uk_bin_collection 0.144.1__py3-none-any.whl → 0.144.3__py3-none-any.whl

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/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/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/uk_bin_collection/councils/KnowsleyMBCouncil.py

@@ -1,140 +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 Select
-from selenium.webdriver.support.wait import WebDriverWait
+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
 
 
-# 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:
-            data = {"bins": []}
-            collections = []
+            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)
 
-            # Create Selenium webdriver
             driver = create_webdriver(web_driver, headless, None, __name__)
-            driver.get(
-                "https://knowsleytransaction.mendixcloud.com/link/youarebeingredirected?target=bincollectioninformation"
-            )
+            driver.set_window_size(1920, 1080)  # 👈 ensure full viewport
 
-            # Wait for the postcode field to appear then populate it
-            inputElement_postcode = WebDriverWait(driver, 30).until(
-                EC.visibility_of_element_located(
-                    (
-                        By.XPATH,
-                        "/html/body/div[1]/div/div/div/div/div/div[2]/div/div/div/div/div/div[3]/div/div[1]/div/div[1]/div/div/input",
-                    )
+            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')]")
                 )
             )
-            inputElement_postcode.send_keys(user_postcode)
+            search_btn.send_keys(Keys.RETURN)
 
-            # Wait for address search button, then click it
-            addressSearch_button = WebDriverWait(driver, 10).until(
+            # Step 2: Enter postcode
+            postcode_box = WebDriverWait(driver, 60).until(
                 EC.presence_of_element_located(
-                    (
-                        By.XPATH,
-                        "/html/body/div[1]/div/div/div/div/div/div[2]/div/div/div/div/div/div[3]/div/div[1]/div/div[2]/div/button",
-                    )
+                    (By.XPATH, "//label[contains(text(), 'Please enter the post code')]/following-sibling::input")
                 )
             )
-            addressSearch_button.click()
+            postcode_box.send_keys(user_postcode)
 
-            # Wait until the address list has loaded
-            WebDriverWait(driver, 30).until(
-                EC.presence_of_element_located(
-                    (
-                        By.XPATH,
-                        "/html/body/div[1]/div/div/div/div/div/div[2]/div/div/div/div/div/div[3]/div/div[1]/div/div[3]/div/div",
-                    )
+            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)
 
-            # Select the correct address from the list
-            addressList_rows = driver.find_elements(By.CLASS_NAME, "row")
-            for row in addressList_rows:
-                option_name = row.text[0 : len(user_paon)]
-                if option_name == user_paon:
-                    break
-            address_to_select = row.find_element(By.LINK_TEXT, "Choose this address")
-            address_to_select.click()
-
-            # Wait for bin dates to load
-            WebDriverWait(driver, 20).until(
+            # 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,
-                        "/html/body/div[1]/div/div/div/div/div/div[2]/div/div/div/div/div/div[3]/div/div[1]/div/div[4]/div/div",
-                    )
+                    (By.XPATH, "//label[contains(text(), 'collection')]")
                 )
             )
 
-            # Parse the HTML from the WebDriver
-            soup = BeautifulSoup(driver.page_source, features="html.parser")
-            soup.prettify()
+            bin_info_container = driver.find_element(
+                By.XPATH, "//label[contains(text(), 'collection')]/ancestor::div[contains(@class, 'mx-dataview-content')]")
 
-            z = soup.find(
-                "div", {"class": "mx-name-textBox5 mx-textbox form-group"}
-            ).find_next("div", {"class": "form-control-static"})
+            soup = BeautifulSoup(bin_info_container.get_attribute("innerHTML"), "html.parser")
 
-            maroon_bin_date = datetime.strptime(
-                soup.find("div", {"class": "mx-name-textBox3 mx-textbox form-group"})
-                .find_next("div", {"class": "form-control-static"})
-                .get_text(strip=True),
-                "%A %d/%m/%Y",
-            )
-            collections.append(("Maroon bin", maroon_bin_date))
+            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
 
-            grey_bin_date = datetime.strptime(
-                soup.find("div", {"class": "mx-name-textBox4 mx-textbox form-group"})
-                .find_next("div", {"class": "form-control-static"})
-                .get_text(strip=True),
-                "%A %d/%m/%Y",
-            )
-            collections.append(("Grey bin", grey_bin_date))
+                label_text = label.text.strip()
+                value_text = value.text.strip()
 
-            blue_bin_date = datetime.strptime(
-                soup.find("div", {"class": "mx-name-textBox5 mx-textbox form-group"})
-                .find_next("div", {"class": "form-control-static"})
-                .get_text(strip=True),
-                "%A %d/%m/%Y",
-            )
-            collections.append(("Blue bin", blue_bin_date))
+                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,
+                    })
 
-            ordered_data = sorted(collections, key=lambda x: x[1])
-            for item in ordered_data:
-                dict_data = {
-                    "type": item[0].capitalize(),
-                    "collectionDate": item[1].strftime(date_format),
-                }
-                data["bins"].append(dict_data)
+            bindata["bins"].sort(
+                key=lambda x: datetime.strptime(x["collectionDate"], "%d/%m/%Y")
+            )
 
         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
+        return bindata

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

uk_bin_collection/uk_bin_collection/councils/SandwellBoroughCouncil.py

@@ -1,10 +1,14 @@
+import logging
 import time
+from datetime import datetime
 
 import requests
 
 from uk_bin_collection.uk_bin_collection.common import *
 from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
 
+logger = logging.getLogger(__name__)
+
 
 # import the wonderful Beautiful Soup and the URL grabber
 class CouncilClass(AbstractGetBinDataClass):
@@ -14,29 +18,51 @@ class CouncilClass(AbstractGetBinDataClass):
     implementation.
     """
 
+    SESSION_URL = "https://my.sandwell.gov.uk/authapi/isauthenticated?uri=https%253A%252F%252Fmy.sandwell.gov.uk%252Fen%252F..."
+    API_URL = "https://my.sandwell.gov.uk/apibroker/runLookup"
+    HEADERS = {
+        "Content-Type": "application/json",
+        "Accept": "application/json",
+        "User-Agent": "Mozilla/5.0",
+        "X-Requested-With": "XMLHttpRequest",
+        "Referer": "https://my.sandwell.gov.uk/fillform/?iframe_id=fillform-frame-1&db_id=",
+    }
+    LOOKUPS = [
+        (
+            "58a1a71694992",
+            "DWDate",
+            [
+                "Recycling (Blue)",
+                "Household Waste (Grey)",
+                "Food Waste (Brown)",
+                "Batteries",
+            ],
+        ),
+        ("56b1cdaf6bb43", "GWDate", ["Garden Waste (Green)"]),
+    ]
+
     def parse_data(self, page: str, **kwargs) -> dict:
+        """
+        Parse bin collection data for a given UPRN using the Sandwell API.
 
+        Args:
+            page (str): Unused HTML page content.
+            **kwargs: Must include 'uprn'.
+
+        Returns:
+            dict: A dictionary with bin collection types and dates.
+        """
         user_uprn = kwargs.get("uprn")
         check_uprn(user_uprn)
         bindata = {"bins": []}
 
-        SESSION_URL = "https://my.sandwell.gov.uk/authapi/isauthenticated?uri=https%253A%252F%252Fmy.sandwell.gov.uk%252Fen%252FAchieveForms%252F%253Fform_uri%253Dsandbox-publish%253A%252F%252FAF-Process-ebaa26a2-393c-4a3c-84f5-e61564192a8a%252FAF-Stage-e4c2cb32-db55-4ff5-845c-8b27f87346c4%252Fdefinition.json%2526redirectlink%253D%25252Fen%2526cancelRedirectLink%253D%25252Fen%2526consentMessage%253Dyes&hostname=my.sandwell.gov.uk&withCredentials=true"
-
-        API_URL = "https://my.sandwell.gov.uk/apibroker/runLookup"
-
-        headers = {
-            "Content-Type": "application/json",
-            "Accept": "application/json",
-            "User-Agent": "Mozilla/5.0",
-            "X-Requested-With": "XMLHttpRequest",
-            "Referer": "https://my.sandwell.gov.uk/fillform/?iframe_id=fillform-frame-1&db_id=",
-        }
-        s = requests.session()
+        session = requests.session()
         # Establish a session and grab the session ID
-        r = s.get(SESSION_URL)
+        r = session.get(self.SESSION_URL)
         r.raise_for_status()
         session_data = r.json()
         sid = session_data["auth-session"]
+        timestamp = str(int(time.time() * 1000))
 
         payload = {
             "formValues": {
@@ -45,7 +71,7 @@ class CouncilClass(AbstractGetBinDataClass):
                         "value": user_uprn,
                     },
                     "NextCollectionFromDate": {
-                        "value": datetime.now().strftime("%Y-%m-%d"),
+                        "value": datetime.today().strftime("%Y-%m-%d")
                     },
                 },
             },
@@ -57,39 +83,46 @@ class CouncilClass(AbstractGetBinDataClass):
             "log_id": "",
             "app_name": "AF-Renderer::Self",
             # unix_timestamp
-            "_": str(int(time.time() * 1000)),
+            "_": timestamp,
             "sid": sid,
         }
         # (request_id, date field to use from response, bin type labels)
-        lookups = [
-            (
-                "58a1a71694992",
-                "DWDate",
-                [
-                    "Recycling (Blue)",
-                    "Household Waste (Grey)",
-                    "Food Waste (Brown)",
-                    "Batteries",
-                ],
-            ),
-            ("56b1cdaf6bb43", "GWDate", ["Garden Waste (Green)"]),
-        ]
-
-        for request_id, date_key, bin_types in lookups:
+
+        for request_id, date_key, bin_types in self.LOOKUPS:
             params = {"id": request_id, **base_params}
 
-            resp = s.post(API_URL, json=payload, headers=headers, params=params)
-            resp.raise_for_status()
-            result = resp.json()
+            try:
+                resp = session.post(
+                    self.API_URL, json=payload, headers=self.HEADERS, params=params
+                )
+                resp.raise_for_status()
+                result = resp.json()
 
-            rows_data = result["integration"]["transformed"]["rows_data"]
-            if not isinstance(rows_data, dict):
-                # Garden waste for some Uprns returns an empty list
-                continue
+                rows_data = result["integration"]["transformed"]["rows_data"]
+
+                if not isinstance(rows_data, dict):
+                    logger.warning("Unexpected rows_data format: %s", rows_data)
+                    continue
+
+                for row in rows_data.values():
+                    date = row.get(date_key)
+                    if not date:
+                        logger.warning(
+                            "Date key '%s' missing in row: %s", date_key, row
+                        )
+                        continue
 
-            for row in rows_data.values():
-                date = row[date_key]
-                for bin_type in bin_types:
-                    bindata["bins"].append({"type": bin_type, "collectionDate": date})
+                    for bin_type in bin_types:
+                        bindata["bins"].append(
+                            {"type": bin_type, "collectionDate": date}
+                        )
+
+            except requests.RequestException as e:
+                logger.error("API request failed: %s", e)
+                continue
+            except (KeyError, ValueError, TypeError) as e:
+                logger.warning("Unexpected structure in response: %s", e)
+                continue
 
+        logger.info("Parsed bins: %s", bindata["bins"])
         return bindata

{uk_bin_collection-0.144.1.dist-info → uk_bin_collection-0.144.3.dist-info}/METADATA

@@ -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.dist-info → uk_bin_collection-0.144.3.dist-info}/RECORD

@@ -3,7 +3,7 @@ uk_bin_collection/tests/check_selenium_url_in_input.json.py,sha256=Iecdja0I3XIiY
 uk_bin_collection/tests/council_feature_input_parity.py,sha256=DO6Mk4ImYgM5ZCZ-cutwz5RoYYWZRLYx2tr6zIs_9Rc,3843
 uk_bin_collection/tests/features/environment.py,sha256=VQZjJdJI_kZn08M0j5cUgvKT4k3iTw8icJge1DGOkoA,127
 uk_bin_collection/tests/features/validate_council_outputs.feature,sha256=SJK-Vc737hrf03tssxxbeg_JIvAH-ddB8f6gU1LTbuQ,251
-uk_bin_collection/tests/input.json,sha256=6GN41kIFiUAvCo4mzwTWpxumcY9MSYTqCIqsvY5wg_4,121957
+uk_bin_collection/tests/input.json,sha256=zxDyP74ZRcogEGCcRCGeDj1EOU61mpQJXSsv8z5sznE,122869
 uk_bin_collection/tests/output.schema,sha256=ZwKQBwYyTDEM4G2hJwfLUVM-5v1vKRvRK9W9SS1sd18,1086
 uk_bin_collection/tests/step_defs/step_helpers/file_handler.py,sha256=Ygzi4V0S1MIHqbdstUlIqtRIwnynvhu4UtpweJ6-5N8,1474
 uk_bin_collection/tests/step_defs/test_validate_council.py,sha256=VZ0a81sioJULD7syAYHjvK_-nT_Rd36tUyzPetSA0gk,3475
@@ -12,7 +12,7 @@ uk_bin_collection/tests/test_common_functions.py,sha256=cCUwXKGijmsvTLz0KoaedXkp
 uk_bin_collection/tests/test_conftest.py,sha256=qI_zgGjNOnwE9gmZUiuirL1SYz3TFw5yfGFgT4T3aG4,1100
 uk_bin_collection/tests/test_get_data.py,sha256=sFJz_Fd6o-1r2gdmzY52JGwVi0Of_mDzvYSoc7a3RUw,7239
 uk_bin_collection/uk_bin_collection/collect_data.py,sha256=dB7wWXsJX4fm5bIf84lexkvHIcO54CZ3JPxqmS-60YY,4654
-uk_bin_collection/uk_bin_collection/common.py,sha256=Wj6o2NaxYDE1lkpYzMFDIZiPARX0K3xmt-5bnt2kjSI,10970
+uk_bin_collection/uk_bin_collection/common.py,sha256=r3hV7HZv-WKr11nYq-99Dpmw_UPK6359MUFD6vDuFLc,11022
 uk_bin_collection/uk_bin_collection/councils/AberdeenCityCouncil.py,sha256=Je8VwVLK9KnYl9vqf2gWJ7ZYDgUq3A7caDiIzk5Xof8,4194
 uk_bin_collection/uk_bin_collection/councils/AberdeenshireCouncil.py,sha256=aO1CSdyqa8oAD0fB79y1Q9bikAWCP_JFa7CsyTa2j9s,1655
 uk_bin_collection/uk_bin_collection/councils/AdurAndWorthingCouncils.py,sha256=ppbrmm-MzB1wOulK--CU_0j4P-djNf3ozMhHnmQFqLo,1511
@@ -146,6 +146,7 @@ uk_bin_collection/uk_bin_collection/councils/HerefordshireCouncil.py,sha256=JpQh
 uk_bin_collection/uk_bin_collection/councils/HertsmereBoroughCouncil.py,sha256=ZbSsmqHStd2JtTMAq1Bhcvsj1BYp6ijELyOjZFX2GSw,6435
 uk_bin_collection/uk_bin_collection/councils/HighPeakCouncil.py,sha256=x7dfy8mdt2iGl8qJxHb-uBh4u0knmi9MJ6irOJw9WYA,4805
 uk_bin_collection/uk_bin_collection/councils/HighlandCouncil.py,sha256=GNxDU65QuZHV5va2IrKtcJ6TQoDdwmV03JvkVqOauP4,3291
+uk_bin_collection/uk_bin_collection/councils/Hillingdon.py,sha256=R1enDv5gjwCUT3HKgj8C87xWrwvrutAN6XLu5P7tef8,10532
 uk_bin_collection/uk_bin_collection/councils/HinckleyandBosworthBoroughCouncil.py,sha256=51vXTKrstfJhb7cLCcrsvA9qKCsptyNMZvy7ML9DasM,2344
 uk_bin_collection/uk_bin_collection/councils/HounslowCouncil.py,sha256=LXhJ47rujx7k3naz0tFiTT1l5k6gAYcVdekJN1t_HLY,4564
 uk_bin_collection/uk_bin_collection/councils/HullCityCouncil.py,sha256=UHcesBoctFVcXDYuwfag43KbcJcopkEDzJ-54NxtK0Q,1851
@@ -155,7 +156,7 @@ uk_bin_collection/uk_bin_collection/councils/IslingtonCouncil.py,sha256=xavzL6ZI
 uk_bin_collection/uk_bin_collection/councils/KingsLynnandWestNorfolkBC.py,sha256=Shj18R-7NW4ivqJJFVJOLmf-EeN6hXP2Of30oI-SeAQ,1932
 uk_bin_collection/uk_bin_collection/councils/KingstonUponThamesCouncil.py,sha256=iZ7njIxccCGBhUUWWd9Azh7cxUAKaofebCm3lo-TuxA,3543
 uk_bin_collection/uk_bin_collection/councils/KirkleesCouncil.py,sha256=WPM7koIqK5Wz-iT9Mds6AptihGZtl4KZhkVTcT9cx_c,2762
-uk_bin_collection/uk_bin_collection/councils/KnowsleyMBCouncil.py,sha256=VdlWDESoHfr_X0r8-UMaLMUQhKZOa2BnpVPkX-1u3EQ,5605
+uk_bin_collection/uk_bin_collection/councils/KnowsleyMBCouncil.py,sha256=DsCVBCprCS2u_2E8IRBGOO_NWo-WC8i9jSxUI-rue_s,4654
 uk_bin_collection/uk_bin_collection/councils/LancasterCityCouncil.py,sha256=FmHT6oyD4BwWuhxA80PHnGA7HPrLuyjP_54Cg8hT6k4,2537
 uk_bin_collection/uk_bin_collection/councils/LeedsCityCouncil.py,sha256=VWdhw6qvCTj3EhFHf046xPWgc6szeFW2Xbt6W2J0e6w,4371
 uk_bin_collection/uk_bin_collection/councils/LeicesterCityCouncil.py,sha256=o3kE8sjThQa4_AvSK5NH8VH7jWFO9MMPgoqLOTjyh0w,1851
@@ -183,6 +184,7 @@ uk_bin_collection/uk_bin_collection/councils/MidAndEastAntrimBoroughCouncil.py,s
 uk_bin_collection/uk_bin_collection/councils/MidDevonCouncil.py,sha256=8MxqGgOJVseMkrTmEMT0EyDW7UMbXMoa5ZcJ2nD55Ew,3367
 uk_bin_collection/uk_bin_collection/councils/MidSuffolkDistrictCouncil.py,sha256=h6M-v5jVYe7OlQ47Vf-0pEgECZLOOacK3_XE6zbpsM4,6329
 uk_bin_collection/uk_bin_collection/councils/MidSussexDistrictCouncil.py,sha256=AZgC9wmDLEjUOtIFvf0ehF5LHturXTH4DkE3ioPSVBA,6254
+uk_bin_collection/uk_bin_collection/councils/MidUlsterDistrictCouncil.py,sha256=dBDZvWQRlOQQDhLJVq0OzQy6iazstQ9NnDb6PIj5NOw,5020
 uk_bin_collection/uk_bin_collection/councils/MiddlesbroughCouncil.py,sha256=BiYexiZj-9PxRnB7sYRy0G-72s3L9jfh2vd1Y2NQwtg,4223
 uk_bin_collection/uk_bin_collection/councils/MidlothianCouncil.py,sha256=-VKvdIhrs859-YqxsNMzRWm2alP1avBR1_J8O9gJnYw,6725
 uk_bin_collection/uk_bin_collection/councils/MiltonKeynesCityCouncil.py,sha256=7e2pGBLCw24pNItHeI9jkxQ3rEOZ4WC4zVlbvKYGdXE,2600
@@ -239,7 +241,7 @@ uk_bin_collection/uk_bin_collection/councils/RunnymedeBoroughCouncil.py,sha256=v
 uk_bin_collection/uk_bin_collection/councils/RushcliffeBoroughCouncil.py,sha256=nWo8xeER71FEbnMTX8W9bcwZNpLEExWzPvgRT7DmcMc,4221
 uk_bin_collection/uk_bin_collection/councils/RushmoorCouncil.py,sha256=ZsGnXjoEaOS6U7fI0w7-uqxayAHdNVKsJi2fqIWEls8,3375
 uk_bin_collection/uk_bin_collection/councils/SalfordCityCouncil.py,sha256=XUGemp2cdzsvkWjnv2m4YKTMcoKDUfIlVy3YucX-_o4,2601
-uk_bin_collection/uk_bin_collection/councils/SandwellBoroughCouncil.py,sha256=Y9aPYNu1ZahJJ0BuDIWoQqynSz2AQGUcwrJR_cvPsvc,3516
+uk_bin_collection/uk_bin_collection/councils/SandwellBoroughCouncil.py,sha256=KePbZ_Ec4mvVEKu7-hd2CDy_qaWjhiNUnmbYh-Ghw2A,4275
 uk_bin_collection/uk_bin_collection/councils/SeftonCouncil.py,sha256=XUEz2li0oHrRhdkls5qzlZNZ0GuwSG7r0dwsL-qdoFA,2480
 uk_bin_collection/uk_bin_collection/councils/SevenoaksDistrictCouncil.py,sha256=qqrrRaSVm9CYAtm0rB2ZnyH_nLwaReuacoUxZpo597k,4260
 uk_bin_collection/uk_bin_collection/councils/SheffieldCityCouncil.py,sha256=9g9AeiackoWyej9EVlKUzywzAtMuBVD0f93ZryAUha8,2016
@@ -329,8 +331,8 @@ uk_bin_collection/uk_bin_collection/councils/YorkCouncil.py,sha256=I2kBYMlsD4bId
 uk_bin_collection/uk_bin_collection/councils/council_class_template/councilclasstemplate.py,sha256=EQWRhZ2pEejlvm0fPyOTsOHKvUZmPnxEYO_OWRGKTjs,1158
 uk_bin_collection/uk_bin_collection/create_new_council.py,sha256=m-IhmWmeWQlFsTZC4OxuFvtw5ZtB8EAJHxJTH4O59lQ,1536
 uk_bin_collection/uk_bin_collection/get_bin_data.py,sha256=YvmHfZqanwrJ8ToGch34x-L-7yPe31nB_x77_Mgl_vo,4545
-uk_bin_collection-0.144.1.dist-info/LICENSE,sha256=vABBUOzcrgfaTKpzeo-si9YVEun6juDkndqA8RKdKGs,1071
-uk_bin_collection-0.144.1.dist-info/METADATA,sha256=Pk5QeIPJ_FQYDxoe4UgUdqG8-vDxsX4CbzkE-EGVmzs,19858
-uk_bin_collection-0.144.1.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-uk_bin_collection-0.144.1.dist-info/entry_points.txt,sha256=36WCSGMWSc916S3Hi1ZkazzDKHaJ6CD-4fCEFm5MIao,90
-uk_bin_collection-0.144.1.dist-info/RECORD,,
+uk_bin_collection-0.144.3.dist-info/LICENSE,sha256=vABBUOzcrgfaTKpzeo-si9YVEun6juDkndqA8RKdKGs,1071
+uk_bin_collection-0.144.3.dist-info/METADATA,sha256=p836krZfbmZyZq_lEotYfXqB6JdLNtK3y6b4lhFIioM,19858
+uk_bin_collection-0.144.3.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+uk_bin_collection-0.144.3.dist-info/entry_points.txt,sha256=36WCSGMWSc916S3Hi1ZkazzDKHaJ6CD-4fCEFm5MIao,90
+uk_bin_collection-0.144.3.dist-info/RECORD,,