Azure 存储 Python SDK：将文件上传到 Azure Blob 存储而不将其写入我的磁盘

Question

我有很多来自我的 Apache 服务器的图像，我想将它们放到 azure 中。 我负担不起按顺序进行，所以我会在之后添加线程。我可以从给定的 URL 访问这些图像并在其上构建一个列表。简单的。 现在我没有足够的磁盘空间来下载图像并上传它然后删除它。我想要更干净的东西。

现在有没有办法做到这一点？

类似：

block_blob_service.AZURECOMMAND(container, source_URL, target_blob_name)

如果不可能，是否有解决方法？

这是我今天拥有的完整代码（下载然后上传，我想避免）： 编辑：感谢 Gaurav Mantri，我现在明白了。我更新了代码。

    import requests
    from bs4 import BeautifulSoup
    from os.path  import basename
    import os
    import sys
    import urllib
    import urllib2
    import urlparse
    import argparse
    import json
    import config
    import random
    import base64
    import datetime
    import time
    import string
    from azure.storage import CloudStorageAccount, AccessPolicy
    from azure.storage.blob import BlockBlobService, PageBlobService, AppendBlobService
    from azure.storage.models import CorsRule, Logging, Metrics, RetentionPolicy, ResourceTypes, AccountPermissions
    from azure.storage.blob.models import BlobBlock, ContainerPermissions, ContentSettings
    #from azure.storage.blob import BlobService
    from azure.storage import *

    #from azure.storage.blob.blobservice import BlobService

    CURRENT_DIR = os.getcwd()
    STORING_DIRECTORY_NAME = "stroage_scrapped_images"
    STORING_DIRECTORY = CURRENT_DIR+"/"+STORING_DIRECTORY_NAME

    if not os.path.exists(STORING_DIRECTORY):
        os.makedirs(STORING_DIRECTORY)

    def randomword(length):
       letters = string.ascii_lowercase
       return ''.join(random.choice(letters) for i in range(length))

    startdate = time.clock()

    metadata_loaded = {'Owner': 'ToBeAddedSoon', 'Date_Of_Upload': startdate, 'VAR_2': 'VAL_VAR_2','VAR_3': 'VAL_VAR_3','VAR_4': 'VAL_VAR_4'}

    with open("credentials.json", 'r') as f:
        data = json.loads(f.read())
        StoAcc_var_name = data["storagacc"]["Accountname"]
        StoAcc_var_key = data["storagacc"]["AccountKey"]
        StoAcc_var_container = data["storagacc"]["Container"]
        #print StoAcc_var_name, StoAcc_var_key, StoAcc_var_container


    def copy_azure_files(source_url,destination_object,destination_container):
            blob_service = BlockBlobService(account_name=StoAcc_var_name, account_key=StoAcc_var_key)
            blob_service.copy_blob(destination_container, destination_object, source_url)

    block_blob_service = BlockBlobService(account_name=StoAcc_var_name, account_key=StoAcc_var_key)

    def upload_func(container,blobname,filename):
        start = time.clock()
        block_blob_service.create_blob_from_path(
            container,
            blobname,
            filename)
        elapsed = time.clock()
        elapsed = elapsed - start
        print "*** DEBUG ***  Time spent uploading API " , filename , " is : " , elapsed , " in Bucket/container : " , container

    #URL_TARGET = "https://mouradcloud.westeurope.cloudapp.azure.com/blog/blog/category/food/"
    URL_TARGET = "https://www.cdiscount.com/search/10/telephone.html"
    base_url = URL_TARGET
    out_folder = '/tmp'
    r = requests.get(URL_TARGET)
    data = r.text
    soup = BeautifulSoup(data, "lxml")


    for link in soup.find_all('img'):
            src = link
            image_url = link.get("src")
            while image_url is not None :
                    if 'http' in image_url:
                            blocks = []
                            if image_url.endswith(('.png', '.jpg', '.jpeg')):
                                    print " ->>>>>>>>>>>>>> THIS IS AN IMAGE ... PROCESSING "
                                    file_name_downloaded = basename(image_url)
                                    file_name_path_local = STORING_DIRECTORY+"/"+file_name_downloaded
                                    with open(file_name_path_local, "wb") as f:
                                            f.write(requests.get(image_url).content)
                                    filename_in_clouddir="uploads"+"/"+file_name_downloaded
                                    #upload_func(StoAcc_var_container,filename_in_clouddir,file_name_path_local)
                                    copy_azure_files(image_url,filename_in_clouddir,StoAcc_var_container)


                                    break
                            else :
                                    print " ->>>>>>>>>>>>>> THIS NOT AN IMAGE ... SKIPPING "
                                    break
                    else :
                            print " ->>>>>>>>>>>>>> THIS IS A LOCAL IMAGE ... SKIPPING "
                            break
            continue

Answer 1

确实有这样的东西：copy_blob

block_blob_service.copy_blob(container, target_blob_name, source_URL)

请记住，此复制操作是异步服务器端复制，因此：

• 副本的来源应公开。
• 您必须等待复制操作完成才能删除源项目。

更新

修改后的代码（我没试过运行）

    import requests
    from bs4 import BeautifulSoup
    from os.path  import basename
    import os
    import sys
    import urllib
    import urllib2
    import urlparse
    import argparse
    import json
    import config
    import random
    import base64
    import datetime
    import time
    import string
    from azure.storage import CloudStorageAccount, AccessPolicy
    from azure.storage.blob import BlockBlobService, PageBlobService, AppendBlobService
    from azure.storage.models import CorsRule, Logging, Metrics, RetentionPolicy, ResourceTypes, AccountPermissions
    from azure.storage.blob.models import BlobBlock, ContainerPermissions, ContentSettings

    CURRENT_DIR = os.getcwd()
    STORING_DIRECTORY_NAME = "stroage_scrapped_images"
    STORING_DIRECTORY = CURRENT_DIR+"/"+STORING_DIRECTORY_NAME

    if not os.path.exists(STORING_DIRECTORY):
        os.makedirs(STORING_DIRECTORY)

    def randomword(length):
       letters = string.ascii_lowercase
       return ''.join(random.choice(letters) for i in range(length))

    startdate = time.clock()

    metadata_loaded = {'Owner': 'ToBeAddedSoon', 'Date_Of_Upload': startdate, 'VAR_2': 'VAL_VAR_2','VAR_3': 'VAL_VAR_3','VAR_4': 'VAL_VAR_4'}

    with open("credentials.json", 'r') as f:
        data = json.loads(f.read())
        StoAcc_var_name = data["storagacc"]["Accountname"]
        StoAcc_var_key = data["storagacc"]["AccountKey"]
        StoAcc_var_container = data["storagacc"]["Container"]
        #print StoAcc_var_name, StoAcc_var_key, StoAcc_var_container
    block_blob_service = BlockBlobService(account_name=StoAcc_var_name, account_key=StoAcc_var_key)

    def upload_func(container,blobname,sourceurl):
        start = time.clock()
        block_blob_service.copy_blob(
            container,
            blobname,
            sourceurl)
        elapsed = time.clock()
        elapsed = elapsed - start
        print "*** DEBUG ***  Time spent uploading API " , filename , " is : " , elapsed , " in Bucket/container : " , container

    #URL_TARGET = "https://mouradcloud.westeurope.cloudapp.azure.com/blog/blog/category/food/"
    URL_TARGET = "https://www.cdiscount.com/search/10/telephone.html"
    base_url = URL_TARGET
    out_folder = '/tmp'
    r = requests.get(URL_TARGET)
    data = r.text
    soup = BeautifulSoup(data, "lxml")

    for link in soup.find_all('img'):
            src = link
            image_url = link.get("src")
            while image_url is not None :
                    if 'http' in image_url:
                            blocks = []
                            if image_url.endswith(('.png', '.jpg', '.jpeg')):
                                    print " ->>>>>>>>>>>>>> THIS IS AN IMAGE ... PROCESSING "
                                    file_name_downloaded = basename(image_url)
                                    filename_in_clouddir="uploads"+"/"+file_name_downloaded
                                    upload_func(StoAcc_var_container,filename_in_clouddir,image_url)


                                    break
                            else :
                                    print " ->>>>>>>>>>>>>> THIS NOT AN IMAGE ... SKIPPING "
                                    break
                    else :
                            print " ->>>>>>>>>>>>>> THIS IS A LOCAL IMAGE ... SKIPPING "
                            break
            continue