(我已将自己的论点移至母阶级)。它还容忍XML分子的空洞价值。

import xml.etree.ElementTree as ET

def GetMapData( xmlfile ):
    result = ""
    try:
        tree = ET.parse( xmlfile )
    except IOError, e:
        print "Failure Parsing %s: %s" % (xmlfile, e)
    root = tree.getroot() # root node
    for child in root:
        if ( child.tag ==  LandmarkPointListXml  ):
            result +=  |  + loopLandmark(child) +  | 
        elif child.text is not None:
            result += child.text +  , 
    return result

def loopLandmark( landmarks ):
    result=""
    for landmark in landmarks:
        if ( landmark.tag ==  anyType  ): # check also xsi:type="LandmarkPointProperty"?
            for child in landmark:
                if ( child.text and child.tag in [  LandmarkPointX ,  LandmarkPointY  ] ):
                    result += child.text +  , 
    return result

GetMapData(  xml.in  )

Answer 2

i 设法从公布的XML档案中提取数据。但认为,这比提供答案更简单。获取每项数据的通道。

import sys
import socket
import os
from xml.dom.minidom import Document, parse, parseString

class mapDataClass:

def __init__(self):
    self.XMLdoc = Document()
    self.MakeRootNode()

def MakeRootNode(self):
    self.RootNode = self.XMLdoc.createElement( Map )
    self.XMLdoc.appendChild(self.RootNode)

def GetXML_Doc(self):
    return self.XMLdoc

def LoadXMLFile(self, AbsFileName):
    try:
        self.XMLdoc.unlink()
        self.XMLdoc = parse(AbsFileName)
        if (self.XMLdoc.hasChildNodes()): #if not empty
            #Determine if root node <CalibrationData> exist
            if (cmp(self.XMLdoc.firstChild.nodeName,
                                 Map ) == 0):
                self.RootNode = self.XMLdoc.firstChild

        return True

    except IOError:
        print  File   + AbsFileName +   not found 
        return False

def GetMapData(self):
    result = ""
    haha = self.XMLdoc.firstChild #root node
    for child in haha.childNodes:
        if cmp(child.nodeName,  LandmarkPointListXml )==0:
            result1 = self.loopLandmark(child)
        elif cmp(child.nodeName,  RegionPointListXml )==0:
            print  Empty 
        elif cmp(child.nodeName,  URL )==0:
            result = result + child.firstChild.nodeValue
        else:
            result = result + child.firstChild.nodeValue +  , 
    result = result + "|" + result1 + "EMPTY"
    return result

def loopLandmark(self,landmarks):
    result2=""
    tempResult=""
    haha=landmarks.getElementsByTagName( anyType )
    for i in range(0, len(haha)):
        result2=self.loopAnyType(haha[i])
        if ((i+1)!=len(haha)):
            tempResult = tempResult + result2 +  ; 
        else:
            tempResult = tempResult + result2 +  | 
    return tempResult

def loopAnyType(self,anyType):
    result3=""
    haha1=anyType.getElementsByTagName( LandmarkPointX )[0]
    haha2=anyType.getElementsByTagName( LandmarkPointY )[0]
    haha3=anyType.getElementsByTagName( LandmarkDesc )[0]
    result3 = haha1.firstChild.nodeValue + "," + haha2.firstChild.nodeValue + "," + haha3.firstChild.nodeValue
    return result3

profile = mapDataClass()
boolean = profile.LoadXMLFile( uploader.m )
print boolean
result = profile.GetMapData()
print result

Answer 3

我先前的答复还不完整。这里应认为是right。

import sys
import socket
import os
from xml.dom.minidom import Document, parse, parseString, Node

class mapDataClass:

def __init__(self):
    self.XMLdoc = Document()
    self.MakeRootNode()

def MakeRootNode(self):
    self.RootNode = self.XMLdoc.createElement( Map )
    self.XMLdoc.appendChild(self.RootNode)

def GetXML_Doc(self):
    return self.XMLdoc

def LoadXMLFile(self, AbsFileName):
    try:
        self.XMLdoc.unlink()
        self.XMLdoc = parse(AbsFileName)
        if (self.XMLdoc.hasChildNodes()): #if not empty
            if (cmp(self.XMLdoc.firstChild.nodeName,
                                 Map ) == 0):
                self.RootNode = self.XMLdoc.firstChild

        return True

    except IOError:
        print  File   + AbsFileName +   not found 
        return False

def GetMapData(self):
    result = ""
    result1 = ""
    result2 = ""
    haha = self.XMLdoc.firstChild #root node
    for child in haha.childNodes:
        if child.nodeType == Node.ELEMENT_NODE:
            if cmp(child.nodeName,  LandmarkPointListXml )<>0 and cmp(child.nodeName,  RegionPointListXml )<>0:
                if cmp(child.nodeName,  URL )==0:
                    result = result + child.firstChild.nodeValue       
                else:
                    result = result + child.firstChild.nodeValue +  , 
            elif cmp(child.nodeName,  LandmarkPointListXml )==0:
                if child.firstChild is not None:
                    result1 = self.loopLandmark(child)
                else:
                    result1 =  EMPTY| 
            elif cmp(child.nodeName,  RegionPointListXml )==0:
                if child.firstChild is None:
                    result2 =   EMPTY 

    result = result + "|" + result1 + result2
    return result

def loopLandmark(self,landmarks):
    result2=""
    tempResult=""
    haha=landmarks.getElementsByTagName( anyType )
    for i in range(0, len(haha)):
        result2=self.loopAnyType(haha[i])
        if ((i+1)!=len(haha)):
            tempResult = tempResult + result2 +  ; 
        else:
            tempResult = tempResult + result2 +  | 
    return tempResult

def loopAnyType(self,anyType):
    result3=""
    haha1=anyType.getElementsByTagName( LandmarkPointX )[0]
    haha2=anyType.getElementsByTagName( LandmarkPointY )[0]
    haha3=anyType.getElementsByTagName( LandmarkDesc )[0]
    result3 = haha1.firstChild.nodeValue + "," + haha2.firstChild.nodeValue + "," + haha3.firstChild.nodeValue
    return result3

data = mapDataClass()
success = data.LoadXMLFile("uploadhomeTest.m")
if success:
    print "file loaded"
    print data.GetMapData()
else:
    print "no such file found"

友情链接