python – 搜索/替换xml的内容

import os,sys,glob,xml.etree.ElementTree as ET
path = r"G:63D RRC GIS Datametadatageneral2010_contract"
for fn in os.listdir(path):
    filepaths = glob.glob(path + os.sep + fn + os.sep + "*overall.xml")
    for filepath in filepaths:
        (pa,filename) = os.path.split(filepath)
        ####use this section to grab element text from old,archived metadata files; this text then gets put into current,working .xml###
        root = ET.parse(pa + os.sep + "archive" + os.sep + "base_metadata_overall.xml").getroot()

        iterator = root.getiterator()
        for item in iterator:
            if item.tag == "abstract":
                correct_abstract = item.text

        root2 = ET.parse(pa + os.sep + "base_metadata_overall.xml").getroot()

        iterator2 = root2.getiterator("descript")
        for item in iterator2:
            if item.tag == "abstract":
                old_abstract = item.find("abstract")
                old_abstract_text = old_abstract.text
                item.remove(old_abstract)
                new_symbol_abstract = ET.SubElement(item,"title")
                new_symbol_abstract.text = correct_abstract                
        tree = ET.ElementTree(root2)
        tree.write(pa + os.sep + "base_metadata_overall.xml")
        print "created --- " + filename + " metadata"

但现在,我需要：

1)搜索xml并抓取“attr”标签之间的所有内容,下面是示例：

<attr><attrlabl Sync="TRUE">OBJECTID</attrlabl><attalias Sync="TRUE">ObjectIdentifier</attalias><attrtype Sync="TRUE">OID</attrtype><attwidth Sync="TRUE">4</attwidth><atprecis Sync="TRUE">0</atprecis><attscale Sync="TRUE">0</attscale><attrdef Sync="TRUE">Internal feature number.</attrdef></attr>

2)现在,我需要打开一个不同的xml并搜索相同“attr”标记之间的所有内容,并替换为上面的内容.

基本上,我之前在做什么,但忽略了“attr”标签之间的子元素,属性等等,并将其视为文本.

谢谢！！

请耐心等待,这个论坛有点不同(发帖)然后我习惯了！

这是我到目前为止所拥有的：

import os,re,xml.etree.ElementTree as ET
from lxml import etree

path = r"C:temppythonxml"
for fn in os.listdir(path):
    filepaths = glob.glob(path + os.sep + fn + os.sep +  "*overall.xml")
    for filepath in filepaths:
            (pa,filename) = os.path.split(filepath)

            xml = open(pa + os.sep + "attributes.xml")
            xmltext = xml.read()
            correct_attrs = re.findall("<attr> (.*?)</attr>",xmltext,re.DOTALL)
            for item in correct_attrs:
                correct_attribute = "<attr>" + item + "</attr>"

                xml2 = open(pa + os.sep + "base_metadata_overall.xml")
                xmltext2 = xml2.read()
                old_attrs = re.findall("<attr>(.*?)</attr>",re.DOTALL)
                for item2 in old_attrs:
                    old_attribute = "<attr>" + item + "</attr>"               



                    old = etree.fromstring(old_attribute)
                    replacement = new.xpath('//attr')
                    for attr in old.xpath('//attr'):
                        attr.getparent().replace(attr,copy.deepcopy(replacement))
                        print lxml.etree.tostring(old)

得到这个工作,见下文,甚至想出如何导出到新的.xml
但是,如果attr的数量是不同的.从源到dest,我得到以下错误,有什么建议吗？

node = replacements.pop()

IndexError：从空列表中弹出

import os,copy,lxml,xml.etree.ElementTree as ET
from lxml import etree
path = r"C:temppythonxml"
for fn in os.listdir(path):
filepaths = glob.glob(path + os.sep + fn + os.sep + "*overall.xml")
for filepath in filepaths:
        xmlatributes = open(pa + os.sep + "attributes.xml")
        xmlatributes_txt = xmlatributes.read()
        xmltarget = open(pa + os.sep + "base_metadata_overall.xml")
        xmltarget_txt = xmltarget.read()
        source = lxml.etree.fromstring(xmlatributes_txt)
        dest = lxml.etree.fromstring(xmltarget_txt)            




        replacements = source.xpath('//attr')
        replacements.reverse()


        for attr in dest.xpath('//attr'):
            node = replacements.pop()
            attr.getparent().replace(attr,copy.deepcopy(node))
        #print lxml.etree.tostring(dest)
        tree = ET.ElementTree(dest)
        tree.write (pa + os.sep + "edited_metadata.xml")
        print fn + "--- sucessfully edited"

更新5/16/2011
重组了一些东西来修复上面提到的“IndexError：pop from empty list”错误.意识到更换“attr”标签并不总是一对一的替代品.对于前者有时源.xml有20个attr’s,目的地.xml有25个attr’s.在这种情况下,1比1的替换会窒息.

无论如何,下面将删除所有attr,然后替换源attr’s.它还检查另一个标签,“子类型”(如果存在),它在attr之后添加它们,但在“详细”标签内.

再次感谢所有帮助过的人.

import os,xml.etree.ElementTree as ET
from lxml import etree
path = r"G:63D RRC GIS Datametadatageneral2010_contract"
#path = r"C:temppythonxml"
for fn in os.listdir(path):
    correct_title = fn.replace ('_',' ') + " various facilities"
    correct_fc_name = fn.replace ('_',' ')
    filepaths = glob.glob(path + os.sep + fn + os.sep + "*overall.xml")
    for filepath in filepaths:
        print "-----" + fn + "-----"
        (pa,filename) = os.path.split(filepath)
        xmlatributes = open(pa + os.sep + "attributes.xml")
        xmlatributes_txt = xmlatributes.read()
        xmltarget = open(pa + os.sep + "base_metadata_overall.xml")
        xmltarget_txt = xmltarget.read()
        source = lxml.etree.fromstring(xmlatributes_txt)
        dest = lxml.etree.fromstring(xmltarget_txt)
        replacements = source.xpath('//attr')
        replacesubtypes = source.xpath('//subtype')
        subtype_true_f = len(replacesubtypes)

        attrtag = dest.xpath('//attr')
        #print len(attrtag)
        num_realatrs = len(replacements)
        for n in attrtag:
            n.getparent().remove(n)
        print n.tag + " removed"

        detailedtag = dest.xpath('//detailed')
        for n2 in detailedtag:
            pos = 0
            for realatrs in replacements:
                n2.insert(pos + 1,realatrs)
            print "attr's replaced"
            if subtype_true_f >= 1:
                #print subtype_true_f
                for realsubtypes in replacesubtypes:
                   n2.insert(num_realatrs + 1,realsubtypes)
                print "subtype's replaced"

        tree = ET.ElementTree(dest)
        tree.write (pa + os.sep + "base_metadata_overall_v2.xml")
        print fn + "--- sucessfully edited"