uk_bin_collection 0.144.1__tar.gz → 0.144.3__tar.gz

{uk_bin_collection-0.144.1 → uk_bin_collection-0.144.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.144.1
+Version: 0.144.3
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.144.1 → uk_bin_collection-0.144.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.144.1"
+version = "0.144.3"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.144.1 → uk_bin_collection-0.144.3}/uk_bin_collection/tests/input.json

@@ -990,6 +990,15 @@
         "wiki_name": "Highland Council",
         "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN."
     },
+    "Hillingdon": {
+        "house_number": "1, Milverton Drive, Ickenham, UB10 8PP, Ickenham, Hillingdon",
+        "postcode": "UB10 8PP",
+        "skip_get_url": true,
+        "url": "https://www.hillingdon.gov.uk/collection-day",
+        "web_driver": "http://selenium:4444",
+        "wiki_name": "High Peak Council",
+        "wiki_note": "Pass the postcode and the full address as it appears in the address pulldown menu."
+    },
     "HinckleyandBosworthBoroughCouncil": {
         "uprn": "100030533512",
         "url": "https://www.hinckley-bosworth.gov.uk",
@@ -1053,7 +1062,7 @@
         "wiki_note": "Provide your UPRN. Find your UPRN using [FindMyAddress](https://www.findmyaddress.co.uk/search)."
     },
     "KnowsleyMBCouncil": {
-        "house_number": "22",
+        "house_number": "2 ALTMOOR ROAD HUYTON L36 3UY",
         "postcode": "L36 3UY",
         "skip_get_url": true,
         "url": "https://knowsleytransaction.mendixcloud.com/link/youarebeingredirected?target=bincollectioninformation",
@@ -1277,6 +1286,15 @@
         "wiki_name": "Midlothian Council",
         "wiki_note": "Pass the house name/number wrapped in double quotes along with the postcode parameter."
     },
+    "MidUlsterDistrictCouncil": {
+        "house_number": "20 HILLHEAD, STEWARTSTOWN, BT71 5HY",
+        "postcode": "BT71 5HY",
+        "skip_get_url": true,
+        "url": "https://www.midulstercouncil.org",
+        "web_driver": "http://selenium:4444",
+        "wiki_name": "Mid Ulster District Council",
+        "wiki_note": "Pass the full address of the house postcode as displayed on the site. This parser requires a Selenium webdriver."
+    },
     "MiltonKeynesCityCouncil": {
         "uprn": "25109551",
         "url": "https://mycouncil.milton-keynes.gov.uk/en/service/Waste_Collection_Round_Checker",

{uk_bin_collection-0.144.1 → uk_bin_collection-0.144.3}/uk_bin_collection/uk_bin_collection/common.py

@@ -337,6 +337,7 @@ def create_webdriver(
     options.add_argument("--disable-gpu")
     options.add_argument("--start-maximized")
     options.add_argument("--disable-dev-shm-usage")
+    options.add_argument("--window-size=1920,1080")
     if user_agent:
         options.add_argument(f"--user-agent={user_agent}")
     options.add_experimental_option("excludeSwitches", ["enable-logging"])

uk_bin_collection-0.144.3/uk_bin_collection/uk_bin_collection/councils/Hillingdon.py

@@ -0,0 +1,273 @@
+import json
+from datetime import datetime, timedelta
+from typing import Any, Dict
+
+from bs4 import BeautifulSoup
+from dateutil.parser import parse
+from selenium.common.exceptions import (
+    NoSuchElementException,
+    StaleElementReferenceException,
+    TimeoutException,
+)
+from selenium.webdriver.common.by import By
+from selenium.webdriver.common.keys import Keys
+from selenium.webdriver.remote.webdriver import WebDriver
+from selenium.webdriver.support import expected_conditions as EC
+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
+
+# Dictionary mapping day names to their weekday numbers (Monday=0, Sunday=6)
+DAYS_OF_WEEK = {
+    "Monday": 0,
+    "Tuesday": 1,
+    "Wednesday": 2,
+    "Thursday": 3,
+    "Friday": 4,
+    "Saturday": 5,
+    "Sunday": 6,
+}
+
+
+# This function checks for bank holiday collection changes,
+# but the page seems manually written so might break easily
+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)
+
+    # Wait for page to load
+    wait = WebDriverWait(driver, 10)
+    wait.until(EC.presence_of_element_located((By.TAG_NAME, "table")))
+
+    # Parse the page
+    soup = BeautifulSoup(driver.page_source, features="html.parser")
+    changes: Dict[str, str] = {}
+
+    # 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
+
+    return changes
+
+
+class CouncilClass(AbstractGetBinDataClass):
+    def parse_data(self, page: str, **kwargs: Any) -> Dict[str, Any]:
+        driver = None
+        try:
+            data: Dict[str, Any] = {"bins": []}
+            user_paon = kwargs.get("paon")
+            user_postcode = kwargs.get("postcode")
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+            url = kwargs.get("url")
+
+            check_paon(user_paon)
+            check_postcode(user_postcode)
+
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            driver.get(url)
+
+            # Handle cookie banner if present
+            wait = WebDriverWait(driver, 30)
+            try:
+                cookie_button = wait.until(
+                    EC.element_to_be_clickable(
+                        (
+                            By.CLASS_NAME,
+                            "btn btn--cookiemessage btn--cancel btn--contrast",
+                        )
+                    )
+                )
+                cookie_button.click()
+            except (TimeoutException, NoSuchElementException):
+                pass
+
+            # Enter postcode
+            post_code_input = wait.until(
+                EC.element_to_be_clickable(
+                    (
+                        By.ID,
+                        "WASTECOLLECTIONDAYLOOKUPINCLUDEGARDEN_ADDRESSLOOKUPPOSTCODE",
+                    )
+                )
+            )
+            post_code_input.clear()
+            post_code_input.send_keys(user_postcode)
+            post_code_input.send_keys(Keys.TAB + Keys.ENTER)
+
+            # Wait for address options to populate
+            try:
+                # Wait for the address dropdown to be present and clickable
+                address_select = wait.until(
+                    EC.presence_of_element_located(
+                        (
+                            By.ID,
+                            "WASTECOLLECTIONDAYLOOKUPINCLUDEGARDEN_ADDRESSLOOKUPADDRESS",
+                        )
+                    )
+                )
+
+                # Wait for actual address options to appear
+                wait.until(
+                    lambda driver: len(driver.find_elements(By.TAG_NAME, "option")) > 1
+                )
+
+                # Find and select address
+                options = address_select.find_elements(By.TAG_NAME, "option")[
+                    1:
+                ]  # Skip placeholder
+                if not options:
+                    raise Exception(f"No addresses found for postcode: {user_postcode}")
+
+                # Normalize user input by keeping only alphanumeric characters
+                normalized_user_input = "".join(
+                    c for c in user_paon if c.isalnum()
+                ).lower()
+
+                # Find matching address in dropdown
+                for option in options:
+                    # Normalize option text by keeping only alphanumeric characters
+                    normalized_option = "".join(
+                        c for c in option.text if c.isalnum()
+                    ).lower()
+                    if normalized_user_input in normalized_option:
+                        option.click()
+                        break
+            except TimeoutException:
+                raise Exception("Timeout waiting for address options to populate")
+
+            # Wait for collection table and day text
+            wait.until(
+                EC.presence_of_element_located(
+                    (By.ID, "WASTECOLLECTIONDAYLOOKUPINCLUDEGARDEN_COLLECTIONTABLE")
+                )
+            )
+
+            # Wait for collection day text to be fully populated
+            wait.until(
+                lambda driver: len(
+                    driver.find_element(
+                        By.ID, "WASTECOLLECTIONDAYLOOKUPINCLUDEGARDEN_COLLECTIONTABLE"
+                    )
+                    .find_elements(By.TAG_NAME, "tr")[2]
+                    .find_elements(By.TAG_NAME, "td")[1]
+                    .text.strip()
+                    .split()
+                )
+                > 1
+            )
+
+            # Parse the table
+            soup = BeautifulSoup(driver.page_source, features="html.parser")
+            table = soup.find(
+                "div", id="WASTECOLLECTIONDAYLOOKUPINCLUDEGARDEN_COLLECTIONTABLE"
+            ).find("table")
+
+            # Get collection day
+            collection_day_text = table.find_all("tr")[2].find_all("td")[1].text.strip()
+            day_of_week = next(
+                (
+                    day
+                    for day in DAYS_OF_WEEK
+                    if day.lower() in collection_day_text.lower()
+                ),
+                None,
+            )
+            if not day_of_week:
+                raise Exception(
+                    f"Could not determine collection day from text: '{collection_day_text}'"
+                )
+
+            # Calculate next collection date
+            today = datetime.now()
+            days_ahead = (DAYS_OF_WEEK[day_of_week] - today.weekday()) % 7
+            if days_ahead == 0:  # If today is collection day, get next week's date
+                days_ahead = 7
+            next_collection = today + timedelta(days=days_ahead)
+
+            # Add collection dates for each bin type
+            bin_types = ["General Waste", "Recycling", "Food Waste"]
+            for bin_type in bin_types:
+                data["bins"].append(
+                    {
+                        "type": bin_type,
+                        "collectionDate": next_collection.strftime("%d/%m/%Y"),
+                    }
+                )
+
+            # Process collection details
+            bin_rows = soup.select("div.bin--row:not(:first-child)")
+            for row in bin_rows:
+                try:
+                    bin_type = row.select_one("div.col-md-3").text.strip()
+                    collection_dates_div = row.select("div.col-md-3")[1]
+                    next_collection_text = "".join(
+                        collection_dates_div.find_all(text=True, recursive=False)
+                    ).strip()
+                    cleaned_date_text = remove_ordinal_indicator_from_date_string(
+                        next_collection_text
+                    )
+                    parsed_date = parse(cleaned_date_text, fuzzy=True)
+                    bin_date = parsed_date.strftime("%d/%m/%Y")
+
+                    if bin_type and bin_date:
+                        data["bins"].append(
+                            {
+                                "type": bin_type,
+                                "collectionDate": bin_date,
+                            }
+                        )
+                except Exception as e:
+                    print(f"Error processing item: {e}")
+                    continue
+
+            # Get bank holiday changes
+            print("\nChecking for bank holiday collection changes...")
+            bank_holiday_changes = get_bank_holiday_changes(driver)
+
+            # Apply any bank holiday changes to collection dates
+            for bin_data in data["bins"]:
+                original_date = bin_data["collectionDate"]
+                if original_date in bank_holiday_changes:
+                    new_date = bank_holiday_changes[original_date]
+                    print(
+                        f"Bank holiday change: {bin_data['type']} collection moved from {original_date} to {new_date}"
+                    )
+                    bin_data["collectionDate"] = new_date
+
+        except Exception as e:
+            print(f"An error occurred: {e}")
+            raise
+        finally:
+            if driver:
+                driver.quit()
+
+        # Print the final data dictionary for debugging
+        print("\nFinal data dictionary:")
+        print(json.dumps(data, indent=2))
+
+        return data

uk_bin_collection-0.144.3/uk_bin_collection/uk_bin_collection/councils/KnowsleyMBCouncil.py

@@ -0,0 +1,116 @@
+import time
+from bs4 import BeautifulSoup
+from datetime import datetime
+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 WebDriverWait
+
+from uk_bin_collection.uk_bin_collection.common import *
+from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
+
+
+class CouncilClass(AbstractGetBinDataClass):
+    def parse_data(self, page: str, **kwargs) -> dict:
+        driver = None
+        try:
+            bindata = {"bins": []}
+            user_paon = kwargs.get("paon")
+            user_postcode = kwargs.get("postcode")
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+
+            check_paon(user_paon)
+            check_postcode(user_postcode)
+
+            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")
+
+            # 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')]"))
+                )
+                accept_cookies.click()
+                time.sleep(1)
+            except:
+                pass  # Cookie popup not shown
+
+            # 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')]")
+                )
+            )
+            search_btn.send_keys(Keys.RETURN)
+
+            # 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")
+                )
+            )
+            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")
+                )
+            )
+            postcode_search_btn.send_keys(Keys.RETURN)
+
+            # 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")
+                )
+            )
+            address_selection_button.send_keys(Keys.RETURN)
+
+            # Step 4: Wait until the bin info is present
+            WebDriverWait(driver, 60).until(
+                EC.presence_of_element_located(
+                    (By.XPATH, "//label[contains(text(), 'collection')]")
+                )
+            )
+
+            bin_info_container = driver.find_element(
+                By.XPATH, "//label[contains(text(), 'collection')]/ancestor::div[contains(@class, 'mx-dataview-content')]")
+
+            soup = BeautifulSoup(bin_info_container.get_attribute("innerHTML"), "html.parser")
+
+            for group in soup.find_all("div", class_="form-group"):
+                label = group.find("label")
+                value = group.find("div", class_="form-control-static")
+                if not label or not value:
+                    continue
+
+                label_text = label.text.strip()
+                value_text = value.text.strip()
+
+                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")
+                    except ValueError:
+                        continue
+
+                    bindata["bins"].append({
+                        "type": bin_type,
+                        "collectionDate": collection_date,
+                    })
+
+            bindata["bins"].sort(
+                key=lambda x: datetime.strptime(x["collectionDate"], "%d/%m/%Y")
+            )
+
+        except Exception as e:
+            print(f"An error occurred: {e}")
+            raise
+        finally:
+            if driver:
+                driver.quit()
+
+        return bindata

uk_bin_collection-0.144.3/uk_bin_collection/uk_bin_collection/councils/MidUlsterDistrictCouncil.py

@@ -0,0 +1,135 @@
+import time
+
+from bs4 import BeautifulSoup
+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
+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):
+    """
+    Concrete classes have to implement all abstract operations of the
+    base class. They can also override some operations with a default
+    implementation.
+    """
+
+    def parse_data(self, page: str, **kwargs) -> dict:
+        driver = None
+        try:
+            user_postcode = kwargs.get("postcode")
+            if not user_postcode:
+                raise ValueError("No postcode provided.")
+            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__)
+            page = "https://www.midulstercouncil.org/resident/bins-recycling"
+
+            driver.get(page)
+
+            wait = WebDriverWait(driver, 10)
+            try:
+                accept_cookies_button = wait.until(
+                    EC.element_to_be_clickable(
+                        (
+                            By.XPATH,
+                            "//button/span[contains(text(), 'I Accept Cookies')]",
+                        )
+                    )
+                )
+                accept_cookies_button.click()
+            except Exception as e:
+                print(
+                    "Accept cookies button not found or clickable within the specified time."
+                )
+                pass
+
+            postcode_input = wait.until(
+                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(
+                    (By.XPATH, "//button[contains(text(), 'Go')]")
+                )
+            )
+
+            postcode_search_btn.click()
+
+            address_btn = wait.until(
+                EC.element_to_be_clickable(
+                    (By.XPATH, f"//button[contains(text(), '{user_paon}')]")
+                )
+            )
+            address_btn.send_keys(Keys.RETURN)
+
+            results_heading = wait.until(
+                EC.presence_of_element_located(
+                    (By.XPATH, "//h3[contains(text(), 'Collection day:')]")
+                )
+            )
+
+            results = wait.until(
+                EC.presence_of_element_located(
+                    (By.XPATH, "//div/h3[contains(text(), 'My address:')]/parent::div")
+                )
+            )
+
+            soup = BeautifulSoup(
+                results.get_attribute("innerHTML"), features="html.parser"
+            )
+            data = {"bins": []}
+
+            # 1. Extract the date string
+            try:
+                date_span = soup.select_one("h2.collection-day span.date-text")
+                if date_span:
+                    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)
+                else:
+                    collection_date = None
+            except Exception as e:
+                print(f"Failed to parse date: {e}")
+                collection_date = None
+
+            # 2. Extract bin types
+            if collection_date:
+                bin_blocks = soup.select("div.bin")
+                for bin_block in bin_blocks:
+                    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,
+                        })
+
+            # 3. Optional: sort bins by collectionDate
+            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
+            print(f"An error occurred: {e}")
+            # Optionally, re-raise the exception if you want it to propagate
+            raise
+        finally:
+            # This block ensures that the driver is closed regardless of an exception
+            if driver:
+                driver.quit()
+        return data