Updates 2024-08-28 - Added more functionalty with search methods

README.md

@@ -4,25 +4,38 @@
 
 >[!IMPORTANT]
 > THIS IS A WORK IN PROGRESS
+> Using London's Datastore to test functionality
 
 # Purpose
 
 **The aim of this project is simple, create a basic python library to explore and interact with the UK's open data catalogues**.
 
 ## Examples of UK Open Data Catalogues
 
-1. [Bristol Open Data](https://opendata.bristol.gov.uk)
-2. [London Datastore](https://data.london.gov.uk)
-3. [Data Mill North](https://datamillnorth.org)
-4. [Gov Open Data](https://www.data.gov.uk)
+| Catalogue Name | Website | Catalogue API Endpoint |
+|----------------|---------|-------------------|
+| Bristol Open Data | https://opendata.bristol.gov.uk | TBC |
+| London Datastore | https://data.london.gov.uk | CKAN: https://data.london.gov.uk/api/3/ |
+| Data Mill North | https://datamillnorth.org | TBC |
+| Gov Open Data | https://www.data.gov.uk | TBC |
 
 ## Basic usage examples:
 
 ```python
-# Example usage
+# Example usage 1
 if __name__ == "__main__":
     with CatSession("data.london.gov.uk") as session:
         explore = CatExplorer(session)
-        v =  explore.package_search_json(search_query="census")
-        pprint(v)
+        census_package =  explore.package_search_json(search_query="census")
+        pprint(census_package)
+```
+
+```python
+# Example usage 2
+if __name__ == "__main__":
+    with CatSession("data.london.gov.uk") as session:
+        explore = CatExplorer(session)
+        packlage_list = explore.package_list_json()
+        boundary_info = explore.package_show_info_json('2011-boundary-files')
+        pprint(show_info)
 ```

pytest.ini

@@ -1,3 +1,3 @@
 [pytest]
-pythonpath = .
+pythonpath = src/
 addopts = -v

src/api_endpoints.py

@@ -2,6 +2,7 @@ class CkanApiPaths:
     BASE_PATH = "/api/3/action/{}"
     PACKAGE_LIST = BASE_PATH.format("package_list")
     PACKAGE_SEARCH = BASE_PATH.format("package_search")
+    PACKAGE_INFO = BASE_PATH.format("package_show")
     # Add more paths as needed...
 
 

src/herding_cats.py

@@ -8,8 +8,8 @@
 from enum import Enum
 from urllib.parse import urlencode
 
-from .api_endpoints import CkanApiPaths
-from .cats_errors import CatExplorerError, CatSessionError
+from api_endpoints import CkanApiPaths
+from cats_errors import CatExplorerError, CatSessionError
 
 class CatSession:
     def __init__(self, domain: str) -> None:
@@ -93,7 +93,24 @@ def package_search_json(self, search_query: Optional[str]=None):
             params["q"] = search_query
 
         url = f"{base_url}?{urlencode(params)}" if params else base_url
-        print(url)
+
+        try:
+            response = self.cat_session.session.get(url)
+            response.raise_for_status()
+            data = response.json()
+            return data['result']
+        except requests.RequestException as e:
+            logger.error(f"Failed to search datasets: {e}")
+            raise CatExplorerError(f"Failed to search datasets: {str(e)}")
+
+    def package_show_info_json(self, package_name:str):
+        base_url = self.cat_session.base_url + CkanApiPaths.PACKAGE_INFO
+
+        params = {}
+        if package_name:
+            params["id"] = package_name
+
+        url = f"{base_url}?{urlencode(params)}" if params else base_url
 
         try:
             response = self.cat_session.session.get(url)
@@ -119,5 +136,6 @@ def get_package_count(self) -> int:
 if __name__ == "__main__":
     with CatSession("data.london.gov.uk") as session:
         explore = CatExplorer(session)
-        v =  explore.package_search_json(search_query="census")
-        pprint(v)
+        show_list = explore.package_list_json()
+        show_info = explore.package_show_info_json('2011-boundary-files')
+        pprint(show_info)