Pull images with API keys when token is missing (#89)

* Pull images with API keys when token is missing

* added option during export for token

* bump version number

Co-authored-by: Simon Edwardsson <[email protected]>

Author: andreaazzini

darwin/cli.py

@@ -69,7 +69,7 @@ def run(args, parser):
         elif args.action == "report":
             f.dataset_report(args.dataset, args.granularity or "day")
         elif args.action == "export":
-            f.export_dataset(args.dataset, args.annotation_class, args.name)
+            f.export_dataset(args.dataset, args.include_url_token, args.annotation_class, args.name)
         elif args.action == "releases":
             f.dataset_list_releases(args.dataset)
         elif args.action == "pull":

darwin/cli_functions.py

@@ -199,7 +199,9 @@ def dataset_report(dataset_slug: str, granularity) -> Path:
         _error(f"Dataset '{dataset_slug}' does not exist.")
 
 
-def export_dataset(dataset_slug: str, annotation_class_ids: Optional[List] = None, name: Optional[str] = None):
+def export_dataset(
+    dataset_slug: str, include_url_token: bool, annotation_class_ids: Optional[List] = None, name: Optional[str] = None
+):
     """Create a new release for the dataset
 
     Parameters
@@ -214,7 +216,7 @@ def export_dataset(dataset_slug: str, annotation_class_ids: Optional[List] = Non
     client = _load_client(offline=False)
     identifier = DatasetIdentifier.parse(dataset_slug)
     ds = client.get_remote_dataset(identifier)
-    ds.export(annotation_class_ids=annotation_class_ids, name=name)
+    ds.export(annotation_class_ids=annotation_class_ids, name=name, include_url_token=include_url_token)
     identifier.version = name
     print(f"Dataset {dataset_slug} successfully exported to {identifier}")
 

darwin/dataset/download_manager.py

@@ -2,14 +2,14 @@
 import json
 import time
 from pathlib import Path
-from typing import Optional
 
 import requests
 
 from darwin.utils import is_image_extension_allowed
 
 
 def download_all_images_from_annotations(
+    api_key: str,
     api_url: str,
     annotations_path: Path,
     images_path: Path,
@@ -21,6 +21,8 @@ def download_all_images_from_annotations(
 
     Parameters
     ----------
+    api_key : str
+        API Key of the current team
     api_url : str
         Url of the darwin API (e.g. 'https://darwin.v7labs.com/api/')
     annotations_path : Path
@@ -73,17 +75,23 @@ def download_all_images_from_annotations(
     # Create the generator with the partial functions
     count = len(annotations_to_download_path)
     generator = lambda: (
-        functools.partial(download_image_from_annotation, api_url, annotation_path, images_path, annotation_format)
+        functools.partial(
+            download_image_from_annotation, api_key, api_url, annotation_path, images_path, annotation_format
+        )
         for annotation_path in annotations_to_download_path
     )
     return generator, count
 
 
-def download_image_from_annotation(api_url: str, annotation_path: Path, images_path: str, annotation_format: str):
+def download_image_from_annotation(
+    api_key: str, api_url: str, annotation_path: Path, images_path: str, annotation_format: str
+):
     """Helper function: dispatcher of functions to download an image given an annotation
 
     Parameters
     ----------
+    api_key : str
+        API Key of the current team
     api_url : str
         Url of the darwin API (e.g. 'https://darwin.v7labs.com/api/')
     annotation_path : Path
@@ -94,20 +102,22 @@ def download_image_from_annotation(api_url: str, annotation_path: Path, images_p
         Format of the annotations. Currently only JSON is supported
     """
     if annotation_format == "json":
-        download_image_from_json_annotation(api_url, annotation_path, images_path)
+        download_image_from_json_annotation(api_key, api_url, annotation_path, images_path)
     elif annotation_format == "xml":
         print("sorry can't let you do that dave")
         raise NotImplementedError
         # download_image_from_xml_annotation(annotation_path, images_path)
 
 
-def download_image_from_json_annotation(api_url: str, annotation_path: Path, image_path: str):
+def download_image_from_json_annotation(api_key: str, api_url: str, annotation_path: Path, image_path: str):
     """
     Helper function: downloads an image given a .json annotation path
     and renames the json after the image filename
 
     Parameters
     ----------
+    api_key : str
+        API Key of the current team
     api_url : str
         Url of the darwin API (e.g. 'https://darwin.v7labs.com/api/')
     annotation_path : Path
@@ -122,10 +132,10 @@ def download_image_from_json_annotation(api_url: str, annotation_path: Path, ima
     original_filename_suffix = Path(annotation["image"]["original_filename"]).suffix
     path = Path(image_path) / (annotation_path.stem + original_filename_suffix)
 
-    download_image(annotation["image"]["url"], path)
+    download_image(annotation["image"]["url"], path, api_key)
 
 
-def download_image(url: str, path: Path, verbose: Optional[bool] = False):
+def download_image(url: str, path: Path, api_key: str):
     """Helper function: downloads one image from url.
 
     Parameters
@@ -134,17 +144,18 @@ def download_image(url: str, path: Path, verbose: Optional[bool] = False):
         Url of the image to download
     path : Path
         Path where to download the image, with filename
-    verbose : bool
-        Flag for the logging level
+    api_key : str
+        API Key of the current team
     """
     if path.exists():
         return
-    if verbose:
-        print(f"Dowloading {path.name}")
     TIMEOUT = 60
     start = time.time()
     while True:
-        response = requests.get(url, stream=True)
+        if "token" in url:
+            response = requests.get(url, stream=True)
+        else:
+            response = requests.get(url, headers={"Authorization": f"ApiKey {api_key}"}, stream=True)
         # Correct status: download image
         if response.status_code == 200:
             with open(str(path), "wb") as file:

darwin/dataset/remote_dataset.py

@@ -233,8 +233,12 @@ def pull(
             # No images will be downloaded
             return None, 0
 
+        team_config = self.client.config.get_team(self.team)
+        api_key = team_config.get("api_key")
+
         # Create the generator with the download instructions
         progress, count = download_all_images_from_annotations(
+            api_key=api_key,
             api_url=self.client.url,
             annotations_path=annotations_dir,
             images_path=self.local_images_path,
@@ -295,7 +299,7 @@ def fetch_remote_classes(self):
             "annotation_classes"
         ]
 
-    def export(self, name: str, annotation_class_ids: Optional[List[str]] = None):
+    def export(self, name: str, annotation_class_ids: Optional[List[str]] = None, include_url_token: bool = False):
         """Create a new release for the dataset
 
         Parameters
@@ -304,10 +308,16 @@ def export(self, name: str, annotation_class_ids: Optional[List[str]] = None):
             Name of the release
         annotation_class_ids: List
             List of the classes to filter
+        include_url_token: bool
+            Should the image url in the export be include a token enabling access without team membership
         """
         if annotation_class_ids is None:
             annotation_class_ids = []
-        payload = {"annotation_class_ids": annotation_class_ids, "name": name}
+        payload = {
+            "annotation_class_ids": annotation_class_ids,
+            "name": name,
+            "include_export_token": include_url_token,
+        }
         self.client.post(
             f"/datasets/{self.dataset_id}/exports",
             payload=payload,

darwin/options.py

@@ -95,6 +95,13 @@ def __init__(self):
         parser_export.add_argument("dataset", type=str, help="Remote dataset name to export.")
         parser_export.add_argument("name", type=str, help="Name with with the version gets tagged.")
         parser_export.add_argument("annotation_class", type=str, nargs="?", help="List of class filters")
+        parser_export.add_argument(
+            "--include-url-token",
+            default=False,
+            action="store_true",
+            help="Each annotation file includes a url with an access token."
+            "Warning, anyone with the url can access the images, even without being a team member",
+        )
 
         # Releases
         parser_dataset_version = dataset_action.add_parser("releases", help="Available version of a dataset.")

setup.py

@@ -5,7 +5,7 @@
 
 setuptools.setup(
     name="darwin-py",
-    version="0.5.1",
+    version="0.5.2",
     author="V7",
     author_email="[email protected]",
     description="Library and command line interface for darwin.v7labs.com",