Merge pull request #330 from callumrollo/callum-patch-14

add file download functinality to ERDDAP

erddapy/core/url.py

@@ -439,3 +439,52 @@ def get_download_url(
 
     url = _distinct(url, distinct)
     return url
+
+
+download_formats = [
+    "asc",
+    "csv",
+    "csvp",
+    "csv0",
+    "dataTable",
+    "das",
+    "dds",
+    "dods",
+    "esriCsv",
+    "fgdc",
+    "geoJson",
+    "graph",
+    "help",
+    "html",
+    "iso19115",
+    "itx",
+    "json",
+    "jsonlCSV1",
+    "jsonlCSV",
+    "jsonlKVP",
+    "mat",
+    "nc",
+    "ncHeader",
+    "ncCF",
+    "ncCFHeader",
+    "ncCFMA",
+    "ncCFMAHeader",
+    "nccsv",
+    "nccsvMetadata",
+    "ncoJson",
+    "odvTxt",
+    "subset",
+    "tsv",
+    "tsvp",
+    "tsv0",
+    "wav",
+    "xhtml",
+    "kml",
+    "smallPdf",
+    "pdf",
+    "largePdf",
+    "smallPng",
+    "png",
+    "largePng",
+    "transparentPng",
+]

erddapy/erddapy.py

@@ -1,7 +1,10 @@
 """Pythonic way to access ERDDAP data."""
 
 import functools
+import hashlib
+from pathlib import Path
 from typing import Dict, List, Optional, Tuple, Union
+from urllib.request import urlretrieve
 
 import pandas as pd
 
@@ -16,6 +19,7 @@
     _distinct,
     _format_constraints_url,
     _quote_string_constraints,
+    download_formats,
     get_categorize_url,
     get_download_url,
     get_info_url,
@@ -471,3 +475,23 @@ def get_var_by_attr(self, dataset_id: OptionalStr = None, **kwargs) -> List[str]
             if has_value_flag is True:
                 vs.append(vname)
         return vs
+
+    def download_file(
+        self,
+        file_type,
+    ):
+        """Download the dataset to a file in a user specified format"""
+        file_type = file_type.lstrip(".")
+        if file_type not in download_formats:
+            raise ValueError(
+                f"Requested filetype {file_type} not available on ERDDAP",
+            )
+        url = self.get_download_url(response=file_type)
+        constraints_str = str(dict(sorted(self.constraints.items()))) + str(
+            sorted(self.variables),
+        )
+        constraints_hash = hashlib.shake_256(constraints_str.encode()).hexdigest(5)
+        file_name = Path(f"{self.dataset_id}_{constraints_hash}.{file_type}")
+        if not file_name.exists():
+            urlretrieve(url, file_name)
+        return file_name

tests/test_to_objects.py

@@ -197,3 +197,15 @@ def test_to_iris_griddap(dataset_griddap):
     """Test converting griddap to an iris cube."""
     cubes = dataset_griddap.to_iris()
     assert isinstance(cubes, iris.cube.CubeList)
+
+
+@pytest.mark.web
+def test_download_file(dataset_tabledap):
+    """Test direct download of tabledap dataset"""
+    fn = dataset_tabledap.download_file("nc")
+    ds = xr.load_dataset(fn)
+    assert ds["time"].name == "time"
+    assert ds["temperature"].name == "temperature"
+    dataset_tabledap.variables = dataset_tabledap.variables[::-1]
+    fn_new = dataset_tabledap.download_file("nc")
+    assert fn_new == fn