使用Bitbucket Pipeline将整个Bitbucket repo上传到S3

Question

我正在使用Bitbuckets Pipeline.我希望它将我的仓库(非常小)的全部内容推送到S3.我不想将其压缩,推送到S3然后解压缩.我只是希望它在我的Bitbucket仓库中采用现有的文件/文件夹结构并将其推送到S3.

yaml文件和.py文件应该是什么样的？

这是当前的yaml文件:

image: python:3.5.1

pipelines:
  branches:
    master:
      - step:
          script:
            # - apt-get update # required to install zip
            # - apt-get install -y zip # required if you want to zip repository objects
            - pip install boto3==1.3.0 # required for s3_upload.py
            # the first argument is the name of the existing S3 bucket to upload the artefact to
            # the second argument is the artefact to be uploaded
            # the third argument is the the bucket key
            # html files
            - python s3_upload.py my-bucket-name html/index_template.html html/index_template.html # run the deployment script
            # Example command line parameters. Replace with your values
            #- python s3_upload.py bb-s3-upload SampleApp_Linux.zip SampleApp_Linux # run the deployment script

这是我目前的python:

from __future__ import print_function
import os
import sys
import argparse
import boto3
from botocore.exceptions import ClientError

def upload_to_s3(bucket, artefact, bucket_key):
    """
    Uploads an artefact to Amazon S3
    """
    try:
        client = boto3.client('s3')
    except ClientError as err:
        print("Failed to create boto3 client.\n" + str(err))
        return False
    try:
        client.put_object(
            Body=open(artefact, 'rb'),
            Bucket=bucket,
            Key=bucket_key
        )
    except ClientError as err:
        print("Failed to upload artefact to S3.\n" + str(err))
        return False
    except IOError as err:
        print("Failed to access artefact in this directory.\n" + str(err))
        return False
    return True


def main():

    parser = argparse.ArgumentParser()
    parser.add_argument("bucket", help="Name of the existing S3 bucket")
    parser.add_argument("artefact", help="Name of the artefact to be uploaded to S3")
    parser.add_argument("bucket_key", help="Name of the S3 Bucket key")
    args = parser.parse_args()

    if not upload_to_s3(args.bucket, args.artefact, args.bucket_key):
        sys.exit(1)

if __name__ == "__main__":
    main()

这要求我将yaml文件中repo中的每个文件列为另一个命令.我只是希望它抓住所有内容并将其上传到S3.

Answer 1

我自己想出来了。这是 python 文件“s3_upload.py”

from __future__ import print_function
import os
import sys
import argparse
import boto3
#import zipfile
from botocore.exceptions import ClientError

def upload_to_s3(bucket, artefact, is_folder, bucket_key):
    try:
        client = boto3.client('s3')
    except ClientError as err:
        print("Failed to create boto3 client.\n" + str(err))
        return False
    if is_folder == 'true':
        for root, dirs, files in os.walk(artefact, topdown=False):
            print('Walking it')
            for file in files:
                #add a check like this if you just want certain file types uploaded
                #if file.endswith('.js'):
                try:
                    print(file)
                    client.upload_file(os.path.join(root, file), bucket, os.path.join(root, file))
                except ClientError as err:
                    print("Failed to upload artefact to S3.\n" + str(err))
                    return False
                except IOError as err:
                    print("Failed to access artefact in this directory.\n" + str(err))
                    return False
                #else:
                #    print('Skipping file:' + file)
    else:
        print('Uploading file ' + artefact)
        client.upload_file(artefact, bucket, bucket_key)
    return True


def main():

    parser = argparse.ArgumentParser()
    parser.add_argument("bucket", help="Name of the existing S3 bucket")
    parser.add_argument("artefact", help="Name of the artefact to be uploaded to S3")
    parser.add_argument("is_folder", help="True if its the name of a folder")
    parser.add_argument("bucket_key", help="Name of file in bucket")
    args = parser.parse_args()

    if not upload_to_s3(args.bucket, args.artefact, args.is_folder, args.bucket_key):
        sys.exit(1)

if __name__ == "__main__":
    main()

这是 bitbucket-pipelines.yml 文件：

---
image: python:3.5.1

pipelines:
  branches:
    dev:
      - step:
          script:
            - pip install boto3==1.4.1 # required for s3_upload.py
            - pip install requests
            # the first argument is the name of the existing S3 bucket to upload the artefact to
            # the second argument is the artefact to be uploaded
            # the third argument is if the artefact is a folder
            # the fourth argument is the bucket_key to use
            - python s3_emptyBucket.py dev-slz-processor-repo
            - python s3_upload.py dev-slz-processor-repo lambda true lambda
            - python s3_upload.py dev-slz-processor-repo node_modules true node_modules
            - python s3_upload.py dev-slz-processor-repo config.dev.json false config.json
    stage:
      - step:
          script:
            - pip install boto3==1.3.0 # required for s3_upload.py
            - python s3_emptyBucket.py staging-slz-processor-repo
            - python s3_upload.py staging-slz-processor-repo lambda true lambda
            - python s3_upload.py staging-slz-processor-repo node_modules true node_modules
            - python s3_upload.py staging-slz-processor-repo config.staging.json false config.json
    master:
      - step:
          script:
            - pip install boto3==1.3.0 # required for s3_upload.py
            - python s3_emptyBucket.py prod-slz-processor-repo
            - python s3_upload.py prod-slz-processor-repo lambda true lambda
            - python s3_upload.py prod-slz-processor-repo node_modules true node_modules
            - python s3_upload.py prod-slz-processor-repo config.prod.json false config.json

作为 dev 分支的示例，它获取“lambda”文件夹中的所有内容，遍历该文件夹的整个结构，对于找到的每个项目，将其上传到 dev-slz-processor-repo 存储桶

最后，这里有一个有用的函数“s3_emptyBucket”，用于在上传新对象之前从存储桶中删除所有对象：

from __future__ import print_function
import os
import sys
import argparse
import boto3
#import zipfile
from botocore.exceptions import ClientError

def empty_bucket(bucket):
    try:
        resource = boto3.resource('s3')
    except ClientError as err:
        print("Failed to create boto3 resource.\n" + str(err))
        return False
    print("Removing all objects from bucket: " + bucket)
    resource.Bucket(bucket).objects.delete()
    return True


def main():

    parser = argparse.ArgumentParser()
    parser.add_argument("bucket", help="Name of the existing S3 bucket to empty")
    args = parser.parse_args()

    if not empty_bucket(args.bucket):
        sys.exit(1)

if __name__ == "__main__":
    main()