Skip to content

cloudpathlib.GSClient

Bases: Client

Client class for Google Cloud Storage which handles authentication with GCP for GSPath instances. See documentation for the __init__ method for detailed authentication options.

Source code in cloudpathlib/gs/gsclient.py 
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
@register_client_class("gs")
class GSClient(Client):
    """Client class for Google Cloud Storage which handles authentication with GCP for
    [`GSPath`](../gspath/) instances. See documentation for the
    [`__init__` method][cloudpathlib.gs.gsclient.GSClient.__init__] for detailed authentication
    options.
    """

    def __init__(
        self,
        application_credentials: Optional[Union[str, os.PathLike]] = None,
        credentials: Optional["Credentials"] = None,
        project: Optional[str] = None,
        storage_client: Optional["StorageClient"] = None,
        file_cache_mode: Optional[Union[str, FileCacheMode]] = None,
        local_cache_dir: Optional[Union[str, os.PathLike]] = None,
        content_type_method: Optional[Callable] = mimetypes.guess_type,
        download_chunks_concurrently_kwargs: Optional[Dict[str, Any]] = None,
        timeout: Optional[float] = None,
        retry: Optional["Retry"] = None,
    ):
        """Class constructor. Sets up a [`Storage
        Client`](https://googleapis.dev/python/storage/latest/client.html).
        Supports the following authentication methods of `Storage Client`.

        - Environment variable `"GOOGLE_APPLICATION_CREDENTIALS"` containing a
          path to a JSON credentials file for a Google service account. See
          [Authenticating as a Service
          Account](https://cloud.google.com/docs/authentication/production).
        - File path to a JSON credentials file for a Google service account.
        - OAuth2 Credentials object and a project name.
        - Instantiated and already authenticated `Storage Client`.

        If multiple methods are used, priority order is reverse of list above
        (later in list takes priority). If no authentication methods are used,
        then the client will be instantiated as anonymous, which will only have
        access to public buckets.

        Args:
            application_credentials (Optional[Union[str, os.PathLike]]): Path to Google service
                account credentials file.
            credentials (Optional[Credentials]): The OAuth2 Credentials to use for this client.
                See documentation for [`StorageClient`](
                https://googleapis.dev/python/storage/latest/client.html).
            project (Optional[str]): The project which the client acts on behalf of. See
                documentation for [`StorageClient`](
                https://googleapis.dev/python/storage/latest/client.html).
            storage_client (Optional[StorageClient]): Instantiated [`StorageClient`](
                https://googleapis.dev/python/storage/latest/client.html).
            file_cache_mode (Optional[Union[str, FileCacheMode]]): How often to clear the file cache; see
                [the caching docs](https://cloudpathlib.drivendata.org/stable/caching/) for more information
                about the options in cloudpathlib.eums.FileCacheMode.
            local_cache_dir (Optional[Union[str, os.PathLike]]): Path to directory to use as cache
                for downloaded files. If None, will use a temporary directory. Default can be set with
                the `CLOUDPATHLIB_LOCAL_CACHE_DIR` environment variable.
            content_type_method (Optional[Callable]): Function to call to guess media type (mimetype) when
                writing a file to the cloud. Defaults to `mimetypes.guess_type`. Must return a tuple (content type, content encoding).
            download_chunks_concurrently_kwargs (Optional[Dict[str, Any]]): Keyword arguments to pass to
                [`download_chunks_concurrently`](https://cloud.google.com/python/docs/reference/storage/latest/google.cloud.storage.transfer_manager#google_cloud_storage_transfer_manager_download_chunks_concurrently)
                for sliced parallel downloads; Only available in `google-cloud-storage` version 2.7.0 or later, otherwise ignored and a warning is emitted.
            timeout (Optional[float]): Cloud Storage [timeout value](https://cloud.google.com/python/docs/reference/storage/1.39.0/retry_timeout)
            retry (Optional[google.api_core.retry.Retry]): Cloud Storage [retry configuration](https://cloud.google.com/python/docs/reference/storage/1.39.0/retry_timeout#configuring-retries)
        """
        if application_credentials is None:
            application_credentials = os.getenv("GOOGLE_APPLICATION_CREDENTIALS")

        if storage_client is not None:
            self.client = storage_client
        elif credentials is not None:
            self.client = StorageClient(credentials=credentials, project=project)
        elif application_credentials is not None:
            self.client = StorageClient.from_service_account_json(application_credentials)
        else:
            try:
                self.client = StorageClient()
            except DefaultCredentialsError:
                self.client = StorageClient.create_anonymous_client()

        self.download_chunks_concurrently_kwargs = download_chunks_concurrently_kwargs
        self.blob_kwargs: dict[str, Any] = {}
        if timeout is not None:
            self.timeout: float = timeout
            self.blob_kwargs["timeout"] = self.timeout
        if retry is not None:
            self.retry: Retry = retry
            self.blob_kwargs["retry"] = self.retry

        super().__init__(
            local_cache_dir=local_cache_dir,
            content_type_method=content_type_method,
            file_cache_mode=file_cache_mode,
        )

    def _get_metadata(self, cloud_path: GSPath) -> Optional[Dict[str, Any]]:
        bucket = self.client.bucket(cloud_path.bucket)
        blob = bucket.get_blob(cloud_path.blob)

        if blob is None:
            return None
        else:
            return {
                "etag": blob.etag,
                "size": blob.size,
                "updated": blob.updated,
                "content_type": blob.content_type,
                "md5_hash": blob.md5_hash,
            }

    def _download_file(self, cloud_path: GSPath, local_path: Union[str, os.PathLike]) -> Path:
        bucket = self.client.bucket(cloud_path.bucket)
        blob = bucket.get_blob(cloud_path.blob)

        local_path = Path(local_path)
        if transfer_manager is not None and self.download_chunks_concurrently_kwargs is not None:
            transfer_manager.download_chunks_concurrently(
                blob, local_path, **self.download_chunks_concurrently_kwargs
            )
        else:
            if transfer_manager is None and self.download_chunks_concurrently_kwargs is not None:
                warnings.warn(
                    "Ignoring `download_chunks_concurrently_kwargs` for version of google-cloud-storage that does not support them (<2.7.0)."
                )

            blob.download_to_filename(local_path, **self.blob_kwargs)

        return local_path

    def _is_file_or_dir(self, cloud_path: GSPath) -> Optional[str]:
        # short-circuit the root-level bucket
        if not cloud_path.blob:
            return "dir"

        bucket = self.client.bucket(cloud_path.bucket)
        blob = bucket.get_blob(cloud_path.blob)

        if blob is not None:
            return "file"
        else:
            prefix = cloud_path.blob
            if prefix and not prefix.endswith("/"):
                prefix += "/"

            # not a file, see if it is a directory
            f = bucket.list_blobs(max_results=1, prefix=prefix)

            # at least one key with the prefix of the directory
            if bool(list(f)):
                return "dir"
            else:
                return None

    def _exists(self, cloud_path: GSPath) -> bool:
        # short-circuit the root-level bucket
        if not cloud_path.blob:
            return self.client.bucket(cloud_path.bucket).exists()

        return self._is_file_or_dir(cloud_path) in ["file", "dir"]

    def _list_dir(self, cloud_path: GSPath, recursive=False) -> Iterable[Tuple[GSPath, bool]]:
        # shortcut if listing all available buckets
        if not cloud_path.bucket:
            if recursive:
                raise NotImplementedError(
                    "Cannot recursively list all buckets and contents; you can get all the buckets then recursively list each separately."
                )

            yield from (
                (self.CloudPath(f"{cloud_path.cloud_prefix}{str(b)}"), True)
                for b in self.client.list_buckets()
            )
            return

        bucket = self.client.bucket(cloud_path.bucket)

        prefix = cloud_path.blob
        if prefix and not prefix.endswith("/"):
            prefix += "/"
        if recursive:
            yielded_dirs = set()
            for o in bucket.list_blobs(prefix=prefix):
                # get directory from this path
                for parent in PurePosixPath(o.name[len(prefix) :]).parents:
                    # if we haven't surfaced this directory already
                    if parent not in yielded_dirs and str(parent) != ".":
                        yield (
                            self.CloudPath(
                                f"{cloud_path.cloud_prefix}{cloud_path.bucket}/{prefix}{parent}"
                            ),
                            True,  # is a directory
                        )
                        yielded_dirs.add(parent)
                yield (
                    self.CloudPath(f"{cloud_path.cloud_prefix}{cloud_path.bucket}/{o.name}"),
                    False,
                )  # is a file
        else:
            iterator = bucket.list_blobs(delimiter="/", prefix=prefix)

            # files must be iterated first for `.prefixes` to be populated:
            #   see: https://github.com/googleapis/python-storage/issues/863
            for file in iterator:
                yield (
                    self.CloudPath(f"{cloud_path.cloud_prefix}{cloud_path.bucket}/{file.name}"),
                    False,  # is a file
                )

            for directory in iterator.prefixes:
                yield (
                    self.CloudPath(f"{cloud_path.cloud_prefix}{cloud_path.bucket}/{directory}"),
                    True,  # is a directory
                )

    def _move_file(self, src: GSPath, dst: GSPath, remove_src: bool = True) -> GSPath:
        # just a touch, so "REPLACE" metadata
        if src == dst:
            bucket = self.client.bucket(src.bucket)
            blob = bucket.get_blob(src.blob)

            # See https://github.com/googleapis/google-cloud-python/issues/1185#issuecomment-431537214
            if blob.metadata is None:
                blob.metadata = {"updated": datetime.utcnow()}
            else:
                blob.metadata["updated"] = datetime.utcnow()
            blob.patch()

        else:
            src_bucket = self.client.bucket(src.bucket)
            dst_bucket = self.client.bucket(dst.bucket)

            src_blob = src_bucket.get_blob(src.blob)
            src_bucket.copy_blob(src_blob, dst_bucket, dst.blob, **self.blob_kwargs)

            if remove_src:
                src_blob.delete()

        return dst

    def _remove(self, cloud_path: GSPath, missing_ok: bool = True) -> None:
        file_or_dir = self._is_file_or_dir(cloud_path)
        if file_or_dir == "dir":
            blobs = [
                b.blob for b, is_dir in self._list_dir(cloud_path, recursive=True) if not is_dir
            ]
            bucket = self.client.bucket(cloud_path.bucket)
            for blob in blobs:
                bucket.get_blob(blob).delete()
        elif file_or_dir == "file":
            bucket = self.client.bucket(cloud_path.bucket)
            bucket.get_blob(cloud_path.blob).delete()
        else:
            # Does not exist
            if not missing_ok:
                raise FileNotFoundError(f"File does not exist: {cloud_path}")

    def _upload_file(self, local_path: Union[str, os.PathLike], cloud_path: GSPath) -> GSPath:
        bucket = self.client.bucket(cloud_path.bucket)
        blob = bucket.blob(cloud_path.blob)

        extra_args = {}
        if self.content_type_method is not None:
            content_type, _ = self.content_type_method(str(local_path))
            extra_args["content_type"] = content_type

        blob.upload_from_filename(str(local_path), **extra_args, **self.blob_kwargs)
        return cloud_path

    def _get_public_url(self, cloud_path: GSPath) -> str:
        bucket = self.client.get_bucket(cloud_path.bucket)
        blob = bucket.blob(cloud_path.blob)
        return blob.public_url

    def _generate_presigned_url(self, cloud_path: GSPath, expire_seconds: int = 60 * 60) -> str:
        bucket = self.client.get_bucket(cloud_path.bucket)
        blob = bucket.blob(cloud_path.blob)
        url = blob.generate_signed_url(
            version="v4", expiration=timedelta(seconds=expire_seconds), method="GET"
        )
        return url

Attributes

blob_kwargs: dict[str, Any] = {} instance-attribute

client = StorageClient() instance-attribute

content_type_method = content_type_method instance-attribute

download_chunks_concurrently_kwargs = download_chunks_concurrently_kwargs instance-attribute

file_cache_mode = file_cache_mode instance-attribute

retry: Retry = retry instance-attribute

timeout: float = timeout instance-attribute

Functions

CloudPath(cloud_path: Union[str, BoundedCloudPath]) -> BoundedCloudPath

Source code in cloudpathlib/client.py 
112
113
def CloudPath(self, cloud_path: Union[str, BoundedCloudPath]) -> BoundedCloudPath:
    return self._cloud_meta.path_class(cloud_path=cloud_path, client=self)  # type: ignore

__init__(application_credentials: Optional[Union[str, os.PathLike]] = None, credentials: Optional[Credentials] = None, project: Optional[str] = None, storage_client: Optional[StorageClient] = None, file_cache_mode: Optional[Union[str, FileCacheMode]] = None, local_cache_dir: Optional[Union[str, os.PathLike]] = None, content_type_method: Optional[Callable] = mimetypes.guess_type, download_chunks_concurrently_kwargs: Optional[Dict[str, Any]] = None, timeout: Optional[float] = None, retry: Optional[Retry] = None)

Class constructor. Sets up a Storage Client. Supports the following authentication methods of Storage Client.

  • Environment variable "GOOGLE_APPLICATION_CREDENTIALS" containing a path to a JSON credentials file for a Google service account. See Authenticating as a Service Account.
  • File path to a JSON credentials file for a Google service account.
  • OAuth2 Credentials object and a project name.
  • Instantiated and already authenticated Storage Client.

If multiple methods are used, priority order is reverse of list above (later in list takes priority). If no authentication methods are used, then the client will be instantiated as anonymous, which will only have access to public buckets.

Parameters:

Name Type Description Default
application_credentials Optional[Union[str, PathLike]]

Path to Google service account credentials file.

 None
credentials Optional[Credentials]

The OAuth2 Credentials to use for this client. See documentation for StorageClient.

 None
project Optional[str]

The project which the client acts on behalf of. See documentation for StorageClient.

 None
storage_client Optional[Client]

Instantiated StorageClient.

 None
file_cache_mode Optional[Union[str, FileCacheMode]]

How often to clear the file cache; see the caching docs for more information about the options in cloudpathlib.eums.FileCacheMode.

 None
local_cache_dir Optional[Union[str, PathLike]]

Path to directory to use as cache for downloaded files. If None, will use a temporary directory. Default can be set with the CLOUDPATHLIB_LOCAL_CACHE_DIR environment variable.

 None
content_type_method Optional[Callable]

Function to call to guess media type (mimetype) when writing a file to the cloud. Defaults to mimetypes.guess_type. Must return a tuple (content type, content encoding).

 guess_type
download_chunks_concurrently_kwargs Optional[Dict[str, Any]]

Keyword arguments to pass to download_chunks_concurrently for sliced parallel downloads; Only available in google-cloud-storage version 2.7.0 or later, otherwise ignored and a warning is emitted.

 None
timeout Optional[float]

Cloud Storage timeout value

 None
retry Optional[Retry]

Cloud Storage retry configuration

 None
Source code in cloudpathlib/gs/gsclient.py 
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
def __init__(
    self,
    application_credentials: Optional[Union[str, os.PathLike]] = None,
    credentials: Optional["Credentials"] = None,
    project: Optional[str] = None,
    storage_client: Optional["StorageClient"] = None,
    file_cache_mode: Optional[Union[str, FileCacheMode]] = None,
    local_cache_dir: Optional[Union[str, os.PathLike]] = None,
    content_type_method: Optional[Callable] = mimetypes.guess_type,
    download_chunks_concurrently_kwargs: Optional[Dict[str, Any]] = None,
    timeout: Optional[float] = None,
    retry: Optional["Retry"] = None,
):
    """Class constructor. Sets up a [`Storage
    Client`](https://googleapis.dev/python/storage/latest/client.html).
    Supports the following authentication methods of `Storage Client`.

    - Environment variable `"GOOGLE_APPLICATION_CREDENTIALS"` containing a
      path to a JSON credentials file for a Google service account. See
      [Authenticating as a Service
      Account](https://cloud.google.com/docs/authentication/production).
    - File path to a JSON credentials file for a Google service account.
    - OAuth2 Credentials object and a project name.
    - Instantiated and already authenticated `Storage Client`.

    If multiple methods are used, priority order is reverse of list above
    (later in list takes priority). If no authentication methods are used,
    then the client will be instantiated as anonymous, which will only have
    access to public buckets.

    Args:
        application_credentials (Optional[Union[str, os.PathLike]]): Path to Google service
            account credentials file.
        credentials (Optional[Credentials]): The OAuth2 Credentials to use for this client.
            See documentation for [`StorageClient`](
            https://googleapis.dev/python/storage/latest/client.html).
        project (Optional[str]): The project which the client acts on behalf of. See
            documentation for [`StorageClient`](
            https://googleapis.dev/python/storage/latest/client.html).
        storage_client (Optional[StorageClient]): Instantiated [`StorageClient`](
            https://googleapis.dev/python/storage/latest/client.html).
        file_cache_mode (Optional[Union[str, FileCacheMode]]): How often to clear the file cache; see
            [the caching docs](https://cloudpathlib.drivendata.org/stable/caching/) for more information
            about the options in cloudpathlib.eums.FileCacheMode.
        local_cache_dir (Optional[Union[str, os.PathLike]]): Path to directory to use as cache
            for downloaded files. If None, will use a temporary directory. Default can be set with
            the `CLOUDPATHLIB_LOCAL_CACHE_DIR` environment variable.
        content_type_method (Optional[Callable]): Function to call to guess media type (mimetype) when
            writing a file to the cloud. Defaults to `mimetypes.guess_type`. Must return a tuple (content type, content encoding).
        download_chunks_concurrently_kwargs (Optional[Dict[str, Any]]): Keyword arguments to pass to
            [`download_chunks_concurrently`](https://cloud.google.com/python/docs/reference/storage/latest/google.cloud.storage.transfer_manager#google_cloud_storage_transfer_manager_download_chunks_concurrently)
            for sliced parallel downloads; Only available in `google-cloud-storage` version 2.7.0 or later, otherwise ignored and a warning is emitted.
        timeout (Optional[float]): Cloud Storage [timeout value](https://cloud.google.com/python/docs/reference/storage/1.39.0/retry_timeout)
        retry (Optional[google.api_core.retry.Retry]): Cloud Storage [retry configuration](https://cloud.google.com/python/docs/reference/storage/1.39.0/retry_timeout#configuring-retries)
    """
    if application_credentials is None:
        application_credentials = os.getenv("GOOGLE_APPLICATION_CREDENTIALS")

    if storage_client is not None:
        self.client = storage_client
    elif credentials is not None:
        self.client = StorageClient(credentials=credentials, project=project)
    elif application_credentials is not None:
        self.client = StorageClient.from_service_account_json(application_credentials)
    else:
        try:
            self.client = StorageClient()
        except DefaultCredentialsError:
            self.client = StorageClient.create_anonymous_client()

    self.download_chunks_concurrently_kwargs = download_chunks_concurrently_kwargs
    self.blob_kwargs: dict[str, Any] = {}
    if timeout is not None:
        self.timeout: float = timeout
        self.blob_kwargs["timeout"] = self.timeout
    if retry is not None:
        self.retry: Retry = retry
        self.blob_kwargs["retry"] = self.retry

    super().__init__(
        local_cache_dir=local_cache_dir,
        content_type_method=content_type_method,
        file_cache_mode=file_cache_mode,
    )

clear_cache()

Clears the contents of the cache folder. Does not remove folder so it can keep being written to.

Source code in cloudpathlib/client.py 
115
116
117
118
119
120
121
122
123
124
def clear_cache(self):
    """Clears the contents of the cache folder.
    Does not remove folder so it can keep being written to.
    """
    if self._local_cache_dir.exists():
        for p in self._local_cache_dir.iterdir():
            if p.is_file():
                p.unlink()
            else:
                shutil.rmtree(p)

get_default_client() -> Client classmethod

Get the default client, which the one that is used when instantiating a cloud path instance for this cloud without a client specified.

Source code in cloudpathlib/client.py 
 98
 99
100
101
102
103
104
105
@classmethod
def get_default_client(cls) -> "Client":
    """Get the default client, which the one that is used when instantiating a cloud path
    instance for this cloud without a client specified.
    """
    if cls._default_client is None:
        cls._default_client = cls()
    return cls._default_client

set_as_default_client() -> None

Set this client instance as the default one used when instantiating cloud path instances for this cloud without a client specified.

Source code in cloudpathlib/client.py 
107
108
109
110
def set_as_default_client(self) -> None:
    """Set this client instance as the default one used when instantiating cloud path
    instances for this cloud without a client specified."""
    self.__class__._default_client = self