uk_bin_collection 0.144.4__tar.gz → 0.146.0__tar.gz

{uk_bin_collection-0.144.4 → uk_bin_collection-0.146.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.144.4
+Version: 0.146.0
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.144.4 → uk_bin_collection-0.146.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.144.4"
+version = "0.146.0"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.144.4 → uk_bin_collection-0.146.0}/uk_bin_collection/map.html

@@ -37,23 +37,37 @@
         const coveredLADs = new Set();
         const integrationByLAD24CD = {};
 
-        for (const entry of Object.values(integrationData)) {
-          const rawCode = entry.LAD24CD;
-          const code = rawCode?.replace(/[^\x20-\x7E]/g, '').trim();  // Sanitize non-printables
-          if (code) {
-            console.log(`✅ Adding LAD24CD: [${code}] from raw: [${rawCode}]`);
-            coveredLADs.add(code);
-            integrationByLAD24CD[code] = {
-              wiki_name: entry.wiki_name || "Unknown Council",
-              url: `https://github.com/robbrad/UKBinCollectionData/wiki/Councils#${slugify(entry.wiki_name || "unknown-council")}`
-            };
-          } else {
-            console.warn("⚠️ Entry with missing or bad LAD24CD:", entry);
+        for (const [moduleName, entry] of Object.entries(integrationData)) {
+          const wikiName = entry.wiki_name || moduleName;
+          const wikiUrl = `https://github.com/robbrad/UKBinCollectionData/wiki/Councils#${slugify(wikiName)}`;
+
+          // Case 1: Direct LAD24CD
+          if (entry.LAD24CD) {
+            const code = entry.LAD24CD?.replace(/[^\x20-\x7E]/g, '').trim();
+            if (code) {
+              coveredLADs.add(code);
+              integrationByLAD24CD[code] = { wiki_name: wikiName, url: wikiUrl };
+            } else {
+              console.warn("⚠️ Entry with bad LAD24CD:", moduleName, entry);
+            }
+          }
+
+          // Case 2: Shared modules with multiple LADs
+          if (Array.isArray(entry.supported_councils_LAD24CD)) {
+            for (const codeRaw of entry.supported_councils_LAD24CD) {
+              const code = codeRaw?.replace(/[^\x20-\x7E]/g, '').trim();
+              if (code) {
+                coveredLADs.add(code);
+                // Only overwrite if not already present (prefer specific match)
+                if (!integrationByLAD24CD[code]) {
+                  integrationByLAD24CD[code] = { wiki_name: wikiName, url: wikiUrl };
+                }
+              }
+            }
           }
         }
 
-        console.log("🧪 Contains E06000065?", coveredLADs.has("E06000065"));
-        console.log("📦 Final set of covered LADs:", [...coveredLADs]);
+        console.log("📦 Final covered LADs:", [...coveredLADs]);
 
         return fetch('Local_Authority_Boundaries.geojson')
           .then(res => res.json())
@@ -74,7 +88,6 @@
                 const name = feature.properties.LAD24NM;
                 const covered = coveredLADs.has(code);
 
-                console.log("🌍 GeoJSON Feature:", code, name);
                 if (!code) console.warn("⚠️ Missing LAD24CD in GeoJSON feature:", feature);
                 if (!covered && code) console.warn("❌ Not covered LAD:", code, name);
 
@@ -90,14 +103,11 @@
               }
             }).addTo(map);
 
-            // ✅ 🔍 Missing LADs debug block
-            const missing = [];
-            geojson.features.forEach(f => {
-              const code = f.properties.LAD24CD?.trim();
-              if (!coveredLADs.has(code)) {
-                missing.push(`${code} - ${f.properties.LAD24NM}`);
-              }
-            });
+            // Debug missing LADs
+            const missing = geojson.features
+              .map(f => [f.properties.LAD24CD?.trim(), f.properties.LAD24NM])
+              .filter(([code]) => !coveredLADs.has(code))
+              .map(([code, name]) => `${code} - ${name}`);
             console.warn("🛠️ Missing LADs in input.json:", missing);
           });
       })

{uk_bin_collection-0.144.4 → uk_bin_collection-0.146.0}/uk_bin_collection/tests/check_selenium_url_in_input.json.py

@@ -23,10 +23,14 @@ def get_council_files(repo, branch):
                 name = item["name"]
                 if name.endswith(".py"):
                     council_name = name.replace(".py", "")
-                    councils[council_name] = item["url"]  # 'url' gives API-based content URL
+                    councils[council_name] = item[
+                        "url"
+                    ]  # 'url' gives API-based content URL
             return councils
         else:
-            raise ValueError("Expected a list from the GitHub response but got something else.")
+            raise ValueError(
+                "Expected a list from the GitHub response but got something else."
+            )
     else:
         print(f"Failed to fetch councils from files: {response.content}")
         return {}
@@ -39,7 +43,9 @@ def get_council_file_content(api_url):
     We'll use the latter, decode base64, and return the text.
     """
     # Example: https://api.github.com/repos/robbrad/UKBinCollectionData/contents/...
-    response = requests.get(api_url, headers={"Accept": "application/vnd.github.v3+json"})
+    response = requests.get(
+        api_url, headers={"Accept": "application/vnd.github.v3+json"}
+    )
     if response.status_code == 200:
         file_json = response.json()
         # file_json["content"] is base64-encoded
@@ -82,8 +88,8 @@ def council_needs_update(council_name, json_data, council_file_content):
     # If the council isn't in the JSON at all, we can't do the check
     # (or we assume no JSON data => no web_driver?).
     council_data = json_data.get(council_name, {})
-    web_driver_missing = ("web_driver" not in council_data)
-    create_webdriver_present = ("create_webdriver" in council_file_content)
+    web_driver_missing = "web_driver" not in council_data
+    create_webdriver_present = "create_webdriver" in council_file_content
 
     return web_driver_missing and create_webdriver_present
 
@@ -165,20 +171,21 @@ def main(repo="robbrad/UKBinCollectionData", branch="master"):
     # 4) Print results
     table_data = []
     headers = ["Council Name", "In Files", "In JSON", "Needs Update?", "Discrepancies"]
+
     # Sort councils so that ones with the highest discrepancy or update appear first
     # Then alphabetical if tie:
     def sort_key(item):
         # item is (council_name, data_dict)
         return (
-            item[1]["needs_update"],         # sort by needs_update (False < True)
+            item[1]["needs_update"],  # sort by needs_update (False < True)
             item[1]["discrepancies_count"],  # then by discrepancies
-            item[0],                         # then by name
+            item[0],  # then by name
         )
 
     # We'll sort descending for "needs_update", so invert the boolean or reverse later
     sorted_councils = sorted(
         all_councils_data.items(),
-        key=lambda x: (not x[1]["needs_update"], x[1]["discrepancies_count"], x[0])
+        key=lambda x: (not x[1]["needs_update"], x[1]["discrepancies_count"], x[0]),
     )
 
     for council, presence in sorted_councils:

{uk_bin_collection-0.144.4 → uk_bin_collection-0.146.0}/uk_bin_collection/tests/input.json

@@ -983,7 +983,38 @@
     "GooglePublicCalendarCouncil": {
         "url": "https://calendar.google.com/calendar/ical/0d775884b4db6a7bae5204f06dae113c1a36e505b25991ebc27c6bd42edf5b5e%40group.calendar.google.com/public/basic.ics",
         "wiki_name": "Google Calendar (Public)",
-        "wiki_note": "The URL should be the public ics file URL for the public Google calendar. See https://support.google.com/calendar/answer/37083?sjid=7202815583021446882-EU. Councils that currently need this are Trafford."
+        "wiki_note": "The URL should be the public ics file URL for the public Google calendar. See https://support.google.com/calendar/answer/37083?sjid=7202815583021446882-EU. Councils that currently need this are Trafford.",
+        "supported_councils": [
+            "TraffordCouncil",
+            "ClackmannanshireCouncil",
+            "HavantBoroughCouncil",
+            "NorthWarwickshireBoroughCouncil",
+            "NewryMourneAndDownDistrictCouncil",
+            "EastDunbartonshireCouncil",
+            "PendleBoroughCouncil",
+            "TorfaenCountyBoroughCouncil",
+            "EastHampshireCountyCouncil",
+            "RibbleValleyCouncil",
+            "BrentwoodBoroughCouncil",
+            "IsleOfWightCouncil",
+            "WestmorlAndFurnessCouncil",
+            "DerryAndStrabaneDistrictCouncil",
+            "NorwichCityCouncil"
+        ],
+        "supported_councils_LAD24CD": [
+            "E06000046",
+            "E07000068",
+            "E07000085",
+            "E07000090",
+            "E07000124",
+            "E07000218",
+            "E08000009",
+            "N09000005",
+            "N09000010",
+            "S12000005",
+            "S12000045",
+            "W06000020"
+        ]
     },
     "GraveshamBoroughCouncil": {
         "skip_get_url": true,

{uk_bin_collection-0.144.4 → uk_bin_collection-0.146.0}/uk_bin_collection/uk_bin_collection/common.py

@@ -177,7 +177,11 @@ def is_working_day(date_to_check: datetime, region: Region = Region.ENG) -> bool
     :param region: The UK nation to check. Defaults to ENG.
     :return: Bool - true if a working day (non-holiday, Mon-Fri).
     """
-    return False if is_holiday(date_to_check, region) or is_weekend(date_to_check) else True
+    return (
+        False
+        if is_holiday(date_to_check, region) or is_weekend(date_to_check)
+        else True
+    )
 
 
 def get_next_working_day(date: datetime, region: Region = Region.ENG) -> datetime:
@@ -232,7 +236,7 @@ def get_next_occurrence_from_day_month(date: datetime) -> datetime:
 
     # Check if the target date has already occurred this year
     if (target_month < current_month) or (
-            target_month == current_month and target_day < current_day
+        target_month == current_month and target_day < current_day
     ):
         date = pd.to_datetime(date) + pd.DateOffset(years=1)
 
@@ -315,10 +319,10 @@ def contains_date(string, fuzzy=False) -> bool:
 
 
 def create_webdriver(
-        web_driver: str = None,
-        headless: bool = True,
-        user_agent: str = None,
-        session_name: str = None,
+    web_driver: str = None,
+    headless: bool = True,
+    user_agent: str = None,
+    session_name: str = None,
 ) -> webdriver.Chrome:
     """
     Create and return a Chrome WebDriver configured for optional headless operation.

{uk_bin_collection-0.144.4 → uk_bin_collection-0.146.0}/uk_bin_collection/uk_bin_collection/councils/GooglePublicCalendarCouncil.py

@@ -29,9 +29,11 @@ class CouncilClass(AbstractGetBinDataClass):
             if not event.summary or not event.start:
                 continue
 
-            bindata["bins"].append({
-                "type": event.summary,
-                "collectionDate": event.start.date().strftime(date_format)
-            })
+            bindata["bins"].append(
+                {
+                    "type": event.summary,
+                    "collectionDate": event.start.date().strftime(date_format),
+                }
+            )
 
         return bindata

{uk_bin_collection-0.144.4 → uk_bin_collection-0.146.0}/uk_bin_collection/uk_bin_collection/councils/GreatYarmouthBoroughCouncil.py

@@ -10,6 +10,7 @@ from datetime import datetime
 from uk_bin_collection.uk_bin_collection.common import *
 from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
 
+
 # import the wonderful Beautiful Soup and the URL grabber
 class CouncilClass(AbstractGetBinDataClass):
     """
@@ -31,7 +32,7 @@ class CouncilClass(AbstractGetBinDataClass):
             check_postcode(user_postcode)
 
             driver = create_webdriver(web_driver, headless, None, __name__)
-            
+
             driver.get(url)
 
             wait = WebDriverWait(driver, 10)
@@ -78,19 +79,23 @@ class CouncilClass(AbstractGetBinDataClass):
             time.sleep(5)
             # Wait for the specified div to be present
             target_div = WebDriverWait(driver, 10).until(
-                EC.presence_of_element_located((By.ID, "WASTECOLLECTIONCALENDARV2_LOOKUP_SHOWSCHEDULE"))
+                EC.presence_of_element_located(
+                    (By.ID, "WASTECOLLECTIONCALENDARV2_LOOKUP_SHOWSCHEDULE")
+                )
             )
 
             soup = BeautifulSoup(driver.page_source, "html.parser")
 
             bin_data = {"bins": []}
-            next_collections = {}  # Dictionary to store the next collection for each bin type
+            next_collections = (
+                {}
+            )  # Dictionary to store the next collection for each bin type
 
             bin_types = {
                 "bulky": "Bulky Collection",
                 "green": "Recycling",
                 "black": "General Waste",
-                "brown": "Garden Waste"
+                "brown": "Garden Waste",
             }
 
             for div in soup.select(".collection-area"):
@@ -108,21 +113,26 @@ class CouncilClass(AbstractGetBinDataClass):
 
                 # Determine bin type from alt or description
                 description = detail.get_text(separator=" ", strip=True).lower()
-                alt_text = img['alt'].lower()
+                alt_text = img["alt"].lower()
 
                 for key, name in bin_types.items():
                     if key in alt_text or key in description:
                         # Format date as dd/mm/yyyy
                         formatted_date = date_obj.strftime("%d/%m/%Y")
-                        bin_entry = {
-                            "type": name,
-                            "collectionDate": formatted_date
-                        }
-                        
+                        bin_entry = {"type": name, "collectionDate": formatted_date}
+
                         # Only keep the earliest date for each bin type
-                        if name not in next_collections or date_obj < datetime.strptime(next_collections[name]["collectionDate"], "%d/%m/%Y"):
+                        if (
+                            name not in next_collections
+                            or date_obj
+                            < datetime.strptime(
+                                next_collections[name]["collectionDate"], "%d/%m/%Y"
+                            )
+                        ):
                             next_collections[name] = bin_entry
-                            print(f"Found next collection for {name}: {formatted_date}")  # Debug output
+                            print(
+                                f"Found next collection for {name}: {formatted_date}"
+                            )  # Debug output
                         break
 
             # Add the next collections to the bin_data
@@ -134,7 +144,7 @@ class CouncilClass(AbstractGetBinDataClass):
         finally:
             if driver:
                 driver.quit()
-                
+
         print("\nFinal bin data:")
         print(bin_data)  # Debug output
         return bin_data

{uk_bin_collection-0.144.4 → uk_bin_collection-0.146.0}/uk_bin_collection/uk_bin_collection/councils/KnowsleyMBCouncil.py

@@ -26,12 +26,19 @@ class CouncilClass(AbstractGetBinDataClass):
             driver = create_webdriver(web_driver, headless, None, __name__)
             driver.set_window_size(1920, 1080)  # 👈 ensure full viewport
 
-            driver.get("https://www.knowsley.gov.uk/bins-waste-and-recycling/your-household-bins/putting-your-bins-out")
+            driver.get(
+                "https://www.knowsley.gov.uk/bins-waste-and-recycling/your-household-bins/putting-your-bins-out"
+            )
 
             # Dismiss cookie popup if it exists
             try:
                 accept_cookies = WebDriverWait(driver, 10).until(
-                    EC.element_to_be_clickable((By.XPATH, "//a[contains(@class, 'agree-button') and contains(text(), 'Accept all cookies')]"))
+                    EC.element_to_be_clickable(
+                        (
+                            By.XPATH,
+                            "//a[contains(@class, 'agree-button') and contains(text(), 'Accept all cookies')]",
+                        )
+                    )
                 )
                 accept_cookies.click()
                 time.sleep(1)
@@ -41,7 +48,10 @@ class CouncilClass(AbstractGetBinDataClass):
             # Step 1: Click "Search by postcode"
             search_btn = WebDriverWait(driver, 60).until(
                 EC.element_to_be_clickable(
-                    (By.XPATH, "//a[contains(text(), 'Search by postcode to find out when your bins are emptied')]")
+                    (
+                        By.XPATH,
+                        "//a[contains(text(), 'Search by postcode to find out when your bins are emptied')]",
+                    )
                 )
             )
             search_btn.send_keys(Keys.RETURN)
@@ -49,14 +59,20 @@ class CouncilClass(AbstractGetBinDataClass):
             # Step 2: Enter postcode
             postcode_box = WebDriverWait(driver, 60).until(
                 EC.presence_of_element_located(
-                    (By.XPATH, "//label[contains(text(), 'Please enter the post code')]/following-sibling::input")
+                    (
+                        By.XPATH,
+                        "//label[contains(text(), 'Please enter the post code')]/following-sibling::input",
+                    )
                 )
             )
             postcode_box.send_keys(user_postcode)
 
             postcode_search_btn = WebDriverWait(driver, 60).until(
                 EC.element_to_be_clickable(
-                    (By.XPATH, "//label[contains(text(), 'Please enter the post code')]/parent::div/following-sibling::button")
+                    (
+                        By.XPATH,
+                        "//label[contains(text(), 'Please enter the post code')]/parent::div/following-sibling::button",
+                    )
                 )
             )
             postcode_search_btn.send_keys(Keys.RETURN)
@@ -64,7 +80,10 @@ class CouncilClass(AbstractGetBinDataClass):
             # Step 3: Select address from results
             address_selection_button = WebDriverWait(driver, 60).until(
                 EC.element_to_be_clickable(
-                    (By.XPATH, f"//span[contains(text(), '{user_paon}')]/ancestor::li//button")
+                    (
+                        By.XPATH,
+                        f"//span[contains(text(), '{user_paon}')]/ancestor::li//button",
+                    )
                 )
             )
             address_selection_button.send_keys(Keys.RETURN)
@@ -77,9 +96,13 @@ class CouncilClass(AbstractGetBinDataClass):
             )
 
             bin_info_container = driver.find_element(
-                By.XPATH, "//label[contains(text(), 'collection')]/ancestor::div[contains(@class, 'mx-dataview-content')]")
+                By.XPATH,
+                "//label[contains(text(), 'collection')]/ancestor::div[contains(@class, 'mx-dataview-content')]",
+            )
 
-            soup = BeautifulSoup(bin_info_container.get_attribute("innerHTML"), "html.parser")
+            soup = BeautifulSoup(
+                bin_info_container.get_attribute("innerHTML"), "html.parser"
+            )
 
             for group in soup.find_all("div", class_="form-group"):
                 label = group.find("label")
@@ -93,14 +116,18 @@ class CouncilClass(AbstractGetBinDataClass):
                 if "bin next collection date" in label_text.lower():
                     bin_type = label_text.split(" bin")[0]
                     try:
-                        collection_date = datetime.strptime(value_text, "%A %d/%m/%Y").strftime("%d/%m/%Y")
+                        collection_date = datetime.strptime(
+                            value_text, "%A %d/%m/%Y"
+                        ).strftime("%d/%m/%Y")
                     except ValueError:
                         continue
 
-                    bindata["bins"].append({
-                        "type": bin_type,
-                        "collectionDate": collection_date,
-                    })
+                    bindata["bins"].append(
+                        {
+                            "type": bin_type,
+                            "collectionDate": collection_date,
+                        }
+                    )
 
             bindata["bins"].sort(
                 key=lambda x: datetime.strptime(x["collectionDate"], "%d/%m/%Y")

{uk_bin_collection-0.144.4 → uk_bin_collection-0.146.0}/uk_bin_collection/uk_bin_collection/councils/MidUlsterDistrictCouncil.py

@@ -5,12 +5,13 @@ from selenium.webdriver.common.by import By
 from selenium.webdriver.support import expected_conditions as EC
 from selenium.webdriver.support.ui import Select, WebDriverWait
 
-#import selenium keys
+# import selenium keys
 from selenium.webdriver.common.keys import Keys
 
 from uk_bin_collection.uk_bin_collection.common import *
 from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
 
+
 # import the wonderful Beautiful Soup and the URL grabber
 class CouncilClass(AbstractGetBinDataClass):
     """
@@ -28,7 +29,7 @@ class CouncilClass(AbstractGetBinDataClass):
             check_postcode(user_postcode)
             user_paon = kwargs.get("paon")
             check_paon(user_paon)
-            
+
             headless = kwargs.get("headless")
             web_driver = kwargs.get("web_driver")
             driver = create_webdriver(web_driver, headless, None, __name__)
@@ -54,13 +55,10 @@ class CouncilClass(AbstractGetBinDataClass):
                 pass
 
             postcode_input = wait.until(
-                EC.presence_of_element_located(
-                    (By.ID, 'postcode-search-input')
-                )
+                EC.presence_of_element_located((By.ID, "postcode-search-input"))
             )
             postcode_input.send_keys(user_postcode)
 
-
             # Wait for the element to be clickable
             postcode_search_btn = wait.until(
                 EC.element_to_be_clickable(
@@ -101,7 +99,9 @@ class CouncilClass(AbstractGetBinDataClass):
                     date_text = date_span.text.strip()
                     current_year = datetime.now().year
                     full_date = f"{date_text} {current_year}"  # e.g., "18 Apr 2025"
-                    collection_date = datetime.strptime(full_date, "%d %b %Y").strftime(date_format)
+                    collection_date = datetime.strptime(full_date, "%d %b %Y").strftime(
+                        date_format
+                    )
                 else:
                     collection_date = None
             except Exception as e:
@@ -115,13 +115,17 @@ class CouncilClass(AbstractGetBinDataClass):
                     bin_title_div = bin_block.select_one("div.bin-title")
                     if bin_title_div:
                         bin_type = bin_title_div.get_text(strip=True)
-                        data["bins"].append({
-                            "type": bin_type,
-                            "collectionDate": collection_date,
-                        })
+                        data["bins"].append(
+                            {
+                                "type": bin_type,
+                                "collectionDate": collection_date,
+                            }
+                        )
 
             # 3. Optional: sort bins by collectionDate
-            data["bins"].sort(key=lambda x: datetime.strptime(x.get("collectionDate"), date_format))
+            data["bins"].sort(
+                key=lambda x: datetime.strptime(x.get("collectionDate"), date_format)
+            )
 
         except Exception as e:
             # Here you can log the exception if needed
@@ -132,4 +136,4 @@ class CouncilClass(AbstractGetBinDataClass):
             # This block ensures that the driver is closed regardless of an exception
             if driver:
                 driver.quit()
-        return data
+        return data

{uk_bin_collection-0.144.4 → uk_bin_collection-0.146.0}/uk_bin_collection/uk_bin_collection/councils/council_class_template/councilclasstemplate.py

@@ -2,6 +2,7 @@ from bs4 import BeautifulSoup
 from uk_bin_collection.uk_bin_collection.common import *
 from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
 
+
 # import the wonderful Beautiful Soup and the URL grabber
 class CouncilClass(AbstractGetBinDataClass):
     """