2

我试图在使用的文件名有时只是完整文件名的一部分的目录中查找文件。

所以

check_meta=os.listdir(currentPath)

trc_boundary_Polygon.prj'、'trc_boundary_Polygon.sbn'、'trc_boundary_Polygon.sbx'、'trc_boundary_Polygon.shp'、'trc_boundary_Polygon.shp.ATGIS29.1772.3444.sr.lock'、'trc_boundary_Polygon.shx'、'trc_boundary_gon.' Urbanlevy_bdy_region.dbf'、'Urbanlevy_bdy_region.prj'、'Urbanlevy_bdy_region.shp'、'Urbanlevy_bdy_region.shp.xml'、'Urbanlevy_bdy_region.shx'、'Urbanlevy_bdy_trc.dbf'、'Urbanlevy_bdy_trc。prj','Urbanlevy_bdy_trc.sbn','Urbanlevy_bdy_trc.sbx','Urbanlevy_bdy_trc.shp','Urbanlevy_bdy_trc.shp.xml','Urbanlevy_bdy_trc.shx'] trc_boundary_Polygon.shp.ATGIS29.1772.3444.sr.lock','trc_boundary_Polygon.shx','trc_boundary_polygon.xml','Urbanlevy_bdy_region.dbf','Urbanlevy_bdy_region.prj','Urbanlevy_bdy_region.shp','Urbanlevy_bdy.xml' ,'Urbanlevy_bdy_region.shx','Urbanlevy_bdy_trc.dbf','Urbanlevy_bdy_trc。prj','Urbanlevy_bdy_trc.sbn','Urbanlevy_bdy_trc.sbx','Urbanlevy_bdy_trc.shp','Urbanlevy_bdy_trc.shp.xml','Urbanlevy_bdy_trc.shx'] trc_boundary_Polygon.shp.ATGIS29.1772.3444.sr.lock','trc_boundary_Polygon.shx','trc_boundary_polygon.xml','Urbanlevy_bdy_region.dbf','Urbanlevy_bdy_region.prj','Urbanlevy_bdy_region.shp','Urbanlevy_bdy.xml' ,'Urbanlevy_bdy_region.shx','Urbanlevy_bdy_trc.dbf','Urbanlevy_bdy_trc。prj','Urbanlevy_bdy_trc.sbn','Urbanlevy_bdy_trc.sbx','Urbanlevy_bdy_trc.shp','Urbanlevy_bdy_trc.shp.xml','Urbanlevy_bdy_trc.shx'] shx','Urbanlevy_bdy_trc.dbf','Urbanlevy_bdy_trc。prj','Urbanlevy_bdy_trc.sbn','Urbanlevy_bdy_trc.sbx','Urbanlevy_bdy_trc.shp','Urbanlevy_bdy_trc.shp.xml','Urbanlevy_bdy_trc.shx'] shx','Urbanlevy_bdy_trc.dbf','Urbanlevy_bdy_trc。prj','Urbanlevy_bdy_trc.sbn','Urbanlevy_bdy_trc.sbx','Urbanlevy_bdy_trc.shp','Urbanlevy_bdy_trc.shp.xml','Urbanlevy_bdy_trc.shx']

我想要

existingXML=FileNm[:FileNm.find('.')]
if  existingXML+"*"+'.xml' in check_meta: # this is where the issue is
   print "exists"

所以有时要使用的 xml 是 Urbanlevy_bdy_trc.shp.xml 而在其他情况下是 Urbanlevy_bdy_trc.xml (以存在者为准 - 请注意,不要简单地对“.shp.xml”使用 OR 函数,因为有多个文件扩展名,如选项卡, ecw 等数据集将具有)。有时,相关的 xml 文件可能称为 Urbanlevy_bdy_trc_Metadata.shp.xml,所以关键是搜索核心文件名“Urbanlevy_bdy_trc”,扩展名为 .xml

我该如何指定?Search and replace multiple lines in xml/text files using python

完整代码

import os, xml, arcpy, shutil, datetime
from xml.etree import ElementTree as et 

path=os.getcwd()
RootDirectory=path
arcpy.env.workspace = path
Count=0

Generated_XMLs=RootDirectory+'\GeneratedXML_LOG.txt'
f = open(Generated_XMLs, 'a')
f.write("Log of Metadata Creation Process - Update: "+str(datetime.datetime.now())+"\n")
f.close()

for root, dirs, files in os.walk(RootDirectory, topdown=False):
    #print root, dirs
    for directory in dirs:
        currentPath=os.path.join(root,directory)
        os.chdir(currentPath)
        arcpy.env.workspace = currentPath
        print currentPath
#def Create_xml(currentPath):

        FileList = arcpy.ListFeatureClasses()
        zone="_Zone"

        for File in FileList:
            Count+=1
            FileDesc_obj = arcpy.Describe(File)
            FileNm=FileDesc_obj.file
            print FileNm

            check_meta=os.listdir(currentPath)
            existingXML=FileNm[:FileNm.find('.')]
            print "XML: "+existingXML
            print check_meta
            #if  existingXML+'.xml' in check_meta:
            if any(f.startswith(existingXML) and f.endswith('.xml') for f in check_meta):
                print "exists"
                newMetaFile=FileNm+"_2012Metadata.xml"
                shutil.copy2(FileNm+'.xml', newMetaFile)
            else:
                print "Does not exist"
                newMetaFile=FileNm+"_BaseMetadata.xml"
                shutil.copy2('L:\Data_Admin\QA\Metadata_python_toolset\Master_Metadata.xml', newMetaFile)
            tree=et.parse(newMetaFile)

            print "Processing: "+str(File)

            for node in tree.findall('.//title'):
                node.text = str(FileNm)
            for node in tree.findall('.//northbc'):
                node.text = str(FileDesc_obj.extent.YMax)
            for node in tree.findall('.//southbc'):
                node.text = str(FileDesc_obj.extent.YMin)
            for node in tree.findall('.//westbc'):
                node.text = str(FileDesc_obj.extent.XMin)
            for node in tree.findall('.//eastbc'):
                node.text = str(FileDesc_obj.extent.XMax)        
            for node in tree.findall('.//native/nondig/formname'):
                node.text = str(os.getcwd()+"\\"+File)
            for node in tree.findall('.//native/digform/formname'):
                node.text = str(FileDesc_obj.featureType)
            for node in tree.findall('.//avlform/nondig/formname'):
                node.text = str(FileDesc_obj.extension)
            for node in tree.findall('.//avlform/digform/formname'):
                node.text = str(float(os.path.getsize(File))/int(1024))+" KB"
            for node in tree.findall('.//theme'):
                node.text = str(FileDesc_obj.spatialReference.name +" ; EPSG: "+str(FileDesc_obj.spatialReference.factoryCode))
            print node.text
            projection_info=[]
            Zone=FileDesc_obj.spatialReference.name

            if "GCS" in str(FileDesc_obj.spatialReference.name):
                projection_info=[FileDesc_obj.spatialReference.GCSName, FileDesc_obj.spatialReference.angularUnitName, FileDesc_obj.spatialReference.datumName, FileDesc_obj.spatialReference.spheroidName]
                print "Geographic Coordinate system"
            else:
                projection_info=[FileDesc_obj.spatialReference.datumName, FileDesc_obj.spatialReference.spheroidName, FileDesc_obj.spatialReference.angularUnitName, Zone[Zone.rfind(zone)-3:]]
                print "Projected Coordinate system"
            x=0
            for node in tree.findall('.//spdom'):
                for node2 in node.findall('.//keyword'):
                    print node2.text
                    node2.text = str(projection_info[x])
                    print node2.text
                    x=x+1


            tree.write(newMetaFile)

            f = open(Generated_XMLs, 'a')
            f.write(str(Count)+": "+File+"; "+newMetaFile+"; "+currentPath+"\n")
            f.close()



    #        Create_xml(currentPath)

结果

4

3 回答 3

1

为什么不直接使用:

searchtext = "sometext"
matching = [ f for f in os.listdir(currentPath) if f.startswith(searchtext) and ".xml" in f]

如果你想检查不同的扩展,你可以列出它们。

exts = (".xml", ".tab", ".shp")
matching = [ f for f in os.listdir(currentPath) if f.startswith(searchtext) and os.path.splitext(f)[-1] in exts]

当然,您也可以找出正则表达式来做同样的事情。

于 2012-01-31T04:29:00.757 回答
0

尝试以下操作:

if any(f.startswith(existingXML) and f.endswith('.xml') for f in check_meta):
   print "exists"

any()内置函数将可迭代对象作为参数,如果任何元素为真,则返回真。我们传递的参数是一个生成器表达式,它将为列表中f.startswith(existingXML) and f.endswith('.xml')的每个文件生成值。fcheck_meta

正则表达式解决方案可能如下所示:

regex = re.compile(re.escape(existingXML) + '.*\.xml$')
if any(regex.match(f) for f in check_meta):
    print "exists"

如果您需要知道哪个条目实际匹配,请改用 for 循环:

for f in check_meta:
    if f.startswith(existingXML) and f.endswith('.xml'):
        print "exists, file name:", f
于 2012-01-31T04:40:21.713 回答
0
import fnmatch, posixpath

existingXML   = posixpath.splitext(FileNm)[-1]
matchingFiles = fnmatch.filter(check_meta, existingXML + "*" + ".xml")

if not matchingFiles:
    raise IOError("no matching XML files")
elif len(matchingFiles) > 1:
    print "more than one matching file, using first"
    matchingFile = matchingFiles[0]
else:   # only one was found, just use it
    matchingFile = matchingFiles[0]
于 2012-01-31T07:17:03.507 回答