test(tests): added extract resource test [2024-11-25]

HerdingCats/explorer/cat_explore.py

@@ -458,7 +458,6 @@ def package_show_info_json(self, package_name: Union[str, dict, Any]) -> List[Di
         url = f"{base_url}?{urlencode(params)}" if params else base_url
 
         try:
-            print(url)
             response = self.cat_session.session.get(url)
             response.raise_for_status()
             data = response.json()
@@ -531,11 +530,17 @@ def package_search_condense_json_unpacked(
                 url to download
 
         # Example usage...
-        if __name__ == "__main__":
-            with CatSession("data.london.gov.uk") as session:
-                explorer = CatExplorer(session)
-                condensed_results = explorer.package_search_condense_json_unpacked("police")
-                pprint(condensed_results)
+        import HerdingCats as hc
+        from pprint import pprint
+
+        def main():
+            with hc.CatSession(hc.CkanDataCatalogues.LONDON_DATA_STORE) as session:
+                explore = hc.CkanCatExplorer(session)
+                packages_search = explore.package_search_condense_json_unpacked("police", 50)
+                pprint(packages_search)
+
+        if __name__ =="__main__":
+            main()
 
         """
         base_url = self.cat_session.base_url + CkanApiPaths.PACKAGE_SEARCH
@@ -790,6 +795,11 @@ def extract_resource_url(
 
         Returns:
         List[format, url]: The format of the resource and the URL.
+        [
+        'spreadsheet',
+        'https://data.london.gov.uk/download/violence-reduction-unit/1ef840d0-2c02-499c-ae40-382005b2a0c7/VRU%2520Dataset%2520Q1%2520April-Nov%25202023.xlsx'
+        ]
+
 
         Example:
             if __name__ == "__main__":
@@ -801,11 +811,6 @@ def extract_resource_url(
                     dl_link = explore.extract_resource_url(info, "VRU Q1 2023-24 Dataset")
                     print(dl_link)
 
-        [
-        'spreadsheet',
-        'https://data.london.gov.uk/download/violence-reduction-unit/1ef840d0-2c02-499c-ae40-382005b2a0c7/VRU%2520Dataset%2520Q1%2520April-Nov%25202023.xlsx'
-        ]
-
         """
 
         for item in package_info:

tests/ckan/test_ckan_extract_resource.py

@@ -0,0 +1,32 @@
+import pytest
+from HerdingCats.session.cat_session import CatSession
+from HerdingCats.explorer.cat_explore import CkanCatExplorer
+from HerdingCats.errors.cats_errors import CatExplorerError
+from loguru import logger
+
+CATALOGUES = ["https://data.london.gov.uk"]
+TEST_PACKAGE = "violence-reduction-unit"
+TEST_RESOURCE = "VRU Q1 2023-24 Dataset"
+
+def test_extract_resource_url():
+   """Test successful resource URL extraction"""
+   with CatSession(CATALOGUES[0]) as cat_session:
+       explorer = CkanCatExplorer(cat_session)
+       try:
+           # First get package info
+           package_info = explorer.package_show_info_json(TEST_PACKAGE)
+
+           # Extract resource URL
+           result = explorer.extract_resource_url(package_info, TEST_RESOURCE)
+
+           logger.success(result)
+
+           # Assertions
+           assert result is not None, "Should return result for known resource"
+           assert isinstance(result, list), "Should return a list"
+           assert len(result) == 2, "Should return format and URL"
+           assert isinstance(result[0], str), "Format should be string"
+           assert isinstance(result[1], str), "URL should be string"
+
+       except Exception as e:
+           pytest.fail(f"Failed to extract resource URL: {str(e)}")