Python custom method for parsing simple XML format files

This article mainly introduces Python custom parsing simple XML format files, involving Python parsing XML file related skills, very practical value, the need for Friends can refer to:

Because the company's internal interface returns the string support 2 kinds of forms: PHP array, XML; results php array python can not be used directly, and XML string format is not standard, so also can not use the standard module parsing. "Non-standard place is the name of some node will be the beginning of the number", so write a simple step to parse the file, used to do interface testing.

?

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26-27--28 29---30 31--32 33 34 35 36 37 38-39 40 41 42 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71

#!/usr/bin/env python #encoding: utf-8 import re class xmlparse:def __init__ (Self, xmlstr): Self.xmlstr = Xmlstr SELF.XM Ldom = Self.__convet2utf8 () self.xmlnodelist = [] Self.xpath = ' def __convet2utf8 (self): Headstr = self.__get_head () XML Domstr = Self.xmlstr.replace (Headstr, ') if ' gbk ' in headstr:xmldomstr = Xmldomstr.decode (' GBK '). Encode (' utf-8 ') elif ' G b2312 ' 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:h Eadstr = Headregobj.group () return headstr Else:return ' Def parse (self, xpath): Self.xpath = XPath xpatlist = [] Xpatha rr = Self.xpath.split ('/') for xnode in xpatharr:if xnode:spcindex = Xnode.find (' [') if spcindex > -1:index = Int (xn ODE[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 xmlnodestr if ' __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

Run Result:

?

1 2 3 4 5 6 7 8 9

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_id get list: [' aaaaa ', ' bbbbb '] get string:aaaaa------------------------------XPath:/product_id[1] Get list: [ ' AAAAA ', ' bbbbb '] get string:bbbbb------------------------------XPath:/A/product_id get list: [' AAAAA '] get string:aaaaa

Because the XML format returned is simpler, there are no nodes with attributes, so it is easier to deal with them. But the test still found a bug. That is, when the same node is nested, there will be a positive match problem, which can be solved by avoiding the presence of nested nodes in XPath, otherwise, only complex mechanisms are rewritten.

I hope this article will help you with your Python programming.