从CZI图像数据解析XML

Question

我有以下XML文件，我想在其中提取关键字的值：信息|图像| S |场景|形状|名称使用Python，例如。 ElementTree的。

我已经尝试了各种各样的东西，但我总是被卡住。任何帮助真的很感激。

塞比

下面是一些代码，我尝试了已经：

from lxml import etree as etl 
import javabridge as jv 
import bioformats as bf 


def getinfo(root, ns, nodenames): 

    NSMAP = {'mw': ns} 
    namespace = u'{%s}' % ns 
    nsl = len(namespace) 

    if len(nodenames) >= 1: 
     search = './/mw:' + nodenames[0] 
    if len(nodenames) >= 2: 
     search = search + '/mw:' + nodenames[1] 
    if len(nodenames) >= 3: 
     search = search + '/mw:' + nodenames[2] 

    out = root.findall(search, namespaces=NSMAP) 

    dictlist = [] 
    for i in range(0, len(out)): 

     dict = {} 
     for k in range(0, len(out[i].attrib)): 
      dict[out[i].keys()[k]] = out[i].values()[k] 
      print out[i].attrib 

     dictlist.append(dict) 

    return dictlist 

filename = r'c:\Users\M1SRH\Documents\Python_Projects_Testdata\CZI_XML_Test\B4_B5_S=8_4Pos_perWell_T=2_Z=1_CH=1.czi' 
bfpath = r'c:\Users\M1SRH\Documents\Software\BioFormats_Package\5.1.10\bioformats_package.jar' 
jars = jv.JARS + [bfpath] 
jv.start_vm(class_path=jars, max_heap_size='4G') 
omexml = bf.get_omexml_metadata(filename) 
new_omexml = omexml.encode('utf-8') 
result = getinfo(etl.fromstring(new_omexml), 'http://www.openmicroscopy.org/Schemas/SA/2015-01', ['StructuredAnnotations', 'XMLAnnotation']) 

print 'Done.' 

这里是XML数据集：

<OME xmlns="http://www.openmicroscopy.org/Schemas/OME/2015-01" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openmicroscopy.org/Schemas/OME/2015-01 http://www.openmicroscopy.org/Schemas/OME/2015-01/ome.xsd"> 
    <Experimenter ID="Experimenter:0" UserName="M1SRH"/> 
    <Instrument ID="Instrument:0"> 
    <Microscope Type="Inverted"/> 
    <Detector ID="Detector:Internal" Model="TestCam"/> 
    <Objective ID="Objective:1" Immersion="Air" LensNA="0.35" Model="Plan-Apochromat 5x/0.35" NominalMagnification="5.0" WorkingDistance="5000.0" WorkingDistanceUnit="µm"/> 
    <FilterSet ID="FilterSet:1"> 
     <DichroicRef ID="Dichroic:1"/> 
     <EmissionFilterRef ID="Filter:1"/> 
     <EmissionFilterRef ID="Filter:2"/> 
     <EmissionFilterRef ID="Filter:3"/> 
    </FilterSet> 
    <Filter ID="Filter:1"> 
     <TransmittanceRange CutIn="458.0" CutInUnit="nm" CutOut="474.0" CutOutUnit="nm"/> 
    </Filter> 
    <Filter ID="Filter:2"> 
     <TransmittanceRange CutIn="546.0" CutInUnit="nm" CutOut="564.0" CutOutUnit="nm"/> 
    </Filter> 
    <Filter ID="Filter:3"> 
     <TransmittanceRange CutIn="618.0" CutInUnit="nm" CutOut="756.0" CutOutUnit="nm"/> 
    </Filter> 
    <Dichroic ID="Dichroic:1"/> 
    </Instrument> 
    <Image ID="Image:0" Name="B4_B5_S=8_4Pos_perWell_T=2_Z=1_CH=1.czi #1"> 
    <AcquisitionDate>2016-07-20T11:44:16.161</AcquisitionDate> 
    <ExperimenterRef ID="Experimenter:0"/> 
    <InstrumentRef ID="Instrument:0"/> 
    <ObjectiveSettings ID="Objective:1" Medium="Air" RefractiveIndex="1.000293"/> 
    <Pixels BigEndian="false" DimensionOrder="XYCZT" ID="Pixels:0" Interleaved="false" PhysicalSizeX="0.39999999999999997" PhysicalSizeXUnit="µm" PhysicalSizeY="0.39999999999999997" PhysicalSizeYUnit="µm" SignificantBits="8" SizeC="1" SizeT="2" SizeX="640" SizeY="640" SizeZ="1" Type="uint8"> 
     <Channel AcquisitionMode="WideField" EmissionWavelength="465.0" EmissionWavelengthUnit="nm" ExcitationWavelength="353.0" ExcitationWavelengthUnit="nm" ID="Channel:0:0" IlluminationType="Epifluorescence" Name="DAPI" SamplesPerPixel="1"> 
     <DetectorSettings Binning="1x1" Gain="0.0" ID="Detector:Internal"/> 
     <FilterSetRef ID="FilterSet:1"/> 
     <LightPath/> 
     </Channel> 
     <MetadataOnly/> 
     <Plane DeltaT="0.46000003814697266" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="30533.145" PositionXUnit="reference frame" PositionY="16533.145" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="0" TheZ="0"/> 
     <Plane DeltaT="5.456000089645386" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="30533.145" PositionXUnit="reference frame" PositionY="16533.145" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="1" TheZ="0"/> 
    </Pixels> 
    </Image> 
    <Image ID="Image:1" Name="B4_B5_S=8_4Pos_perWell_T=2_Z=1_CH=1.czi #2"> 
    <AcquisitionDate>2016-07-20T11:44:16.161</AcquisitionDate> 
    <ExperimenterRef ID="Experimenter:0"/> 
    <InstrumentRef ID="Instrument:0"/> 
    <ObjectiveSettings ID="Objective:1" Medium="Air" RefractiveIndex="1.000293"/> 
    <Pixels BigEndian="false" DimensionOrder="XYCZT" ID="Pixels:1" Interleaved="false" PhysicalSizeX="0.39999999999999997" PhysicalSizeXUnit="µm" PhysicalSizeY="0.39999999999999997" PhysicalSizeYUnit="µm" SignificantBits="8" SizeC="1" SizeT="2" SizeX="640" SizeY="640" SizeZ="1" Type="uint8"> 
     <Channel AcquisitionMode="WideField" EmissionWavelength="465.0" EmissionWavelengthUnit="nm" ExcitationWavelength="353.0" ExcitationWavelengthUnit="nm" ID="Channel:1:0" IlluminationType="Epifluorescence" Name="DAPI" SamplesPerPixel="1"> 
     <DetectorSettings Binning="1x1" Gain="0.0" ID="Detector:Internal"/> 
     <FilterSetRef ID="FilterSet:1"/> 
     <LightPath/> 
     </Channel> 
     <MetadataOnly/> 
     <Plane DeltaT="0.6510000228881836" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="32466.855" PositionXUnit="reference frame" PositionY="16533.145" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="0" TheZ="0"/> 
     <Plane DeltaT="5.6519999504089355" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="32466.855" PositionXUnit="reference frame" PositionY="16533.145" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="1" TheZ="0"/> 
    </Pixels> 
    </Image> 
    <Image ID="Image:2" Name="B4_B5_S=8_4Pos_perWell_T=2_Z=1_CH=1.czi #3"> 
    <AcquisitionDate>2016-07-20T11:44:16.161</AcquisitionDate> 
    <ExperimenterRef ID="Experimenter:0"/> 
    <InstrumentRef ID="Instrument:0"/> 
    <ObjectiveSettings ID="Objective:1" Medium="Air" RefractiveIndex="1.000293"/> 
    <Pixels BigEndian="false" DimensionOrder="XYCZT" ID="Pixels:2" Interleaved="false" PhysicalSizeX="0.39999999999999997" PhysicalSizeXUnit="µm" PhysicalSizeY="0.39999999999999997" PhysicalSizeYUnit="µm" SignificantBits="8" SizeC="1" SizeT="2" SizeX="640" SizeY="640" SizeZ="1" Type="uint8"> 
     <Channel AcquisitionMode="WideField" EmissionWavelength="465.0" EmissionWavelengthUnit="nm" ExcitationWavelength="353.0" ExcitationWavelengthUnit="nm" ID="Channel:2:0" IlluminationType="Epifluorescence" Name="DAPI" SamplesPerPixel="1"> 
     <DetectorSettings Binning="1x1" Gain="0.0" ID="Detector:Internal"/> 
     <FilterSetRef ID="FilterSet:1"/> 
     <LightPath/> 
     </Channel> 
     <MetadataOnly/> 
     <Plane DeltaT="0.8610000610351562" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="30533.145" PositionXUnit="reference frame" PositionY="18466.855" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="0" TheZ="0"/> 
     <Plane DeltaT="5.859999895095825" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="30533.145" PositionXUnit="reference frame" PositionY="18466.855" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="1" TheZ="0"/> 
    </Pixels> 
    </Image> 
    <Image ID="Image:3" Name="B4_B5_S=8_4Pos_perWell_T=2_Z=1_CH=1.czi #4"> 
    <AcquisitionDate>2016-07-20T11:44:16.161</AcquisitionDate> 
    <ExperimenterRef ID="Experimenter:0"/> 
    <InstrumentRef ID="Instrument:0"/> 
    <ObjectiveSettings ID="Objective:1" Medium="Air" RefractiveIndex="1.000293"/> 
    <Pixels BigEndian="false" DimensionOrder="XYCZT" ID="Pixels:3" Interleaved="false" PhysicalSizeX="0.39999999999999997" PhysicalSizeXUnit="µm" PhysicalSizeY="0.39999999999999997" PhysicalSizeYUnit="µm" SignificantBits="8" SizeC="1" SizeT="2" SizeX="640" SizeY="640" SizeZ="1" Type="uint8"> 
     <Channel AcquisitionMode="WideField" EmissionWavelength="465.0" EmissionWavelengthUnit="nm" ExcitationWavelength="353.0" ExcitationWavelengthUnit="nm" ID="Channel:3:0" IlluminationType="Epifluorescence" Name="DAPI" SamplesPerPixel="1"> 
     <DetectorSettings Binning="1x1" Gain="0.0" ID="Detector:Internal"/> 
     <FilterSetRef ID="FilterSet:1"/> 
     <LightPath/> 
     </Channel> 
     <MetadataOnly/> 
     <Plane DeltaT="1.0509998798370361" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="32466.855" PositionXUnit="reference frame" PositionY="18466.855" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="0" TheZ="0"/> 
     <Plane DeltaT="6.055000066757202" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="32466.855" PositionXUnit="reference frame" PositionY="18466.855" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="1" TheZ="0"/> 
    </Pixels> 
    </Image> 
    <Image ID="Image:4" Name="B4_B5_S=8_4Pos_perWell_T=2_Z=1_CH=1.czi #5"> 
    <AcquisitionDate>2016-07-20T11:44:16.161</AcquisitionDate> 
    <ExperimenterRef ID="Experimenter:0"/> 
    <InstrumentRef ID="Instrument:0"/> 
    <ObjectiveSettings ID="Objective:1" Medium="Air" RefractiveIndex="1.000293"/> 
    <Pixels BigEndian="false" DimensionOrder="XYCZT" ID="Pixels:4" Interleaved="false" PhysicalSizeX="0.39999999999999997" PhysicalSizeXUnit="µm" PhysicalSizeY="0.39999999999999997" PhysicalSizeYUnit="µm" SignificantBits="8" SizeC="1" SizeT="2" SizeX="640" SizeY="640" SizeZ="1" Type="uint8"> 
     <Channel AcquisitionMode="WideField" EmissionWavelength="465.0" EmissionWavelengthUnit="nm" ExcitationWavelength="353.0" ExcitationWavelengthUnit="nm" ID="Channel:4:0" IlluminationType="Epifluorescence" Name="DAPI" SamplesPerPixel="1"> 
     <DetectorSettings Binning="1x1" Gain="0.0" ID="Detector:Internal"/> 
     <FilterSetRef ID="FilterSet:1"/> 
     <LightPath/> 
     </Channel> 
     <MetadataOnly/> 
     <Plane DeltaT="1.2590000629425049" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="39533.145" PositionXUnit="reference frame" PositionY="16533.145" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="0" TheZ="0"/> 
     <Plane DeltaT="6.296999931335449" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="39533.145" PositionXUnit="reference frame" PositionY="16533.145" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="1" TheZ="0"/> 
    </Pixels> 
    </Image> 
    <Image ID="Image:5" Name="B4_B5_S=8_4Pos_perWell_T=2_Z=1_CH=1.czi #6"> 
    <AcquisitionDate>2016-07-20T11:44:16.161</AcquisitionDate> 
    <ExperimenterRef ID="Experimenter:0"/> 
    <InstrumentRef ID="Instrument:0"/> 
    <ObjectiveSettings ID="Objective:1" Medium="Air" RefractiveIndex="1.000293"/> 
    <Pixels BigEndian="false" DimensionOrder="XYCZT" ID="Pixels:5" Interleaved="false" PhysicalSizeX="0.39999999999999997" PhysicalSizeXUnit="µm" PhysicalSizeY="0.39999999999999997" PhysicalSizeYUnit="µm" SignificantBits="8" SizeC="1" SizeT="2" SizeX="640" SizeY="640" SizeZ="1" Type="uint8"> 
     <Channel AcquisitionMode="WideField" EmissionWavelength="465.0" EmissionWavelengthUnit="nm" ExcitationWavelength="353.0" ExcitationWavelengthUnit="nm" ID="Channel:5:0" IlluminationType="Epifluorescence" Name="DAPI" SamplesPerPixel="1"> 
     <DetectorSettings Binning="1x1" Gain="0.0" ID="Detector:Internal"/> 
     <FilterSetRef ID="FilterSet:1"/> 
     <LightPath/> 
     </Channel> 
     <MetadataOnly/> 
     <Plane DeltaT="1.4500000476837158" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="41466.855" PositionXUnit="reference frame" PositionY="16533.145" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="0" TheZ="0"/> 
     <Plane DeltaT="6.490000009536743" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="41466.855" PositionXUnit="reference frame" PositionY="16533.145" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="1" TheZ="0"/> 
    </Pixels> 
    </Image> 
    <Image ID="Image:6" Name="B4_B5_S=8_4Pos_perWell_T=2_Z=1_CH=1.czi #7"> 
    <AcquisitionDate>2016-07-20T11:44:16.161</AcquisitionDate> 
    <ExperimenterRef ID="Experimenter:0"/> 
    <InstrumentRef ID="Instrument:0"/> 
    <ObjectiveSettings ID="Objective:1" Medium="Air" RefractiveIndex="1.000293"/> 
    <Pixels BigEndian="false" DimensionOrder="XYCZT" ID="Pixels:6" Interleaved="false" PhysicalSizeX="0.39999999999999997" PhysicalSizeXUnit="µm" PhysicalSizeY="0.39999999999999997" PhysicalSizeYUnit="µm" SignificantBits="8" SizeC="1" SizeT="2" SizeX="640" SizeY="640" SizeZ="1" Type="uint8"> 
     <Channel AcquisitionMode="WideField" EmissionWavelength="465.0" EmissionWavelengthUnit="nm" ExcitationWavelength="353.0" ExcitationWavelengthUnit="nm" ID="Channel:6:0" IlluminationType="Epifluorescence" Name="DAPI" SamplesPerPixel="1"> 
     <DetectorSettings Binning="1x1" Gain="0.0" ID="Detector:Internal"/> 
     <FilterSetRef ID="FilterSet:1"/> 
     <LightPath/> 
     </Channel> 
     <MetadataOnly/> 
     <Plane DeltaT="1.6640000343322754" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="39533.145" PositionXUnit="reference frame" PositionY="18466.855" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="0" TheZ="0"/> 
     <Plane DeltaT="6.700000047683716" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="39533.145" PositionXUnit="reference frame" PositionY="18466.855" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="1" TheZ="0"/> 
    </Pixels> 
    </Image> 
    <Image ID="Image:7" Name="B4_B5_S=8_4Pos_perWell_T=2_Z=1_CH=1.czi #8"> 
    <AcquisitionDate>2016-07-20T11:44:16.161</AcquisitionDate> 
    <ExperimenterRef ID="Experimenter:0"/> 
    <InstrumentRef ID="Instrument:0"/> 
    <ObjectiveSettings ID="Objective:1" Medium="Air" RefractiveIndex="1.000293"/> 
    <Pixels BigEndian="false" DimensionOrder="XYCZT" ID="Pixels:7" Interleaved="false" PhysicalSizeX="0.39999999999999997" PhysicalSizeXUnit="µm" PhysicalSizeY="0.39999999999999997" PhysicalSizeYUnit="µm" SignificantBits="8" SizeC="1" SizeT="2" SizeX="640" SizeY="640" SizeZ="1" Type="uint8"> 
     <Channel AcquisitionMode="WideField" EmissionWavelength="465.0" EmissionWavelengthUnit="nm" ExcitationWavelength="353.0" ExcitationWavelengthUnit="nm" ID="Channel:7:0" IlluminationType="Epifluorescence" Name="DAPI" SamplesPerPixel="1"> 
     <DetectorSettings Binning="1x1" Gain="0.0" ID="Detector:Internal"/> 
     <FilterSetRef ID="FilterSet:1"/> 
     <LightPath/> 
     </Channel> 
     <MetadataOnly/> 
     <Plane DeltaT="1.8569998741149902" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="41466.855" PositionXUnit="reference frame" PositionY="18466.855" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="0" TheZ="0"/> 
     <Plane DeltaT="6.898000001907349" DeltaTUnit="s" ExposureTime="20.0" ExposureTimeUnit="s" PositionX="41466.855" PositionXUnit="reference frame" PositionY="18466.855" PositionYUnit="reference frame" PositionZ="111.842" PositionZUnit="reference frame" TheC="0" TheT="1" TheZ="0"/> 
    </Pixels> 
    </Image> 
    <StructuredAnnotations xmlns="http://www.openmicroscopy.org/Schemas/SA/2015-01"> 
    <XMLAnnotation ID="Annotation:0" Namespace="openmicroscopy.org/OriginalMetadata"> 
     <Value> 
     <OriginalMetadata> 
      <Key>Experiment|AcquisitionBlock|TimeSeriesSetup|RegionsSetup|SampleHolder|AllowedScanArea|ContourType</Key> 
      <Value>[Rectangle]</Value> 
     </OriginalMetadata> 
     </Value> 
    </XMLAnnotation> 
    <XMLAnnotation ID="Annotation:2127" Namespace="openmicroscopy.org/OriginalMetadata"> 
     <Value> 
     <OriginalMetadata> 
      <Key>Information|Image|S|Scene|Shape|Name</Key> 
      <Value>[B4, B4, B4, B4, B5, B5, B5, B5]</Value> 
     </OriginalMetadata> 
     </Value> 
    </XMLAnnotation> 
    </StructuredAnnotations> 
</OME> 

Answer 1

作为一种假设，也许你没有使用命名空间来找到元素。 我试图从OriginalMetadata获取密钥和值。

import xml.etree.ElementTree as ET 

tree = ET.fromstring(initial_string) 
# Define NameSpace 
name_space = "{http://www.openmicroscopy.org/Schemas/SA/2015-01}" 
origin_meta_datas = tree.findall(".//{}OriginalMetadata".format(name_space)) 
# Iterate in founded origins 
for origin in origin_meta_datas: 
    key = origin.find("{}Key".format(name_space)).text 
    if key == "Information|Image|S|Scene|Shape|Name": 
     value = origin.find("{}Value".format(name_space)).text 
     print("Value: {}".format(value))