python ElemetTree 查找包含字符串的元素
python ElemetTree find elements with string
我有很大的 xml 文件（cca 2GB），下面只是这个文件的一部分。在此文件中，我想搜索以以下内容开头的所有元素：
<ManagedElement sourceType = "SIU"> 和 <ManagedElement sourceType = "CELLO"> 然后从中获取一些数据。下面是这些 ManagedElement 下的示例。
这是我的代码：
#!/usr/bin/python
from xml.etree import ElementTree as ElementTree
with open('/var/opt/arne/OSSRC_Model_2014_11_24_3_19_36_PM.xml', 'rt') as f:
tree = ElementTree.parse(f)
with open('/home/gf', 'a') as f1:
for item in tree.findall('.//ManagedElement'):
rank = item.find('.//ipAddress')
rank1=rank.get('string')
name = item.find('.//ManagedElementId')
name1=name.get('string')
site = item.find('.//associatedSite')
site1=site.get('string')
f1.write((name1 + ',' + rank1 + ',' + site1 + '\n'))
问题是还有其他 ManagedElements 而我只想要带有字符串 SIU 和 CELLO 的那些。
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<!DOCTYPE Model SYSTEM "/opt/arne/etc/arne12_2.dtd">
<Model version = "1" importVersion = "12.2">
<!--Validate: /opt/arne/bin/import.sh -f 4_siu_create.xml \ -val:rall -->
<Create>
<SubNetwork userLabel = "ZLNOUR_SIU" networkType = "IPRAN">
<ManagedElement sourceType = "SIU">
<ManagedElementId string = "siu009722"/>
<primaryType type = "STN"/>
<managedElementType types = ""/>
<associatedSite string = "Site=site00972"/>
<nodeVersion string = "T11A"/>
<platformVersion string = ""/>
<swVersion string = ""/>
<vendorName string = ""/>
<userDefinedState string = ""/>
<managedServiceAvailability int = "1"/>
<isManaged boolean = "true"/>
<connectionStatus string = "OFF"/>
<Connectivity>
<DEFAULT>
<emUrl url = "http://10.131.203.117:80/"/>
<ipAddress string = "10.131.203.117"/>
<oldIpAddress string = "int dummy=0"/>
<hostname string = ""/>
<nodeSecurityState state = "ON"/>
<boardId string = ""/>
<Protocol number = "0">
<protocolType string = "SNMP"/>
<port int = "161"/>
<protocolVersion string = "v2c"/>
<securityName string = ""/>
<authenticationMethod string = ""/>
<encryptionMethod string = ""/>
<communityString string = "public"/>
<context string = ""/>
<namingUrl string = ""/>
<namingPort int = ""/>
<notificationIRPAgentVersion string = ""/>
<alarmIRPAgentVersion string = ""/>
<notificationIRPNamingContext context = ""/>
<alarmIRPNamingContext context = ""/>
</Protocol>
<Protocol number = "1">
<protocolType string = "SSH"/>
<port int = "22"/>
<protocolVersion string = ""/>
<securityName string = ""/>
<authenticationMethod string = ""/>
<encryptionMethod string = ""/>
<communityString string = ""/>
<context string = ""/>
<namingUrl string = ""/>
<namingPort int = ""/>
<notificationIRPAgentVersion string = ""/>
<alarmIRPAgentVersion string = ""/>
<notificationIRPNamingContext context = ""/>
<alarmIRPNamingContext context = ""/>
</Protocol>
<Browser>
<browser string = ""/>
<browserURL string = ""/>
<bookname string = ""/>
</Browser>
</DEFAULT>
</Connectivity>
<Tss>
<Entry>
<System string = "siu009722"/>
<Type string = "NORMAL"/>
<User string = "admin"/>
<Password string = "siu009722"/>
</Entry>
<Entry>
<System string = "siu009722"/>
<Type string = "SECURE"/>
<User string = "admin"/>
<Password string = "siu009722"/>
</Entry>
</Tss>
<Relationship>
<AssociableNode TO_FDN = "FtpServer=SMRSSLAVE-rtwaned1o,FtpService=swstore-rtwaned1o" AssociationType = "ManagedElement_to_ftpSwStore"/>
<AssociableNode TO_FDN = "FtpServer=SMRSSLAVE-rtwaned1o,FtpService=cmdown-rtwaned1o" AssociationType = "ManagedElement_to_neTransientCmDown"/>
<AssociableNode TO_FDN = "FtpServer=SMRSSLAVE-rtwaned1o,FtpService=cmup-rtwaned1o" AssociationType = "ManagedElement_to_neTransientCmUp"/>
<AssociableNode TO_FDN = "FtpServer=SMRSSLAVE-rtwaned1o,FtpService=pmup-rtwaned1o" AssociationType = "ManagedElement_to_neTransientPm"/>
<AssociableNode TO_FDN = "ManagementNode=ONRM" AssociationType = "MgmtAssociation"/>
<AssociableNode TO_FDN = "SubNetwork=ZLNOUR3,MeContext=rbs009721,ManagedElement=1,NodeBFunction=1" FROM_FDN = "SubNetwork=ZLNOUR_SIU,ManagedElement=siu009722,StnFunction=STN_ManagedFunction" AssociationType = "StnFunction_to_NodeBFunction"/>
</Relationship>
</ManagedElement>
<ManagedElement sourceType="CELLO">
<ManagedElementId string="3GMUP"/>
<primaryType type="RBS"/>
<managedElementType types=""/>
<associatedSite string="Site=Podgorica"/>
<nodeVersion string=""/>
<platformVersion string=""/>
<swVersion string=""/>
<vendorName string="Ericsson"/>
<userDefinedState string=""/>
<managedServiceAvailability int="1"/>
<isManaged boolean="true"/>
<neMIMVersion string="T.1.201"/>
<connectionStatus string="ON"/>
<ManagedFunction>
<functionType string="NodeB"/>
<supportSystemControl boolean="false"/>
</ManagedFunction>
<Connectivity>
<DEFAULT>
<emUrl url="http://10.132.11.226:80/em/index.html"/>
<ipAddress string="10.132.11.226"/>
<oldIpAddress string=""/>
<hostname string=""/>
<nodeSecurityState state="ON"/>
<boardId string=""/>
<Protocol number="0">
<protocolType string="TELNET"/>
<port int="23"/>
<protocolVersion string=""/>
<securityName string=""/>
<authenticationMethod string=""/>
<encryptionMethod string=""/>
<communityString string=""/>
<context string=""/>
<namingUrl string=""/>
<namingPort int=""/>
<notificationIRPAgentVersion string=""/>
<alarmIRPAgentVersion string=""/>
<notificationIRPNamingContext context=""/>
<alarmIRPNamingContext context=""/>
</Protocol>
<Protocol number="1">
<protocolType string="CORBA"/>
<port int="0"/>
<protocolVersion string=""/>
<securityName string=""/>
<authenticationMethod string=""/>
<encryptionMethod string=""/>
<communityString string=""/>
<context string=""/>
<namingUrl string="http://10.132.11.226:80/cello/ior_files/nameroot.ior"/>
<namingPort int="0"/>
<notificationIRPAgentVersion string="3.2"/>
<alarmIRPAgentVersion string="3.2"/>
<notificationIRPNamingContext context="NOTIFICATION_IRP_VERSION_1_1"/>
<alarmIRPNamingContext context="ALARM_IRP_VERSION_1_1"/>
</Protocol>
<Protocol number="2">
<protocolType string="SFTP"/>
<port int="22"/>
<protocolVersion string=""/>
<securityName string=""/>
<authenticationMethod string=""/>
<encryptionMethod string=""/>
<communityString string=""/>
<context string=""/>
<namingUrl string=""/>
<namingPort int=""/>
<notificationIRPAgentVersion string=""/>
<alarmIRPAgentVersion string=""/>
<notificationIRPNamingContext context=""/>
<alarmIRPNamingContext context=""/>
</Protocol>
<Protocol number="3">
<protocolType string="FTP"/>
<port int="21"/>
<protocolVersion string=""/>
<securityName string=""/>
<authenticationMethod string=""/>
<encryptionMethod string=""/>
<communityString string=""/>
<context string=""/>
<namingUrl string=""/>
<namingPort int=""/>
<notificationIRPAgentVersion string=""/>
<alarmIRPAgentVersion string=""/>
<notificationIRPNamingContext context=""/>
<alarmIRPNamingContext context=""/>
</Protocol>
<Protocol number="4">
<protocolType string="SSH"/>
<port int="22"/>
<protocolVersion string=""/>
<securityName string=""/>
<authenticationMethod string=""/>
<encryptionMethod string=""/>
<communityString string=""/>
<context string=""/>
<namingUrl string=""/>
<namingPort int=""/>
<notificationIRPAgentVersion string=""/>
<alarmIRPAgentVersion string=""/>
<notificationIRPNamingContext context=""/>
<alarmIRPNamingContext context=""/>
</Protocol>
<Browser>
<browser string=""/>
<browserURL string=""/>
<bookname string=""/>
</Browser>
</DEFAULT>
</Connectivity>
<Tss>
<Entry>
<System string="3GMUP"/>
<Type string="SECURE"/>
<User string="rbs"/>
<Password string="rbs"/>
</Entry>
<Entry>
<System string="3GMUP"/>
<Type string="NORMAL"/>
<User string="rbs"/>
<Password string="rbs"/>
</Entry>
</Tss>
<Relationship>
<AssociableNode TO_FDN="FtpServer=SMRSMASTERWRAN-oss1,FtpService=smo-backup-oss1" AssociationType="ManagedElement_to_ftpBackupStore"/>
<AssociableNode TO_FDN="FtpServer=SMRSMASTERWRAN-oss1,FtpService=smo-keystore-oss1" AssociationType="ManagedElement_to_ftpLicenseKeyStore"/>
<AssociableNode TO_FDN="FtpServer=SMRSMASTERWRAN-oss1,FtpService=smo-swstore-oss1" AssociationType="ManagedElement_to_ftpSwStore"/>
<AssociableNode TO_FDN="Group=CD34082729" AssociationType="Group_to_MeContext"/>
<AssociableNode TO_FDN="ManagementNode=ONRM" AssociationType="MgmtAssociation"/>
<AssociableNode TO_FDN="SubNetwork=IPRAN,ManagedElement=MUP_BD,StnFunction=STN_ManagedFunction" FROM_FDN="SubNetwork=RNC111,MeContext=3GMUP,ManagedElement=1,NodeBFunction=1" AssociationType="StnFunction_to_NodeBFunction"/>
<AssociableNode TO_FDN="SubNetwork=RNC111,Group=NodeB" AssociationType="Group_to_MeContext"/>
</Relationship>
</ManagedElement>
</SubNetwork>
</Create>
</Model>
仅获取具有 sourceType 属性等于 "CELLO" 或等于 "SIU" 的 ManagedElement 的正确 XPath 如下：
.//ManagedElement[@sourceType="CELLO" or @sourceType="SIU"]
不幸的是，XPath OR 运算符似乎 not supported by xml.etree.ElementTree, so simply passing above XPath to findall() method won't work. Now, your possible options are to use lxml 库具有更好的 XPath 支持（特别是如果您计划在代码中更广泛地使用复杂的 XPath），或者您可以创建 lambda 表达式以手动按 sourceType 属性值过滤 ManagedElement。例如，不仅仅是 :
tree.findall('.//ManagedElement')
...您可以尝试这样的操作：
filter(lambda x: x.get('sourceType') in ['CELLO','SIU'], tree.findall('.//ManagedElement'))
我有很大的 xml 文件（cca 2GB），下面只是这个文件的一部分。在此文件中，我想搜索以以下内容开头的所有元素：
<ManagedElement sourceType = "SIU"> 和 <ManagedElement sourceType = "CELLO"> 然后从中获取一些数据。下面是这些 ManagedElement 下的示例。
这是我的代码：
#!/usr/bin/python
from xml.etree import ElementTree as ElementTree
with open('/var/opt/arne/OSSRC_Model_2014_11_24_3_19_36_PM.xml', 'rt') as f:
tree = ElementTree.parse(f)
with open('/home/gf', 'a') as f1:
for item in tree.findall('.//ManagedElement'):
rank = item.find('.//ipAddress')
rank1=rank.get('string')
name = item.find('.//ManagedElementId')
name1=name.get('string')
site = item.find('.//associatedSite')
site1=site.get('string')
f1.write((name1 + ',' + rank1 + ',' + site1 + '\n'))
问题是还有其他 ManagedElements 而我只想要带有字符串 SIU 和 CELLO 的那些。
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<!DOCTYPE Model SYSTEM "/opt/arne/etc/arne12_2.dtd">
<Model version = "1" importVersion = "12.2">
<!--Validate: /opt/arne/bin/import.sh -f 4_siu_create.xml \ -val:rall -->
<Create>
<SubNetwork userLabel = "ZLNOUR_SIU" networkType = "IPRAN">
<ManagedElement sourceType = "SIU">
<ManagedElementId string = "siu009722"/>
<primaryType type = "STN"/>
<managedElementType types = ""/>
<associatedSite string = "Site=site00972"/>
<nodeVersion string = "T11A"/>
<platformVersion string = ""/>
<swVersion string = ""/>
<vendorName string = ""/>
<userDefinedState string = ""/>
<managedServiceAvailability int = "1"/>
<isManaged boolean = "true"/>
<connectionStatus string = "OFF"/>
<Connectivity>
<DEFAULT>
<emUrl url = "http://10.131.203.117:80/"/>
<ipAddress string = "10.131.203.117"/>
<oldIpAddress string = "int dummy=0"/>
<hostname string = ""/>
<nodeSecurityState state = "ON"/>
<boardId string = ""/>
<Protocol number = "0">
<protocolType string = "SNMP"/>
<port int = "161"/>
<protocolVersion string = "v2c"/>
<securityName string = ""/>
<authenticationMethod string = ""/>
<encryptionMethod string = ""/>
<communityString string = "public"/>
<context string = ""/>
<namingUrl string = ""/>
<namingPort int = ""/>
<notificationIRPAgentVersion string = ""/>
<alarmIRPAgentVersion string = ""/>
<notificationIRPNamingContext context = ""/>
<alarmIRPNamingContext context = ""/>
</Protocol>
<Protocol number = "1">
<protocolType string = "SSH"/>
<port int = "22"/>
<protocolVersion string = ""/>
<securityName string = ""/>
<authenticationMethod string = ""/>
<encryptionMethod string = ""/>
<communityString string = ""/>
<context string = ""/>
<namingUrl string = ""/>
<namingPort int = ""/>
<notificationIRPAgentVersion string = ""/>
<alarmIRPAgentVersion string = ""/>
<notificationIRPNamingContext context = ""/>
<alarmIRPNamingContext context = ""/>
</Protocol>
<Browser>
<browser string = ""/>
<browserURL string = ""/>
<bookname string = ""/>
</Browser>
</DEFAULT>
</Connectivity>
<Tss>
<Entry>
<System string = "siu009722"/>
<Type string = "NORMAL"/>
<User string = "admin"/>
<Password string = "siu009722"/>
</Entry>
<Entry>
<System string = "siu009722"/>
<Type string = "SECURE"/>
<User string = "admin"/>
<Password string = "siu009722"/>
</Entry>
</Tss>
<Relationship>
<AssociableNode TO_FDN = "FtpServer=SMRSSLAVE-rtwaned1o,FtpService=swstore-rtwaned1o" AssociationType = "ManagedElement_to_ftpSwStore"/>
<AssociableNode TO_FDN = "FtpServer=SMRSSLAVE-rtwaned1o,FtpService=cmdown-rtwaned1o" AssociationType = "ManagedElement_to_neTransientCmDown"/>
<AssociableNode TO_FDN = "FtpServer=SMRSSLAVE-rtwaned1o,FtpService=cmup-rtwaned1o" AssociationType = "ManagedElement_to_neTransientCmUp"/>
<AssociableNode TO_FDN = "FtpServer=SMRSSLAVE-rtwaned1o,FtpService=pmup-rtwaned1o" AssociationType = "ManagedElement_to_neTransientPm"/>
<AssociableNode TO_FDN = "ManagementNode=ONRM" AssociationType = "MgmtAssociation"/>
<AssociableNode TO_FDN = "SubNetwork=ZLNOUR3,MeContext=rbs009721,ManagedElement=1,NodeBFunction=1" FROM_FDN = "SubNetwork=ZLNOUR_SIU,ManagedElement=siu009722,StnFunction=STN_ManagedFunction" AssociationType = "StnFunction_to_NodeBFunction"/>
</Relationship>
</ManagedElement>
<ManagedElement sourceType="CELLO">
<ManagedElementId string="3GMUP"/>
<primaryType type="RBS"/>
<managedElementType types=""/>
<associatedSite string="Site=Podgorica"/>
<nodeVersion string=""/>
<platformVersion string=""/>
<swVersion string=""/>
<vendorName string="Ericsson"/>
<userDefinedState string=""/>
<managedServiceAvailability int="1"/>
<isManaged boolean="true"/>
<neMIMVersion string="T.1.201"/>
<connectionStatus string="ON"/>
<ManagedFunction>
<functionType string="NodeB"/>
<supportSystemControl boolean="false"/>
</ManagedFunction>
<Connectivity>
<DEFAULT>
<emUrl url="http://10.132.11.226:80/em/index.html"/>
<ipAddress string="10.132.11.226"/>
<oldIpAddress string=""/>
<hostname string=""/>
<nodeSecurityState state="ON"/>
<boardId string=""/>
<Protocol number="0">
<protocolType string="TELNET"/>
<port int="23"/>
<protocolVersion string=""/>
<securityName string=""/>
<authenticationMethod string=""/>
<encryptionMethod string=""/>
<communityString string=""/>
<context string=""/>
<namingUrl string=""/>
<namingPort int=""/>
<notificationIRPAgentVersion string=""/>
<alarmIRPAgentVersion string=""/>
<notificationIRPNamingContext context=""/>
<alarmIRPNamingContext context=""/>
</Protocol>
<Protocol number="1">
<protocolType string="CORBA"/>
<port int="0"/>
<protocolVersion string=""/>
<securityName string=""/>
<authenticationMethod string=""/>
<encryptionMethod string=""/>
<communityString string=""/>
<context string=""/>
<namingUrl string="http://10.132.11.226:80/cello/ior_files/nameroot.ior"/>
<namingPort int="0"/>
<notificationIRPAgentVersion string="3.2"/>
<alarmIRPAgentVersion string="3.2"/>
<notificationIRPNamingContext context="NOTIFICATION_IRP_VERSION_1_1"/>
<alarmIRPNamingContext context="ALARM_IRP_VERSION_1_1"/>
</Protocol>
<Protocol number="2">
<protocolType string="SFTP"/>
<port int="22"/>
<protocolVersion string=""/>
<securityName string=""/>
<authenticationMethod string=""/>
<encryptionMethod string=""/>
<communityString string=""/>
<context string=""/>
<namingUrl string=""/>
<namingPort int=""/>
<notificationIRPAgentVersion string=""/>
<alarmIRPAgentVersion string=""/>
<notificationIRPNamingContext context=""/>
<alarmIRPNamingContext context=""/>
</Protocol>
<Protocol number="3">
<protocolType string="FTP"/>
<port int="21"/>
<protocolVersion string=""/>
<securityName string=""/>
<authenticationMethod string=""/>
<encryptionMethod string=""/>
<communityString string=""/>
<context string=""/>
<namingUrl string=""/>
<namingPort int=""/>
<notificationIRPAgentVersion string=""/>
<alarmIRPAgentVersion string=""/>
<notificationIRPNamingContext context=""/>
<alarmIRPNamingContext context=""/>
</Protocol>
<Protocol number="4">
<protocolType string="SSH"/>
<port int="22"/>
<protocolVersion string=""/>
<securityName string=""/>
<authenticationMethod string=""/>
<encryptionMethod string=""/>
<communityString string=""/>
<context string=""/>
<namingUrl string=""/>
<namingPort int=""/>
<notificationIRPAgentVersion string=""/>
<alarmIRPAgentVersion string=""/>
<notificationIRPNamingContext context=""/>
<alarmIRPNamingContext context=""/>
</Protocol>
<Browser>
<browser string=""/>
<browserURL string=""/>
<bookname string=""/>
</Browser>
</DEFAULT>
</Connectivity>
<Tss>
<Entry>
<System string="3GMUP"/>
<Type string="SECURE"/>
<User string="rbs"/>
<Password string="rbs"/>
</Entry>
<Entry>
<System string="3GMUP"/>
<Type string="NORMAL"/>
<User string="rbs"/>
<Password string="rbs"/>
</Entry>
</Tss>
<Relationship>
<AssociableNode TO_FDN="FtpServer=SMRSMASTERWRAN-oss1,FtpService=smo-backup-oss1" AssociationType="ManagedElement_to_ftpBackupStore"/>
<AssociableNode TO_FDN="FtpServer=SMRSMASTERWRAN-oss1,FtpService=smo-keystore-oss1" AssociationType="ManagedElement_to_ftpLicenseKeyStore"/>
<AssociableNode TO_FDN="FtpServer=SMRSMASTERWRAN-oss1,FtpService=smo-swstore-oss1" AssociationType="ManagedElement_to_ftpSwStore"/>
<AssociableNode TO_FDN="Group=CD34082729" AssociationType="Group_to_MeContext"/>
<AssociableNode TO_FDN="ManagementNode=ONRM" AssociationType="MgmtAssociation"/>
<AssociableNode TO_FDN="SubNetwork=IPRAN,ManagedElement=MUP_BD,StnFunction=STN_ManagedFunction" FROM_FDN="SubNetwork=RNC111,MeContext=3GMUP,ManagedElement=1,NodeBFunction=1" AssociationType="StnFunction_to_NodeBFunction"/>
<AssociableNode TO_FDN="SubNetwork=RNC111,Group=NodeB" AssociationType="Group_to_MeContext"/>
</Relationship>
</ManagedElement>
</SubNetwork>
</Create>
</Model>
仅获取具有 sourceType 属性等于 "CELLO" 或等于 "SIU" 的 ManagedElement 的正确 XPath 如下：
.//ManagedElement[@sourceType="CELLO" or @sourceType="SIU"]
不幸的是，XPath OR 运算符似乎 not supported by xml.etree.ElementTree, so simply passing above XPath to findall() method won't work. Now, your possible options are to use lxml 库具有更好的 XPath 支持（特别是如果您计划在代码中更广泛地使用复杂的 XPath），或者您可以创建 lambda 表达式以手动按 sourceType 属性值过滤 ManagedElement。例如，不仅仅是 :
tree.findall('.//ManagedElement')
...您可以尝试这样的操作：
filter(lambda x: x.get('sourceType') in ['CELLO','SIU'], tree.findall('.//ManagedElement'))