uk_bin_collection 0.143.5__tar.gz → 0.144.2__tar.gz

{uk_bin_collection-0.143.5 → uk_bin_collection-0.144.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.143.5
+Version: 0.144.2
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.143.5 → uk_bin_collection-0.144.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.143.5"
+version = "0.144.2"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.143.5 → uk_bin_collection-0.144.2}/uk_bin_collection/tests/input.json

@@ -877,6 +877,15 @@
         "wiki_name": "Gravesham Borough Council",
         "wiki_note": "Pass the UPRN. You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search)."
     },
+    "GreatYarmouthBoroughCouncil": {
+        "postcode": "NR31 7EB",
+        "skip_get_url": true,
+        "uprn": "100090834792",
+        "url": "https://myaccount.great-yarmouth.gov.uk/article/6456/Find-my-waste-collection-days",
+        "web_driver": "http://selenium:4444",
+        "wiki_name": "Great Yarmouth Borough Council",
+        "wiki_note": "Pass the postcode, and UPRN in their respective parameters. This parser requires a Selenium webdriver."
+    },
     "GuildfordCouncil": {
         "house_number": "THE LODGE, PUTTENHAM HILL HOUSE, PUTTENHAM HILL, PUTTENHAM, GUILDFORD, GU3 1AH",
         "postcode": "GU3 1AH",
@@ -1044,7 +1053,7 @@
         "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",
@@ -1268,6 +1277,15 @@
         "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",
@@ -1579,14 +1597,14 @@
         "wiki_note": "To get the UPRN, you can use [FindMyAddress](https://www.findmyaddress.co.uk/search). This parser requires a Selenium webdriver."
     },
     "RenfrewshireCouncil": {
-        "house_number": "1",
-        "paon": "1",
-        "postcode": "PA29ED",
-        "skip_get_url": false,
-        "url": "https://www.renfrewshire.gov.uk/article/2320/Check-your-bin-collection-day",
+        "house_number": "1, STATIONHOUSE DRIVE, JOHNSTONE, RENFREWSHIRE, PA6 7FJ",
+        "paon": "1, STATIONHOUSE DRIVE, JOHNSTONE, RENFREWSHIRE, PA6 7FJ",
+        "postcode": "PA6 7FJ",
+        "skip_get_url": true,
+        "url": "https://www.renfrewshire.gov.uk/bin-day",
         "web_driver": "http://selenium:4444",
         "wiki_name": "Renfrewshire Council",
-        "wiki_note": "Pass the house name/number and postcode in their respective parameters. This parser requires a Selenium webdriver."
+        "wiki_note": "Pass the full address as it appears on the website. This parser requires a Selenium webdriver."
     },
     "RhonddaCynonTaffCouncil": {
         "skip_get_url": true,
@@ -1668,7 +1686,7 @@
     },
     "SandwellBoroughCouncil": {
         "skip_get_url": true,
-        "uprn": "10008755549",
+        "uprn": "32101971",
         "url": "https://www.sandwell.gov.uk",
         "wiki_name": "Sandwell Borough Council",
         "wiki_note": "Pass the UPRN. You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search)."
@@ -2323,4 +2341,4 @@
         "wiki_name": "York Council",
         "wiki_note": "Provide your UPRN."
     }
-}
+}

{uk_bin_collection-0.143.5 → uk_bin_collection-0.144.2}/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-0.144.2/uk_bin_collection/uk_bin_collection/councils/GreatYarmouthBoroughCouncil.py

@@ -0,0 +1,140 @@
+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
+from selenium.webdriver.common.keys import Keys
+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):
+    """
+    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_uprn = kwargs.get("uprn")
+            user_postcode = kwargs.get("postcode")
+            headless = kwargs.get("headless")
+            web_driver = kwargs.get("web_driver")
+            url = kwargs.get("url")
+
+            check_uprn(user_uprn)
+            check_postcode(user_postcode)
+
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            
+            driver.get(url)
+
+            wait = WebDriverWait(driver, 10)
+            accept_cookies_button = wait.until(
+                EC.element_to_be_clickable(
+                    (
+                        By.NAME,
+                        "acceptall",
+                    )
+                )
+            )
+            accept_cookies_button.click()
+
+            postcode_input = WebDriverWait(driver, 10).until(
+                EC.element_to_be_clickable(
+                    (By.ID, "WASTECOLLECTIONCALENDARV2_ADDRESS_ALSF")
+                )
+            )
+
+            postcode_input.send_keys(user_postcode)
+            postcode_input.send_keys(Keys.TAB + Keys.ENTER)
+
+            time.sleep(2)
+            # Wait for address box to be visible
+            select_address_input = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (
+                        By.ID,
+                        "WASTECOLLECTIONCALENDARV2_ADDRESS_ALML",
+                    )
+                )
+            )
+            select_address_input.click()
+
+            # Assume select_address_input is already the dropdown <select> element
+            select = Select(select_address_input)
+
+            # Select the option with the matching UPRN
+            select.select_by_value(user_uprn)
+            select_address_input.click()
+
+            select_address_input.send_keys(Keys.TAB * 2 + Keys.ENTER)
+
+            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"))
+            )
+
+            soup = BeautifulSoup(driver.page_source, "html.parser")
+
+            bin_data = {"bins": []}
+            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"
+            }
+
+            for div in soup.select(".collection-area"):
+                img = div.select_one("img")
+                detail = div.select_one(".collection-detail")
+                date_text = detail.select_one("b").get_text(strip=True)
+
+                try:
+                    # Parse the date text
+                    date_obj = datetime.strptime(date_text + " 2025", "%A %d %B %Y")
+                    if date_obj.date() < datetime.today().date():
+                        continue  # Skip past dates
+                except ValueError:
+                    continue
+
+                # Determine bin type from alt or description
+                description = detail.get_text(separator=" ", strip=True).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
+                        }
+                        
+                        # 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"):
+                            next_collections[name] = bin_entry
+                            print(f"Found next collection for {name}: {formatted_date}")  # Debug output
+                        break
+
+            # Add the next collections to the bin_data
+            bin_data["bins"] = list(next_collections.values())
+
+        except Exception as e:
+            print(f"An error occurred: {e}")
+            raise
+        finally:
+            if driver:
+                driver.quit()
+                
+        print("\nFinal bin data:")
+        print(bin_data)  # Debug output
+        return bin_data

uk_bin_collection-0.144.2/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-0.144.2/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-0.143.5 → uk_bin_collection-0.144.2}/uk_bin_collection/uk_bin_collection/councils/RenfrewshireCouncil.py

@@ -19,6 +19,7 @@ class CouncilClass(AbstractGetBinDataClass):
         driver = None
         try:
             data = {"bins": []}
+            url = kwargs.get("url")
             user_paon = kwargs.get("paon")
             user_postcode = kwargs.get("postcode")
             web_driver = kwargs.get("web_driver")
@@ -28,9 +29,7 @@ class CouncilClass(AbstractGetBinDataClass):
 
             # Create Selenium webdriver
             driver = create_webdriver(web_driver, headless, None, __name__)
-            driver.get(
-                "https://www.renfrewshire.gov.uk/article/2320/Check-your-bin-collection-day"
-            )
+            driver.get("https://www.renfrewshire.gov.uk/bin-day")
 
             accept_button = WebDriverWait(driver, timeout=30).until(
                 EC.element_to_be_clickable((By.ID, "ccc-notify-accept"))

uk_bin_collection-0.144.2/uk_bin_collection/uk_bin_collection/councils/SandwellBoroughCouncil.py

@@ -0,0 +1,128 @@
+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):
+    """
+    Concrete classes have to implement all abstract operations of the
+    base class. They can also override some operations with a default
+    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 = requests.session()
+        # Establish a session and grab the session ID
+        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": {
+                "Property details": {
+                    "Uprn": {
+                        "value": user_uprn,
+                    },
+                    "NextCollectionFromDate": {
+                        "value": datetime.today().strftime("%Y-%m-%d")
+                    },
+                },
+            },
+        }
+        base_params = {
+            "repeat_against": "",
+            "noRetry": "false",
+            "getOnlyTokens": "undefined",
+            "log_id": "",
+            "app_name": "AF-Renderer::Self",
+            # unix_timestamp
+            "_": timestamp,
+            "sid": sid,
+        }
+        # (request_id, date field to use from response, bin type labels)
+
+        for request_id, date_key, bin_types in self.LOOKUPS:
+            params = {"id": request_id, **base_params}
+
+            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):
+                    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 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