解析文本文件中的两项

Question

我有一个包含AWS名称/图像ID的长文件。我想使用python解析"Name“和"ImageId”。问题是它们没有配对，如下文所示。

在下面的示例中，图像ID是ami-00455a561ee2a2221，而名称是temp-rp030-3。

 {
            "VirtualizationType": "hvm", 
            "Description": "", 
            "PlatformDetails": "Linux/UNIX", 
            "EnaSupport": true, 
            "Hypervisor": "xen", 
            "State": "available", 
            "SriovNetSupport": "simple", 
            "ImageId": "ami-00455a561ee2a2221", 
            "UsageOperation": "RunInstances", 
            "BlockDeviceMappings": [
                {
                    "DeviceName": "/dev/xvda", 
                    "Ebs": {
                        "SnapshotId": "snap-097a377c34d632344", 
                        "DeleteOnTermination": true, 
                        "VolumeType": "gp2", 
                        "VolumeSize": 1500, 
                        "Encrypted": true
                    }
                }, 
                {
                    "DeviceName": "/dev/sdb", 
                    "VirtualName": "ephemeral0"
                }, 
                {
                    "DeviceName": "/dev/sdc", 
                    "VirtualName": "ephemeral1"
                }
            ], 
            "Architecture": "x86_64", 
            "ImageLocation": "051929652521/temp-rp030-3", 
            "RootDeviceType": "ebs", 
            "OwnerId": "051929652521", 
            "RootDeviceName": "/dev/xvda", 
            "CreationDate": "2022-01-15T22:36:32.000Z", 
            "Public": false, 
            "ImageType": "machine", 
            "Name": "temp-rp030-3"
        }, 

我尝试了如下方法，搜索图像ID，然后将接下来的18行打印到列表中。然而，我发现并不是每一个Name的出现都是在ImageId之后的18行。

import re
from itertools import islice


iter_list = []


with open("/Users/Desktop/describe_images.txt", 'r') as f:

    for line in f:

        if re.search(r"\"ImageId\"", line):

            iter_list.append(''.join(islice(f, 18)))

下面是一个更大的示例，它包含多个Names和ImageID

 {
            "VirtualizationType": "hvm", 
            "Description": "", 
            "PlatformDetails": "Linux/UNIX", 
            "EnaSupport": true, 
            "Hypervisor": "xen", 
            "State": "available", 
            "SriovNetSupport": "simple", 
            "ImageId": "ami-00455a561ee2a2221", 
            "UsageOperation": "RunInstances", 
            "BlockDeviceMappings": [
                {
                    "DeviceName": "/dev/xvda", 
                    "Ebs": {
                        "SnapshotId": "snap-097a377c34d632344", 
                        "DeleteOnTermination": true, 
                        "VolumeType": "gp2", 
                        "VolumeSize": 1500, 
                        "Encrypted": true
                    }
                }, 
                {
                    "DeviceName": "/dev/sdb", 
                    "VirtualName": "ephemeral0"
                }, 
                {
                    "DeviceName": "/dev/sdc", 
                    "VirtualName": "ephemeral1"
                }
            ], 
            "Architecture": "x86_64", 
            "ImageLocation": "051929652521/temp-rp030-3", 
            "RootDeviceType": "ebs", 
            "OwnerId": "051929652521", 
            "RootDeviceName": "/dev/xvda", 
            "CreationDate": "2022-01-15T22:36:32.000Z", 
            "Public": false, 
            "ImageType": "machine", 
            "Name": "temp-rp030-3"
        }, 
        {
            "VirtualizationType": "hvm", 
            "Description": "This image may not be the latest version available and might include security vulnerabilities. Please check the latest, up-to-date, available version at https://bitnami.com/stacks.", 
            "PlatformDetails": "Linux/UNIX", 
            "EnaSupport": true, 
            "Hypervisor": "xen", 
            "State": "available", 
            "SriovNetSupport": "simple", 
            "ImageId": "ami-00455bda4a1b36dd7", 
            "UsageOperation": "RunInstances", 
            "BlockDeviceMappings": [
                {
                    "DeviceName": "/dev/xvda", 
                    "Ebs": {
                        "SnapshotId": "snap-0dac397dbf6de2dc8", 
                        "DeleteOnTermination": true, 
                        "VolumeType": "gp2", 
                        "VolumeSize": 10, 
                        "Encrypted": false
                    }
                }, 
                {
                    "DeviceName": "/dev/sdb", 
                    "VirtualName": "ephemeral0"
                }, 
                {
                    "DeviceName": "/dev/sdc", 
                    "VirtualName": "ephemeral1"
                }, 
                {
                    "DeviceName": "/dev/sdd", 
                    "VirtualName": "ephemeral2"
                }, 
                {
                    "DeviceName": "/dev/sde", 
                    "VirtualName": "ephemeral3"
                }
            ], 
            "Architecture": "x86_64", 
            "ImageLocation": "979382823631/bitnami-wordpress-5.7.1-7-r06-linux-debian-10-x86_64-hvm-ebs-frontend-aurora-nami", 
            "RootDeviceType": "ebs", 
            "OwnerId": "979382823631", 
            "RootDeviceName": "/dev/xvda", 
            "CreationDate": "2021-05-06T15:54:43.000Z", 
            "Public": true, 
            "ImageType": "machine", 
            "Name": "bitnami-wordpress-5.7.1-7-r06-linux-debian-10-x86_64-hvm-ebs-frontend-aurora-nami"
        }, 
        {
            "ProductCodes": [
                {
                    "ProductCodeId": "78odkuio96rl1u75f08miu3tz", 
                    "ProductCodeType": "marketplace"
                }
            ], 
            "Description": "MXNet-1.6.0, TensorFlow-2.3.0, 2.1.0 & 1.15.3, PyTorch-1.4.0 & 1.6.0, EI, & others. NVIDIA CUDA, cuDNN, NCCL, Intel MKL-DNN, Docker, NVIDIA-Docker, Neuron,AWS Neuron,inference,AWS Inferentia,Inferentia,inf,inf1,EC2 Inf1,Elastic Inference", 
            "PlatformDetails": "Linux/UNIX", 
            "EnaSupport": true, 
            "VirtualizationType": "hvm", 
            "Hypervisor": "xen", 
            "ImageOwnerAlias": "aws-marketplace", 
            "State": "available", 
            "SriovNetSupport": "simple", 
            "ImageId": "ami-004566286db7148f6", 
            "UsageOperation": "RunInstances", 
            "BlockDeviceMappings": [
                {
                    "DeviceName": "/dev/xvda", 
                    "Ebs": {
                        "SnapshotId": "snap-0719a5ec731c4a9b4", 
                        "DeleteOnTermination": true, 
                        "VolumeType": "gp2", 
                        "VolumeSize": 100, 
                        "Encrypted": false
                    }
                }
            ], 
            "Architecture": "x86_64", 
            "ImageLocation": "aws-marketplace/SupportedImages Deep Learning AMI (Amazon Linux 2) Version 34.0-7a4f4a31-b0bf-493c-b3fe-3d5ba59858e7-ami-036251f870bf5b53d.4", 
            "RootDeviceType": "ebs", 
            "OwnerId": "679593333241", 
            "RootDeviceName": "/dev/xvda", 
            "CreationDate": "2020-10-06T17:09:00.000Z", 
            "Public": true, 
            "ImageType": "machine", 
            "Name": "SupportedImages Deep Learning AMI (Amazon Linux 2) Version 34.0-7a4f4a31-b0bf-493c-b3fe-3d5ba59858e7-ami-036251f870bf5b53d.4"
        }, 
        {
            "VirtualizationType": "hvm", 
            "Description": "This image may not be the latest version available and might include security vulnerabilities. Please check the latest, up-to-date, available version at https://bitnami.com/stacks.", 
            "PlatformDetails": "Red Hat Enterprise Linux", 
            "EnaSupport": true, 
            "Hypervisor": "xen", 
            "State": "available", 
            "SriovNetSupport": "simple", 
            "ImageId": "ami-004583c651e1d7f07", 
            "UsageOperation": "RunInstances:0010", 
            "BlockDeviceMappings": [
                {
                    "DeviceName": "/dev/sda1", 
                    "Ebs": {
                        "SnapshotId": "snap-0528a9d30401765f3", 
                        "DeleteOnTermination": true, 
                        "VolumeType": "gp2", 
                        "VolumeSize": 10, 
                        "Encrypted": false
                    }
                }, 
                {
                    "DeviceName": "/dev/sdb", 
                    "VirtualName": "ephemeral0"
                }, 
                {
                    "DeviceName": "/dev/sdc", 
                    "VirtualName": "ephemeral1"
                }, 
                {
                    "DeviceName": "/dev/sdd", 
                    "VirtualName": "ephemeral2"
                }, 
                {
                    "DeviceName": "/dev/sde", 
                    "VirtualName": "ephemeral3"
                }
            ], 
            "Architecture": "x86_64", 
            "ImageLocation": "979382823631/bitnami-drupal-7.67-0-r50-linux-redhat-7.5-x86_64-hvm-ebs", 
            "RootDeviceType": "ebs", 
            "OwnerId": "979382823631", 
            "RootDeviceName": "/dev/sda1", 
            "CreationDate": "2019-05-15T14:07:15.000Z", 
            "Public": true, 
            "ImageType": "machine", 
            "Name": "bitnami-drupal-7.67-0-r50-linux-redhat-7.5-x86_64-hvm-ebs"
        }, 
        {
            "VirtualizationType": "hvm", 
            "Description": "This image may not be the latest version available and might include security vulnerabilities. Please check the latest, up-to-date, available version at https://bitnami.com/stacks.", 
            "PlatformDetails": "Linux/UNIX", 
            "EnaSupport": true, 
            "Hypervisor": "xen", 
            "State": "available", 
            "ImageId": "ami-004585220878e1c1a", 
            "UsageOperation": "RunInstances", 
            "BlockDeviceMappings": [
                {
                    "DeviceName": "/dev/xvda", 
                    "Ebs": {
                        "SnapshotId": "snap-09d73437aed0b4d2c", 
                        "DeleteOnTermination": true, 
                        "VolumeType": "gp2", 
                        "VolumeSize": 10, 
                        "Encrypted": false
                    }
                }, 
                {
                    "DeviceName": "/dev/sdb", 
                    "VirtualName": "ephemeral0"
                }, 
                {
                    "DeviceName": "/dev/sdc", 
                    "VirtualName": "ephemeral1"
                }, 
                {
                    "DeviceName": "/dev/sdd", 
                    "VirtualName": "ephemeral2"
                }, 
                {
                    "DeviceName": "/dev/sde", 
                    "VirtualName": "ephemeral3"
                }
            ], 
            "Architecture": "x86_64", 
            "ImageLocation": "979382823631/bitnami-osclass-3.8.0-2-r50-linux-debian-9-x86_64-hvm-ebs", 
            "RootDeviceType": "ebs", 
            "OwnerId": "979382823631", 
            "RootDeviceName": "/dev/xvda", 
            "CreationDate": "2019-05-16T08:29:17.000Z", 
            "Public": true, 
            "ImageType": "machine", 
            "Name": "bitnami-osclass-3.8.0-2-r50-linux-debian-9-x86_64-hvm-ebs"
        }, 
        {
            "VirtualizationType": "hvm", 
            "Description": "This image may not be the latest version available and might include security vulnerabilities. Please check the latest, up-to-date, available version at https://bitnami.com/stacks.", 
            "PlatformDetails": "Linux/UNIX", 
            "EnaSupport": true, 
            "Hypervisor": "xen", 
            "State": "available", 
            "SriovNetSupport": "simple", 
            "ImageId": "ami-0045895f07e3b53f1", 
            "UsageOperation": "RunInstances", 
            "BlockDeviceMappings": [
                {
                    "DeviceName": "/dev/xvda", 
                    "Ebs": {
                        "SnapshotId": "snap-0653cd833b909ec7d", 
                        "DeleteOnTermination": true, 
                        "VolumeType": "gp2", 
                        "VolumeSize": 10, 
                        "Encrypted": false
                    }
                }, 
                {
                    "DeviceName": "/dev/sdb", 
                    "VirtualName": "ephemeral0"
                }, 
                {
                    "DeviceName": "/dev/sdc", 
                    "VirtualName": "ephemeral1"
                }, 
                {
                    "DeviceName": "/dev/sdd", 
                    "VirtualName": "ephemeral2"
                }, 
                {
                    "DeviceName": "/dev/sde", 
                    "VirtualName": "ephemeral3"
                }
            ], 
            "Architecture": "x86_64", 
            "ImageLocation": "979382823631/bitnami-ghost-3.42.7-7-r03-linux-debian-10-x86_64-hvm-ebs-nami", 
            "RootDeviceType": "ebs", 
            "OwnerId": "979382823631", 
            "RootDeviceName": "/dev/xvda", 
            "CreationDate": "2021-12-01T05:54:42.000Z", 
            "Public": true, 
            "ImageType": "machine", 
            "Name": "bitnami-ghost-3.42.7-7-r03-linux-debian-10-x86_64-hvm-ebs-nami"
        }, 
        {
            "VirtualizationType": "hvm", 
            "EnaSupport": true, 
            "PlatformDetails": "Linux/UNIX", 
            "Hypervisor": "xen", 
            "ImageOwnerAlias": "amazon", 
            "State": "available", 
            "SriovNetSupport": "simple", 
            "ImageId": "ami-00458c099ab0e7541", 
            "UsageOperation": "RunInstances", 
            "BlockDeviceMappings": [
                {
                    "DeviceName": "/dev/xvda", 
                    "Ebs": {
                        "SnapshotId": "snap-0d9dfe3e9582150fa", 
                        "DeleteOnTermination": true, 
                        "VolumeType": "gp2", 
                        "VolumeSize": 8, 
                        "Encrypted": false
                    }
                }
            ], 
            "Architecture": "x86_64", 
            "ImageLocation": "amazon/aws-elasticbeanstalk-amzn-2018.03.20.x86_64-php54-hvm-202006041836", 
            "RootDeviceType": "ebs", 
            "OwnerId": "102837901569", 
            "RootDeviceName": "/dev/xvda", 
            "CreationDate": "2020-06-04T18:38:38.000Z", 
            "Public": true, 
            "ImageType": "machine", 
            "Name": "aws-elasticbeanstalk-amzn-2018.03.20.x86_64-php54-hvm-202006041836"
        }, 
        {
            "VirtualizationType": "hvm", 
            "Description": "This image may not be the latest version available and might include security vulnerabilities. Please check the latest, up-to-date, available version at https://bitnami.com/stacks.", 
            "PlatformDetails": "Linux/UNIX", 
            "EnaSupport": true, 
            "Hypervisor": "xen", 
            "State": "available", 
            "SriovNetSupport": "simple", 
            "ImageId": "ami-0045938b357d69bb1", 
            "UsageOperation": "RunInstances", 
            "BlockDeviceMappings": [
                {
                    "DeviceName": "/dev/xvda", 
                    "Ebs": {
                        "SnapshotId": "snap-0acb077985bc7898b", 
                        "DeleteOnTermination": true, 
                        "VolumeType": "gp2", 
                        "VolumeSize": 10, 
                        "Encrypted": false
                    }
                }, 
                {
                    "DeviceName": "/dev/sdb", 
                    "VirtualName": "ephemeral0"
                }, 
                {
                    "DeviceName": "/dev/sdc", 
                    "VirtualName": "ephemeral1"
                }, 
                {
                    "DeviceName": "/dev/sdd", 
                    "VirtualName": "ephemeral2"
                }, 
                {
                    "DeviceName": "/dev/sde", 
                    "VirtualName": "ephemeral3"
                }
            ], 
            "Architecture": "x86_64", 
            "ImageLocation": "979382823631/bitnami-wordpress-5.7.2-40-r15-linux-debian-10-x86_64-hvm-ebs-high-availability-nami", 
            "RootDeviceType": "ebs", 
            "OwnerId": "979382823631", 
            "RootDeviceName": "/dev/xvda", 
            "CreationDate": "2021-07-16T02:16:30.000Z", 
            "Public": true, 
            "ImageType": "machine", 
            "Name": "bitnami-wordpress-5.7.2-40-r15-linux-debian-10-x86_64-hvm-ebs-high-availability-nami"
        }, 
        {
            "VirtualizationType": "hvm", 
            "Description": "Cloud9 Cloud9AmazonLinux2 AMI", 
            "PlatformDetails": "Linux/UNIX", 
            "EnaSupport": true, 
            "Hypervisor": "xen", 
            "ImageOwnerAlias": "amazon", 
            "State": "available", 
            "SriovNetSupport": "simple", 
            "ImageId": "ami-00459671a0ded6662", 
            "UsageOperation": "RunInstances", 
            "BlockDeviceMappings": [
                {
                    "DeviceName": "/dev/xvda", 
                    "Ebs": {
                        "SnapshotId": "snap-0e3edfa566ceb76e3", 
                        "DeleteOnTermination": true, 
                        "VolumeType": "gp2", 
                        "VolumeSize": 10, 
                        "Encrypted": false
                    }
                }
            ], 
            "Architecture": "x86_64", 
            "ImageLocation": "amazon/Cloud9AmazonLinux2-2021-11-18T10-25", 
            "RootDeviceType": "ebs", 
            "OwnerId": "585441382316", 
            "RootDeviceName": "/dev/xvda", 
            "CreationDate": "2021-11-18T11:12:01.000Z", 
            "Public": true, 
            "ImageType": "machine", 
            "Name": "Cloud9AmazonLinux2-2021-11-18T10-25"
        }, 
        {
            "VirtualizationType": "hvm", 
            "EnaSupport": true, 
            "PlatformDetails": "Linux/UNIX", 
            "Hypervisor": "xen", 
            "State": "available", 
            "SriovNetSupport": "simple", 
            "ImageId": "ami-004596f64f41c9f2c", 
            "UsageOperation": "RunInstances", 
            "BlockDeviceMappings": [
                {
                    "DeviceName": "/dev/xvda", 
                    "Ebs": {
                        "SnapshotId": "snap-03719f667299efdc0", 
                        "DeleteOnTermination": true, 
                        "VolumeType": "standard", 
                        "VolumeSize": 8, 
                        "Encrypted": false
                    }
                }
            ], 
            "Architecture": "x86_64", 
            "ImageLocation": "068169053218/dremio-daasExecutor-test-274f0982-9164-4982-8b05-97e16ec143d9", 
            "RootDeviceType": "ebs", 
            "OwnerId": "068169053218", 
            "RootDeviceName": "/dev/xvda", 
            "CreationDate": "2021-06-16T04:19:20.000Z", 
            "Public": true, 
            "ImageType": "machine", 
            "Name": "dremio-daasExecutor-test-274f0982-9164-4982-8b05-97e16ec143d9"
        }, 
        {
            "VirtualizationType": "hvm", 
            "Description": "This image may not be the latest version available and might include security vulnerabilities. Please check the latest, up-to-date, available version at https://bitnami.com/stacks.", 
            "PlatformDetails": "Linux/UNIX", 
            "EnaSupport": true, 
            "Hypervisor": "xen", 
            "State": "available", 
            "ImageId": "ami-0045a7227274d9e5a", 
            "UsageOperation": "RunInstances", 
            "BlockDeviceMappings": [
                {
                    "DeviceName": "/dev/xvda", 
                    "Ebs": {
                        "SnapshotId": "snap-053d96d6e7b13fe4e", 
                        "DeleteOnTermination": true, 
                        "VolumeType": "gp2", 
                        "VolumeSize": 10, 
                        "Encrypted": false
                    }
                }, 
                {
                    "DeviceName": "/dev/sdb", 
                    "VirtualName": "ephemeral0"
                }, 
                {
                    "DeviceName": "/dev/sdc", 
                    "VirtualName": "ephemeral1"
                }, 
                {
                    "DeviceName": "/dev/sdd", 
                    "VirtualName": "ephemeral2"
                }, 
                {
                    "DeviceName": "/dev/sde", 
                    "VirtualName": "ephemeral3"
                }
            ], 
            "Architecture": "x86_64", 
            "ImageLocation": "979382823631/bitnami-tensorflow-serving-1.12.0-23-linux-debian-9-x86_64-hvm-ebs-nami", 
            "RootDeviceType": "ebs", 
            "OwnerId": "979382823631", 
            "RootDeviceName": "/dev/xvda", 
            "CreationDate": "2019-01-04T14:45:54.000Z", 
            "Public": true, 
            "ImageType": "machine", 
            "Name": "bitnami-tensorflow-serving-1.12.0-23-linux-debian-9-x86_64-hvm-ebs-nami"
        }, 
        {
            "VirtualizationType": "hvm", 
            "Description": "This image may not be the latest version available and might include security vulnerabilities. Please check the latest, up-to-date, available version at https://bitnami.com/stacks.", 
            "PlatformDetails": "Linux/UNIX", 
            "EnaSupport": true, 
            "Hypervisor": "xen", 
            "State": "available", 
            "SriovNetSupport": "simple", 
            "ImageId": "ami-0045b547c0231ac6c", 
            "UsageOperation": "RunInstances", 
            "BlockDeviceMappings": [
                {
                    "DeviceName": "/dev/xvda", 
                    "Ebs": {
                        "SnapshotId": "snap-0b55a356f62d464b0", 
                        "DeleteOnTermination": true, 
                        "VolumeType": "gp2", 
                        "VolumeSize": 10, 
                        "Encrypted": false
                    }
                }, 
                {
                    "DeviceName": "/dev/sdb", 
                    "VirtualName": "ephemeral0"
                }, 
                {
                    "DeviceName": "/dev/sdc", 
                    "VirtualName": "ephemeral1"
                }, 
                {
                    "DeviceName": "/dev/sdd", 
                    "VirtualName": "ephemeral2"
                }, 
                {
                    "DeviceName": "/dev/sde", 
                    "VirtualName": "ephemeral3"
                }
            ], 
            "Architecture": "x86_64", 

Answer 1

正确的答案可能是使用json ..。但是第二个例子似乎并不是有效的json (或者更多的likey是不完整的)，所以您可以使用regex.

print(re.findall('"(Name|ImageID)":\s*"(.*)"',file_contents))

Answer 2

解析json文件并获取属性

import json 
# Opening JSON file
item_list = []
f = open('/Users/Desktop/describe_images.txt') 
# read JSON object
data = json.load(f)
# loop
for item in data:
    item_list.append([item["Name"], item["ImageId"]])
f.close()

Answer 3

尝试这个片段，我假设“包含AMI名称的长文件”是一个带有字典列表的JSON文件。我假设这是因为您在这里粘贴的文件的“长版本”没有正确格式化。

import json

file_name = "aws.json"

with open(file_name) as freader:
    content = json.load(fp=freader)

names = []
image_ids = []
for c in content:
    names.append(c["Name"])
    image_ids.append(c["ImageId"])

print(names)
print(image_ids)

产出：

['temp-rp030-3', 'bitnami-wordpress-5.7.1-7-r06-linux-debian-10-x86_64-hvm-ebs-frontend-aurora-nami', 'SupportedImages Deep Learning AMI (Amazon Linux 2) Version 34.0-7a4f4a31-b0bf-493c-b3fe-3d5ba59858e7-ami-036251f870bf5b53d.4', 'bitnami-drupal-7.67-0-r50-linux-redhat-7.5-x86_64-hvm-ebs', 'bitnami-osclass-3.8.0-2-r50-linux-debian-9-x86_64-hvm-ebs', 'bitnami-ghost-3.42.7-7-r03-linux-debian-10-x86_64-hvm-ebs-nami', 'aws-elasticbeanstalk-amzn-2018.03.20.x86_64-php54-hvm-202006041836', 'bitnami-wordpress-5.7.2-40-r15-linux-debian-10-x86_64-hvm-ebs-high-availability-nami', 'Cloud9AmazonLinux2-2021-11-18T10-25', 'dremio-daasExecutor-test-274f0982-9164-4982-8b05-97e16ec143d9', 'bitnami-tensorflow-serving-1.12.0-23-linux-debian-9-x86_64-hvm-ebs-nami']
['ami-00455a561ee2a2221', 'ami-00455bda4a1b36dd7', 'ami-004566286db7148f6', 'ami-004583c651e1d7f07', 'ami-004585220878e1c1a', 'ami-0045895f07e3b53f1', 'ami-00458c099ab0e7541', 'ami-0045938b357d69bb1', 'ami-00459671a0ded6662', 'ami-004596f64f41c9f2c', 'ami-0045a7227274d9e5a']

如果它不能工作，请更新您的“长版本”的文件，并提供文件的完整副本。