Python-如何使用 Google Drive API 将文件上传到一个文件夹？

Question

使用 Google Drive API，我正在尝试将文件上传到 Google Drive。

请看下面的代码。 该代码成功运行，但不是将所有文件上传到一个文件夹，而是为它上传的每个文件创建单独的文件夹。

我相信我在代码中的这一行出错了： q="name='" + folder + "' and tramed=false and mimeType = 'application/vnd.google-apps.folder' and '{0}' in parents".format(parent_folder_id) 但无法弄清楚。 非常感谢任何帮助。

def uploadFile(service,pathname, mimetype, folder_id,replace):
    # Check if the file exists on google drive
    filename=os.path.split(pathname)[1]
    page_token = None
    q="name='" + filename + "' and trashed=false  and '{0}' in parents".format(folder_id)
    try:
        response = service.files().list(q= q, spaces='drive',
                                          fields="files(name, id)",
                                          pageToken=page_token).execute()
        if replace==True:
            file_id=response.get('files')[1]['id']
            file = service.files().get(fileId=file_id).execute()
             # File's new content.
            media_body = MediaFileUpload(pathname, resumable=True)
             # Send the request to the API.
            updated_file = service.files().update(
                fileId=file_id,
                body=file,
                newRevision=False,
                media_body=media_body).execute()
    except:
        file_metadata = {'name': filename, "parents": [folder_id]}
        media = MediaFileUpload(pathname,
                                mimetype=mimetype)
        file = service.files().create(body=file_metadata,

                                      media_body=media,
                                      fields='id').execute()
#################################
def UploadFiles(inifile, filespec, parent_folder):
    page_token = None
    # Retrieve the parent folder id from the parent folder name
    q="name='" + parent_folder + "' and trashed=false and mimeType = 'application/vnd.google-apps.folder'"
    try:
        response = service.files().list(q=q, spaces='drive',fields="files(name,id)",pageToken=page_token).execute()
    except:
        print("Parent folder",parent_folder,"was not found")
        return
    parent_folder_id = response.get('files')[0]['id']
    ##For loop to go through each file in filelist to upload
    for pathname in glob.glob(filespec):
    #for files in file_list:
        folder=pathname.split('_')[1]
        # Check if the folder exists
        q="name='" + folder + "' and trashed=false and mimeType = 'application/vnd.google-apps.folder' and '{0}' in parents".format(parent_folder_id)
        try:
            response = service.files().list(q=q, spaces='drive',fields="files(name,id,parent_id)").execute()
            folder_id = response.get('files')[0]['id']
        except:
            #if folder doesnt exist, create and upload
            file_metadata = {'name': folder,'mimeType':'application/vnd.google-apps.folder','parents':[parent_folder_id]}
            #createFolder(folder)
            new_folder = service.files().create(body=file_metadata, fields='id').execute()
            folder_id = new_folder.get('id')
        # Now upload the file!
        if pathname.endswith("pdf"):
            mimetype = 'application/pdf'
        else:
            mimetype = 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'
        #print("uploading file ",files," path",filepath," filename",filename, " folderid", folderid)
        uploadFile(service,pathname,mimetype,folder_id,True)

Answer 1

我不是 python 开发人员，因此您可能需要稍微处理一下代码。

您的搜索有问题

#Check if the folder exists
q="name='" + folder + "' and trashed=false and mimeType = 'application/vnd.google-apps.folder' and '{0}' in parents".format(parent_folder_id)

正确的格式是parents in 'ParentFolderId'应该给你。

q="name='" + folder + "' and trashed=false and mimeType = 'application/vnd.google-apps.folder' and parents in '{0}' in ".format(parent_folder_id)

另请记住，如果您想更新现有文件用户 files().update，则每次调用 service.files().create 都会创建一个新文件

Answer 2

我在一个项目中遇到了类似的问题，我已经对其进行了调整，以满足您使用以下虚拟数据上传 Google Drive 的需求：

from googleapiclient import discovery
from googleapiclient.http import MediaFileUpload, MediaIoBaseDownload
from httplib2 import Http
from oauth2client import file, client, tools
from pathlib import Path
import datetime

def gDriveFolder(service, name: str):
        Drive_service = service

        #Check if GDrive folder exists
        folder_metadata = {
            'name': name,
            'mimeType': 'application/vnd.google-apps.folder'
        }
        query = "name contains '{}' and mimeType='{}' and trashed=false".format(folder_metadata["name"],folder_metadata["mimeType"])
        response = Drive_service.files().list(q=query, pageSize=100, fields="nextPageToken, files(id, name, mimeType, size, parents, modifiedTime)").execute().get('files', [])
        if response.__len__() == 1 and response[0].get("name") == folder_metadata["name"]:
            folder_id = response[0].get("id")
        else:
            #creates GDrive folder
            gfolder = Drive_service.files().create(body=folder_metadata,
                                            fields='id').execute()
            folder_id = gfolder.get('id')
        
        return folder_id


def gDriveFolderFilesQuery(service, folder_name_for_q : str):
    Drive_service = service
    folder_id = gDriveFolder(Drive_service, folder_name_for_q)
    folder_query = "'%s' in parents" % folder_id 
    files_response = Drive_service.files().list(q=folder_query, pageSize=100, fields="nextPageToken, files(id, name, mimeType, size, parents, modifiedTime)").execute().get('files', [])
    file_names = dict()
    for log_file in files_response:
        file_names[log_file.get("name")] = log_file.get("id")
    return file_names

def uploadFile(service, pathname, mimetype_v, folder_id, folder_name_for_q, replace):
        Drive_service = service

        file_names = gDriveFolderFilesQuery(Drive_service, folder_name_for_q)

        dummy_file_path = Path(pathname)
        file_name = pathname.name
        
        if not mimetype_v:
            mimetype_v = 'text/plain'
        
        if replace:
            file_metadata = {
                'name': file_name,
                'mimeType': 'application/vnd.google-apps.script',
                'parents':[folder_id]
            }
            media = MediaFileUpload(dummy_file_path,
                                    mimetype=mimetype_v,
                                    resumable=True)
            file = Drive_service.files().create(body=file_metadata,
                                                media_body=media,
                                                fields='id').execute()

        #checks if the text.txt exists
        if file_name in list(file_names.keys()):
            file_id = file_names[file_name]
            media = MediaFileUpload(dummy_file_path,
                                    mimetype=mimetype_v,
                                    resumable=True)
            file = Drive_service.files().update(fileId=file_id,body=None,
                                                media_body=media).execute()

        else:
            file_metadata = {
                'name': file_name,
                'mimeType': 'application/vnd.google-apps.script',
                'parents':[folder_id]
            }
            media = MediaFileUpload(dummy_file_path,
                                    mimetype=mimetype_v,
                                    resumable=True)
            file = Drive_service.files().create(body=file_metadata,
                                                media_body=media,
                                                fields='id').execute()

def uploadFiles(service, DirectoryFolder, mimetype_v, folder_id, folder_name_for_q, replace):

    for a_file in DirectoryFolder.glob("*"):
        if a_file.is_dir():
            continue
        uploadFile(service, a_file, mimetype_v, folder_id, folder_name_for_q, replace)



if __name__ == "__main__":
    
    SCOPES = ['https://www.googleapis.com/auth/drive', 
                        'https://www.googleapis.com/auth/drive.file', 
                        'https://www.googleapis.com/auth/drive.appdata',
                        'https://www.googleapis.com/auth/drive.metadata', 
                        'https://www.googleapis.com/auth/drive.activity']


    store = file.Storage('storage.json')
    creds = store.get()
    if not creds or creds.invalid:
        flow = client.flow_from_clientsecrets('client.json', SCOPES)
        creds = tools.run_flow(flow, store)
    DRIVE = discovery.build('drive', 'v3', http=creds.authorize(Http())) #be prepared to be authorized

    #make a dummy folder
    dummy_file_directory = Path("dummy/")
    dummy_file_directory.mkdir(parents=True, exist_ok=True)

    #create a set list of dummy files
    how_many_files = 5
    for i in range(how_many_files+1):
        dummy_file = dummy_file_directory / ("test_num_%s.txt" % i)
        data = "current date and time for iteration %s is %s" % (i, datetime.datetime.now())
        with open(str(dummy_file), "w", encoding='utf-8') as f:
            f.write(data) 

    folder_name_for_q = "folder_for_priya"
    folder_id = gDriveFolder(DRIVE, folder_name_for_q)

    mimetype_v = 'text/plain'
    uploadFiles(DRIVE, dummy_file_directory, mimetype_v, folder_id, folder_name_for_q, replace=False)

我会尽我所能快速简要介绍正在发生的事情。 运行主程序，声明凭据和范围。 （此授权方法改编自以下指南）

接下来创建一个虚拟文件夹，然后使用datetime模块填充虚拟文件（在本例中为 5 个文本文件）及其各自的迭代和时间戳。

之后，定义了一个新变量来给出要在谷歌驱动器上的文件夹的名称。

gDriveFolder方法检查这样的 GoogleDrive 目录是否已经存在。 无论是否存在这样的文件夹，都会返回该文件夹的文件夹 ID。

接下来调用uploadFiles方法，它采用pathlib.Path object 在其中传递，并遍历它检测到的可能不是文件夹的文件。 对于文件夹dummy_file_directory中的每个文件，都会执行方法uploadFile 。

最后， uploadFile获取文件及其各自的 mimetype，并通过首先调用gDriveFolderFilesQuery方法检查此类文件是否存在，并验证上传文件是否已在 GoogleDrive 目录中。

希望演练足够简单，可以实现您想要的实现。