uk_bin_collection 0.146.0__tar.gz → 0.146.2__tar.gz

{uk_bin_collection-0.146.0 → uk_bin_collection-0.146.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.146.0
+Version: 0.146.2
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com
@@ -9,6 +9,7 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: bs4
+Requires-Dist: geopandas (>=1.0.1,<2.0.0)
 Requires-Dist: holidays
 Requires-Dist: icalevents (>=0.2.1,<0.3.0)
 Requires-Dist: lxml

{uk_bin_collection-0.146.0 → uk_bin_collection-0.146.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.146.0"
+version = "0.146.2"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]
@@ -63,6 +63,7 @@ urllib3 = "*"
 webdriver-manager = "^4.0.1"
 tabulate = "^0.9.0"
 icalevents = "^0.2.1"
+geopandas = "^1.0.1"
 
 [tool.commitizen]
 major_version_zero = true

uk_bin_collection-0.146.2/uk_bin_collection/compare_lad_codes.py

@@ -0,0 +1,58 @@
+import json
+import geopandas as gpd
+
+def extract_lad_codes(input_json_path):
+    with open(input_json_path, "r") as f:
+        data = json.load(f)
+
+    lad_codes = set()
+    lad_code_to_council_input = {}
+
+    for council_key, council_info in data.items():
+        if isinstance(council_info, dict):
+            if "LAD24CD" in council_info:
+                code = council_info["LAD24CD"]
+                lad_codes.add(code)
+                lad_code_to_council_input[code] = council_key
+            if "supported_councils_LAD24CD" in council_info:
+                for code in council_info["supported_councils_LAD24CD"]:
+                    lad_codes.add(code)
+                    lad_code_to_council_input[code] = f"{council_key} (shared)"
+
+    return lad_codes, lad_code_to_council_input
+
+def compare_with_geojson(input_lad_codes, geojson_path):
+    gdf = gpd.read_file(geojson_path)
+    geojson_lad_codes = set(gdf["LAD24CD"].dropna().unique())
+
+    geojson_lad_map = {
+        row["LAD24CD"]: row["LAD24NM"]
+        for _, row in gdf.iterrows()
+        if "LAD24CD" in row and "LAD24NM" in row
+    }
+
+    missing_in_input = geojson_lad_codes - input_lad_codes
+    extra_in_input = input_lad_codes - geojson_lad_codes
+    matching = input_lad_codes & geojson_lad_codes
+
+    return matching, missing_in_input, extra_in_input, geojson_lad_map
+
+# --- Run the comparison ---
+input_json_path = "uk_bin_collection/tests/input.json"
+geojson_path = "uk_bin_collection/Local_Authority_Boundaries.geojson"
+
+input_lad_codes, input_name_map = extract_lad_codes(input_json_path)
+matching, missing, extra, geojson_name_map = compare_with_geojson(input_lad_codes, geojson_path)
+
+# --- Print results ---
+print(f"✅ Matching LAD24CDs ({len(matching)}):")
+for code in sorted(matching):
+    print(f"  {code} → input.json: {input_name_map.get(code)} | geojson: {geojson_name_map.get(code)}")
+
+print(f"\n🟡 LADs in GeoJSON but missing in input.json ({len(missing)}):")
+for code in sorted(missing):
+    print(f"  {code} → geojson: {geojson_name_map.get(code)}")
+
+print(f"\n🔴 LADs in input.json but not in GeoJSON ({len(extra)}):")
+for code in sorted(extra):
+    print(f"  {code} → input.json: {input_name_map.get(code)}")

{uk_bin_collection-0.146.0 → uk_bin_collection-0.146.2}/uk_bin_collection/tests/input.json

@@ -1013,7 +1013,8 @@
             "N09000010",
             "S12000005",
             "S12000045",
-            "W06000020"
+            "W06000020",
+            "E07000122"
         ]
     },
     "GraveshamBoroughCouncil": {

{uk_bin_collection-0.146.0 → uk_bin_collection-0.146.2}/uk_bin_collection/uk_bin_collection/councils/Hillingdon.py

@@ -35,41 +35,62 @@ DAYS_OF_WEEK = {
 def get_bank_holiday_changes(driver: WebDriver) -> Dict[str, str]:
     """Fetch and parse bank holiday collection changes from the council website."""
     bank_holiday_url = "https://www.hillingdon.gov.uk/bank-holiday-collections"
-    driver.get(bank_holiday_url)
+    changes: Dict[str, str] = {}
 
-    # Wait for page to load
-    wait = WebDriverWait(driver, 10)
-    wait.until(EC.presence_of_element_located((By.TAG_NAME, "table")))
+    try:
+        driver.get(bank_holiday_url)
 
-    # Parse the page
-    soup = BeautifulSoup(driver.page_source, features="html.parser")
-    changes: Dict[str, str] = {}
+        # Check if the page is a 404 or has an error
+        if "404" in driver.title or "Page not found" in driver.page_source:
+            print("Bank holiday page not found (404).")
+            return changes
 
-    # Find all tables with collection changes
-    tables = soup.find_all("table")
-    for table in tables:
-        # Check if this is a collection changes table
-        headers = [th.text.strip() for th in table.find_all("th")]
-        if "Normal collection day" in headers and "Revised collection day" in headers:
-            # Process each row
-            for row in table.find_all("tr")[1:]:  # Skip header row
-                cols = row.find_all("td")
-                if len(cols) >= 2:
-                    normal_date = cols[0].text.strip()
-                    revised_date = cols[1].text.strip()
-
-                    # Parse dates
-                    try:
-                        normal_date = parse(normal_date, fuzzy=True).strftime(
-                            "%d/%m/%Y"
-                        )
-                        revised_date = parse(revised_date, fuzzy=True).strftime(
-                            "%d/%m/%Y"
-                        )
-                        changes[normal_date] = revised_date
-                    except Exception as e:
-                        print(f"Error parsing dates: {e}")
-                        continue
+        # Wait for page to load
+        wait = WebDriverWait(driver, 10)
+        try:
+            wait.until(EC.presence_of_element_located((By.TAG_NAME, "table")))
+        except TimeoutException:
+            print("No tables found on the bank holiday page.")
+            return changes
+
+        # Parse the page
+        soup = BeautifulSoup(driver.page_source, features="html.parser")
+
+        # Find all tables with collection changes
+        tables = soup.find_all("table")
+        if not tables:
+            print("No relevant tables found on the bank holiday page.")
+            return changes
+
+        for table in tables:
+            # Check if this is a collection changes table
+            headers = [th.text.strip() for th in table.find_all("th")]
+            if (
+                "Normal collection day" in headers
+                and "Revised collection day" in headers
+            ):
+                # Process each row
+                for row in table.find_all("tr")[1:]:  # Skip header row
+                    cols = row.find_all("td")
+                    if len(cols) >= 2:
+                        normal_date = cols[0].text.strip()
+                        revised_date = cols[1].text.strip()
+
+                        # Parse dates
+                        try:
+                            normal_date = parse(normal_date, fuzzy=True).strftime(
+                                "%d/%m/%Y"
+                            )
+                            revised_date = parse(revised_date, fuzzy=True).strftime(
+                                "%d/%m/%Y"
+                            )
+                            changes[normal_date] = revised_date
+                        except Exception as e:
+                            print(f"Error parsing dates: {e}")
+                            continue
+
+    except Exception as e:
+        print(f"An error occurred while fetching bank holiday changes: {e}")
 
     return changes