Implement first end-to-end scraper with openfreemap data

scraper/src/maps2zim/context.py

@@ -41,6 +41,9 @@ class Context:
     # temporary folder to store temporary assets (e.g. cached API response)
     tmp_folder: Path
 
+    # folder to fetch / store downloaded assets (can be reused across runs)
+    assets_folder: Path
+
     # folder where the ZIM will be built
     output_folder: Path = Path(os.getenv("MAPS_OUTPUT", "output"))
 
@@ -87,6 +90,14 @@ class Context:
         NAME, level=logging.DEBUG, log_format=DEFAULT_FORMAT_WITH_THREADS
     )
 
+    # ------------------------------
+    # Maps specific arguments
+    # ------------------------------
+
+    # By default, download only monaco area ; specify planet to download the whole
+    # planet
+    area: str = "monaco"
+
     @classmethod
     def setup(cls, **kwargs: Any):
         new_instance = cls(**kwargs)

scraper/src/maps2zim/entrypoint.py

@@ -107,6 +107,14 @@ def prepare_context(raw_args: list[str], tmpdir: str) -> None:
         dest="tmp_folder",
     )
 
+    parser.add_argument(
+        "--assets",
+        help="Folder folder to fetch / store downloaded assets (can be reused across "
+        "runs)",
+        type=Path,
+        dest="assets_folder",
+    )
+
     parser.add_argument("--debug", help="Enable verbose output", action="store_true")
 
     parser.add_argument(
@@ -134,6 +142,11 @@ def prepare_context(raw_args: list[str], tmpdir: str) -> None:
         help="Contact information to pass in User-Agent headers",
     )
 
+    parser.add_argument(
+        "--area",
+        help=f"Area to download, either planet or monaco. Default: {Context.area!s}",
+    )
+
     args = parser.parse_args(raw_args)
 
     # Ignore unset values so they do not override the default specified in Context
@@ -147,6 +160,9 @@ def prepare_context(raw_args: list[str], tmpdir: str) -> None:
         else:
             args_dict["tmp_folder"] = Path(tmpdir)
 
+    if not args_dict.get("assets_folder", None):
+        args_dict["assets_folder"] = args_dict["tmp_folder"] / "assets"
+
     args_dict["_current_thread_workitem"] = threading.local()
     args_dict["web_session"] = get_session()