Python custom parsing of simple xml format files, pythonxml

Python custom parsing of simple xml format files, pythonxml

This example describes how to customize python parsing simple xml format files. Share it with you for your reference. The specific analysis is as follows:

Because the strings returned by the Internal interface of the company support two forms: php array and xml; the php array python cannot be used directly, but the xml string format is not standard, therefore, standard module Parsing is not supported. [It is not standard that the names of some nodes start with numbers]. Therefore, write a simple step to parse the file for interface testing.

#!/usr/bin/env python#encoding: utf-8import reclass xmlparse:  def __init__(self, xmlstr):    self.xmlstr = xmlstr    self.xmldom = self.__convet2utf8()    self.xmlnodelist = []    self.xpath = ''  def __convet2utf8(self):    headstr = self.__get_head()    xmldomstr = self.xmlstr.replace(headstr, '')    if 'gbk' in headstr:       xmldomstr = xmldomstr.decode('gbk').encode('utf-8')    elif 'gb2312' in headstr:      xmldomstr = self.xmlstr.decode('gb2312').encode('utf-8')    return xmldomstr  def __get_head(self):    headpat = r'<\?xml.*\?>'    headpatobj = re.compile(headpat)    headregobj = headpatobj.match(self.xmlstr)    if headregobj:      headstr = headregobj.group()      return headstr    else:      return ''  def parse(self, xpath):    self.xpath = xpath    xpatlist = []    xpatharr = self.xpath.split('/')    for xnode in xpatharr:      if xnode:        spcindex = xnode.find('[')        if spcindex > -1:          index = int(xnode[spcindex+1:-1])          xnode = xnode[:spcindex]        else:          index = 0;        temppat = ('<%s>(.*?)</%s>' % (xnode, xnode),index)        xpatlist.append(temppat)    xmlnodestr = self.xmldom    for xpat,index in xpatlist:      xmlnodelist = re.findall(xpat,xmlnodestr)      xmlnodestr = xmlnodelist[index]      if xmlnodestr.startswith(r'<![CDATA['):        xmlnodestr = xmlnodestr.replace(r'<![CDATA[','')[:-3]    self.xmlnodelist = xmlnodelist    return xmlnodestrif '__main__' == __name__:  xmlstr = '<?xml version="1.0" encoding="utf-8" standalone="yes" ?><resultObject><a><product_id>aaaaa</product_id><product_name><![CDATA[bbbbb]]></a><b><product_id>bbbbb</product_id><product_name><![CDATA[bbbbb]]></b></product_name></resultObject>'  xpath1 = '/product_id'  xpath2 = '/product_id[1]'  xpath3 = '/a/product_id'  xp = xmlparse(xmlstr)  print 'xmlstr:',xp.xmlstr  print 'xmldom:',xp.xmldom  print '------------------------------'  getstr = xp.parse(xpath1)  print 'xpath:',xp.xpath  print 'get list:',xp.xmlnodelist  print 'get string:', getstr  print '------------------------------'  getstr = xp.parse(xpath2)  print 'xpath:',xp.xpath  print 'get list:',xp.xmlnodelist  print 'get string:', getstr  print '------------------------------'  getstr = xp.parse(xpath3)  print 'xpath:',xp.xpath  print 'get list:',xp.xmlnodelist  print 'get string:', getstr

Running result:

xmlstr: <?xml version="1.0" encoding="utf-8" standalone="yes" ?><resultObject><a><product_id>aaaaa</product_id><product_name><![CDATA[bbbbb]]></a><b><product_id>bbbbb</product_id><product_name><![CDATA[bbbbb]]></b></product_name></resultObject>xmldom: <resultObject><a><product_id>aaaaa</product_id><product_name><![CDATA[bbbbb]]></a><b><product_id>bbbbb</product_id><product_name><![CDATA[bbbbb]]></b></product_name></resultObject>------------------------------xpath: /product_idget list: ['aaaaa', 'bbbbb']get string: aaaaa------------------------------xpath: /product_id[1] get list: ['aaaaa', 'bbbbb']get string: bbbbb------------------------------xpath: /a/product_idget list: ['aaaaa']get string: aaaaa

Because the returned xml format is relatively simple and there are no nodes with attributes, it is easier to process. However, the test still found a bug. That is, when the same node is nested, a regular expression matching problem occurs. This problem can be solved by avoiding the nested node name in xpath. Otherwise, only a complicated rewrite mechanism is required.

I hope this article will help you with Python programming.