fix: Council Fix Pack - March 2026

uk_bin_collection/tests/input.json

@@ -1344,14 +1344,11 @@
         "LAD24CD": "E07000121"
     },
     "LeedsCityCouncil": {
-        "house_number": "1",
-        "postcode": "LS6 2SE",
         "skip_get_url": true,
         "uprn": "72506983",
         "url": "https://www.leeds.gov.uk/residents/bins-and-recycling/check-your-bin-day",
-        "web_driver": "http://selenium:4444",
         "wiki_name": "Leeds",
-        "wiki_note": "Pass the house number, postcode, and UPRN. This parser requires a Selenium webdriver.",
+        "wiki_note": "Pass the UPRN.",
         "LAD24CD": "E08000035"
     },
     "LeicesterCityCouncil": {
@@ -1420,6 +1417,14 @@
         "wiki_note": "Pass the UPRN. You can find it using [FindMyAddress](https://www.findmyaddress.co.uk/search).",
         "LAD24CD": "E09000009"
     },
+    "LondonBoroughHammersmithandFulham": {
+        "postcode": "W12 0BQ",
+        "url": "https://www.lbhf.gov.uk/",
+        "wiki_command_url_override": "https://www.lbhf.gov.uk/",
+        "wiki_name": "Hammersmith & Fulham",
+        "wiki_note": "Pass only the property postcode",
+        "LAD24CD": "E09000013"
+    },
     "LondonBoroughHarrow": {
         "uprn": "100021298754",
         "url": "https://www.harrow.gov.uk",

uk_bin_collection/uk_bin_collection/councils/BarkingDagenham.py

@@ -47,23 +47,7 @@ def parse_data(self, page: str, **kwargs) -> dict:
             # Close popup if it exists
             driver.switch_to.active_element.send_keys(Keys.ESCAPE)
 
-            # Handle cookie banner if present
-            wait = WebDriverWait(driver, 60)
-            try:
-                cookie_button = wait.until(
-                    EC.element_to_be_clickable(
-                        (
-                            By.CSS_SELECTOR,
-                            ".agree-button.eu-cookie-compliance-secondary-button.button.button--small",
-                        )
-                    ),
-                    message="Cookie banner not found",
-                )
-                cookie_button.click()
-                print("Cookie banner clicked.")
-                time.sleep(1)  # Brief pause to let banner disappear
-            except (TimeoutException, NoSuchElementException):
-                print("No cookie banner appeared or selector failed.")
+            wait = WebDriverWait(driver, 10)
 
             # Enter postcode
             print("Looking for postcode input...")
@@ -84,7 +68,7 @@ def parse_data(self, page: str, **kwargs) -> dict:
                 EC.element_to_be_clickable((By.ID, "address")),
                 message="Address dropdown not found",
             )
-            
+
             dropdown = Select(address_select)
 
             found = False

uk_bin_collection/uk_bin_collection/councils/BromleyBoroughCouncil.py

@@ -30,7 +30,8 @@ def parse_data(self, page: str, **kwargs) -> dict:
             data = {"bins": []}
 
             # Get our initial session running
-            driver = create_webdriver(web_driver, headless, None, __name__)
+            user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+            driver = create_webdriver(web_driver, headless, user_agent, __name__)
             driver.get(kwargs.get("url"))
 
             wait = WebDriverWait(driver, 30)

uk_bin_collection/uk_bin_collection/councils/CumberlandCouncil.py

@@ -1,3 +1,5 @@
+from datetime import date
+
 import requests
 from bs4 import BeautifulSoup
 
@@ -29,64 +31,26 @@ def parse_data(self, page: str, **kwargs) -> dict:
         if not content_region:
             return bindata
 
-        # Parse the text content to extract collection dates
-        text_content = content_region.get_text()
-        lines = [line.strip() for line in text_content.split('\n') if line.strip()]
-
-        current_month = None
-        current_year = None
-        i = 0
-
-        # Determine the year range from the page header
-        year_2026 = "2026" in text_content
-
-        while i < len(lines):
-            line = lines[i]
-
-            # Check if this is a month name
-            if line in ["January", "February", "March", "April", "May", "June", 
-                       "July", "August", "September", "October", "November", "December"]:
-                current_month = line
-                # Determine year based on month and context
-                if year_2026:
-                    current_year = "2026" if line in ["January", "February"] else "2025"
-                else:
-                    current_year = str(datetime.now().year)
-                i += 1
-                continue
-
-            # Check if this is a day number (1-31)
-            if line.isdigit() and 1 <= int(line) <= 31 and current_month:
-                day = line
-                # Next line should be the bin type
-                if i + 1 < len(lines):
-                    bin_type = lines[i + 1]
-
-                    # Skip the subtype line (Refuse/Recycling detail)
-                    if i + 2 < len(lines) and lines[i + 2] in ["Refuse", "Recycling"]:
-                        i += 1
-
-                    # Parse the date
-                    try:
-                        date_str = f"{day} {current_month} {current_year}"
-                        collection_date = datetime.strptime(date_str, "%d %B %Y")
-
-                        dict_data = {
-                            "type": bin_type,
-                            "collectionDate": collection_date.strftime(date_format),
-                        }
-                        bindata["bins"].append(dict_data)
-                    except ValueError:
-                        pass
-
-                    i += 2
-                    continue
-
-            i += 1
+        lis = content_region.find_all("li")
+        for li in lis:
+            collection_day = li.find("span", class_="waste-collection__day--day")
+            collection_type_str = li.find("span", class_="waste-collection__day--type")
+
+            collection_date = collection_day.find("time")["datetime"]
+
+            collection_type = collection_type_str.text
+
+            collection_date = datetime.strptime(collection_date, "%Y-%m-%d")
+
+            dict_data = {
+                "type": collection_type.strip(),
+                "collectionDate": collection_date.strftime(date_format),
+            }
+            bindata["bins"].append(dict_data)
 
         # Sort by collection date
         bindata["bins"].sort(
-            key=lambda x: datetime.strptime(x.get("collectionDate"), "%d/%m/%Y")
+            key=lambda x: datetime.strptime(x.get("collectionDate"), date_format)
         )
 
         return bindata

uk_bin_collection/uk_bin_collection/councils/EastleighBoroughCouncil.py

@@ -23,7 +23,8 @@ def parse_data(self, page: str, **kwargs) -> dict:
             headless = kwargs.get("headless")
             web_driver = kwargs.get("web_driver")
             url = f"https://www.eastleigh.gov.uk/waste-bins-and-recycling/collection-dates/your-waste-bin-and-recycling-collections?uprn={uprn}"
-            driver = create_webdriver(web_driver, headless, None, __name__)
+            user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+            driver = create_webdriver(web_driver, headless, user_agent, __name__)
             driver.get(url)
 
             wait = WebDriverWait(driver, 10)

uk_bin_collection/uk_bin_collection/councils/HarboroughDistrictCouncil.py

@@ -23,15 +23,18 @@ def parse_data(self, page: str, **kwargs) -> dict:
         check_uprn(user_uprn)
         bindata = {"bins": []}
 
-        URI = "https://harborough.fccenvironment.co.uk/detail-address"
+        URI1 = "https://harborough.fccenvironment.co.uk/"
+        URI2 = "https://harborough.fccenvironment.co.uk/detail-address"
+
+        # Make the GET request
+        session = requests.session()
+        response = session.get(
+            URI1, verify=False
+        )  # Initialize session state (cookies) required by URI2
+        response.raise_for_status()  # Validate session initialization
 
-        headers = {
-            "Content-Type": "application/json",
-            "User-Agent": "Mozilla/5.0",
-            "Referer": "https://harborough.fccenvironment.co.uk/",
-        }
         params = {"Uprn": user_uprn}
-        response = requests.post(URI, headers=headers, data=params, verify=False)
+        response = session.post(URI2, data=params, verify=False)
 
         # Check for service errors
         if response.status_code == 502:
@@ -40,20 +43,20 @@ def parse_data(self, page: str, **kwargs) -> dict:
                 f"This is a temporary issue with the council's waste collection system. "
                 f"Please try again later."
             )
-        
+
         response.raise_for_status()
 
         soup = BeautifulSoup(response.content, features="html.parser")
         bin_collection = soup.find(
             "div", {"class": "blocks block-your-next-scheduled-bin-collection-days"}
         )
-        
+
         if bin_collection is None:
             raise ValueError(
                 f"Could not find bin collection data for UPRN {user_uprn}. "
                 "The council website may have changed or the UPRN may be invalid."
             )
-        
+
         lis = bin_collection.find_all("li")
         for li in lis:
             try:

uk_bin_collection/uk_bin_collection/councils/LeedsCityCouncil.py

@@ -1,14 +1,5 @@
-import urllib.request
 from datetime import datetime
 
-import pandas as pd
-from bs4 import BeautifulSoup
-from selenium.webdriver.common.by import By
-from selenium.webdriver.common.keys import Keys
-from selenium.webdriver.support import expected_conditions as EC
-from selenium.webdriver.support.ui import Select
-from selenium.webdriver.support.wait import WebDriverWait
-
 from uk_bin_collection.uk_bin_collection.common import *
 from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
 
@@ -22,92 +13,50 @@ class CouncilClass(AbstractGetBinDataClass):
 
     def parse_data(self, page: str, **kwargs) -> dict:
         driver = None
+        data = {"bins": []}
         try:
-            """
-            Parse council provided CSVs to get the latest bin collections for address
-            """
-
             user_uprn = kwargs.get("uprn")
-            user_postcode = kwargs.get("postcode")
-            web_driver = kwargs.get("web_driver")
-            headless = kwargs.get("headless")
             check_uprn(user_uprn)
-            check_postcode(user_postcode)
-            # Create Selenium webdriver
-            page = f"https://www.leeds.gov.uk/residents/bins-and-recycling/check-your-bin-day"
-
-            driver = create_webdriver(web_driver, headless, None, __name__)
-            driver.get(page)
-
-            wait = WebDriverWait(driver, 60)
-            postcode_box = wait.until(
-                EC.element_to_be_clickable(
-                    (
-                        By.XPATH,
-                        "//input[@id='postcode']",
-                    )
-                )
-            )
-            postcode_box.send_keys(user_postcode)
-            postcode_btn_present = wait.until(
-                EC.presence_of_element_located(
-                    (
-                        By.XPATH,
-                        "//button[contains(text(),'Look up Address')]",
-                    )
-                )
-            )
 
-            postcode_btn_present.send_keys(Keys.RETURN)
+            URI = "https://api.leeds.gov.uk/public/waste/v1/BinsDays"
 
-            dropdown_present = wait.until(
-                EC.presence_of_element_located(
-                    (
-                        By.XPATH,
-                        '//option[contains(text(),"Select an address")]/parent::select',
-                    )
-                )
-            )
+            startDate = datetime.now()
+            endDate = (startDate + timedelta(weeks=8)).strftime("%Y-%m-%d")
+            startDate = startDate.strftime("%Y-%m-%d")
+
+            params = {
+                "uprn": user_uprn,
+                "startDate": startDate,
+                "endDate": endDate,
+            }
+
+            headers = {
+                "ocp-apim-subscription-key": "ad8dd80444fe45fcad376f82cf9a5ab4",
+                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/145.0.0.0 Safari/537.36",
+            }
 
-            dropdown_select = Select(dropdown_present)
+            # print(params)
 
-            dropdown_select.select_by_value(user_uprn)
+            # Send GET request
+            response = requests.get(URI, params=params, headers=headers)
 
-            result = wait.until(
-                EC.presence_of_element_located(
-                    (
-                        By.XPATH,
-                        "//div[@class='lcc-bins']",
-                    )
+            print(response.content)
+
+            collections = json.loads(response.content)
+
+            for collection in collections:
+
+                collectionDate = datetime.strptime(
+                    collection["date"], "%Y-%m-%dT%H:%M:%S"
                 )
-            )
-
-            data = {"bins": []}  # dictionary for data
-            soup = BeautifulSoup(
-                result.get_attribute("innerHTML"), features="html.parser"
-            )
-
-            bin_sections = soup.select("div.lcc-bin:not(.lcc-bin--calendar)")
-
-            for section in bin_sections:
-                h3_text = section.find("h3").get_text(strip=True)
-                bin_type = h3_text.split()[0]  # e.g., 'Black', 'Brown', 'Green'
-
-                # Find all <li> elements inside the bin days list
-                date_elements = section.select("div.lcc-bin__days li")
-                for li in date_elements:
-                    raw_date = li.get_text(strip=True)
-                    if not raw_date:
-                        continue
-                    try:
-                        formatted_date = datetime.strptime(
-                            raw_date, "%A %d %b %Y"
-                        ).strftime(date_format)
-                        data["bins"].append(
-                            {"type": bin_type, "collectionDate": formatted_date}
-                        )
-                    except ValueError:
-                        print(f"Skipping unparseable date: {raw_date}")
+
+                data["bins"].append(
+                    {
+                        "type": collection["type"],
+                        "collectionDate": collectionDate.strftime(date_format),
+                    }
+                )
+
         except Exception as e:
             # Here you can log the exception if needed
             print(f"An error occurred: {e}")