uk_bin_collection 0.138.1__py3-none-any.whl → 0.139.0__py3-none-any.whl

uk_bin_collection/uk_bin_collection/councils/ForestOfDeanDistrictCouncil.py

@@ -12,6 +12,7 @@ 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
+import re
 
 
 class CouncilClass(AbstractGetBinDataClass):
@@ -42,72 +43,82 @@ class CouncilClass(AbstractGetBinDataClass):
             wait = WebDriverWait(driver, 60)
             address_entry_field = wait.until(
                 EC.presence_of_element_located(
-                    (By.XPATH, '//*[@id="combobox-input-19"]')
+                    (By.XPATH, '//*[@placeholder="Search Properties..."]')
                 )
             )
 
             address_entry_field.send_keys(str(full_address))
 
             address_entry_field = wait.until(
-                EC.element_to_be_clickable((By.XPATH, '//*[@id="combobox-input-19"]'))
+                EC.element_to_be_clickable((By.XPATH, f'//*[@title="{full_address}"]'))
             )
             address_entry_field.click()
-            address_entry_field.send_keys(Keys.BACKSPACE)
-            address_entry_field.send_keys(str(full_address[len(full_address) - 1]))
 
-            first_found_address = wait.until(
+            next_button = wait.until(
                 EC.element_to_be_clickable(
-                    (By.XPATH, '//*[@id="dropdown-element-19"]/ul')
+                    (By.XPATH, "//lightning-button/button[contains(text(), 'Next')]")
                 )
             )
+            next_button.click()
 
-            first_found_address.click()
-            # Wait for the 'Select your property' dropdown to appear and select the first result
-            next_btn = wait.until(
-                EC.element_to_be_clickable((By.XPATH, "//lightning-button/button"))
-            )
-            next_btn.click()
-            bin_data = wait.until(
+            result = wait.until(
                 EC.presence_of_element_located(
-                    (By.XPATH, "//span[contains(text(), 'Container')]")
+                    (
+                        By.XPATH,
+                        '//table[@class="slds-table slds-table_header-fixed slds-table_bordered slds-table_edit slds-table_resizable-cols"]',
+                    )
                 )
             )
 
-            soup = BeautifulSoup(driver.page_source, features="html.parser")
+            # Make a BS4 object
+            soup = BeautifulSoup(
+                result.get_attribute("innerHTML"), features="html.parser"
+            )  # Wait for the 'Select your property' dropdown to appear and select the first result
 
+            data = {"bins": []}
+            today = datetime.now()
+            current_year = today.year
+
+            # Find all bin rows in the table
             rows = soup.find_all("tr", class_="slds-hint-parent")
-            current_year = datetime.now().year
 
             for row in rows:
-                columns = row.find_all("td")
-                if columns:
-                    container_type = row.find("th").text.strip()
-                    if columns[0].get_text() == "Today":
-                        collection_day = datetime.now().strftime("%a, %d %B")
-                    elif columns[0].get_text() == "Tomorrow":
-                        collection_day = (datetime.now() + timedelta(days=1)).strftime(
-                            "%a, %d %B"
-                        )
-                    else:
-                        collection_day = re.sub(
-                            r"[^a-zA-Z0-9,\s]", "", columns[0].get_text()
-                        ).strip()
-
-                    # Parse the date from the string
-                    parsed_date = datetime.strptime(collection_day, "%a, %d %B")
-                    if parsed_date < datetime(
-                        parsed_date.year, parsed_date.month, parsed_date.day
-                    ):
-                        parsed_date = parsed_date.replace(year=current_year + 1)
-                    else:
-                        parsed_date = parsed_date.replace(year=current_year)
-                    # Format the date as %d/%m/%Y
-                    formatted_date = parsed_date.strftime("%d/%m/%Y")
+                try:
+                    bin_type_cell = row.find("th")
+                    date_cell = row.find("td")
+
+                    if not bin_type_cell or not date_cell:
+                        continue
+
+                    container_type = bin_type_cell.get("data-cell-value", "").strip()
+                    raw_date_text = date_cell.get("data-cell-value", "").strip()
 
-                    # Add the bin type and collection date to the 'data' dictionary
+                    # Handle relative values like "Today" or "Tomorrow"
+                    if "today" in raw_date_text.lower():
+                        parsed_date = today
+                    elif "tomorrow" in raw_date_text.lower():
+                        parsed_date = today + timedelta(days=1)
+                    else:
+                        # Expected format: "Thu, 10 April"
+                        # Strip any rogue characters and try parsing
+                        cleaned_date = re.sub(r"[^\w\s,]", "", raw_date_text)
+                        try:
+                            parsed_date = datetime.strptime(cleaned_date, "%a, %d %B")
+                            parsed_date = parsed_date.replace(year=current_year)
+                            if parsed_date < today:
+                                # Date has passed this year, must be next year
+                                parsed_date = parsed_date.replace(year=current_year + 1)
+                        except Exception as e:
+                            print(f"Could not parse date '{cleaned_date}': {e}")
+                            continue
+
+                    formatted_date = parsed_date.strftime(date_format)
                     data["bins"].append(
                         {"type": container_type, "collectionDate": formatted_date}
                     )
+
+                except Exception as e:
+                    print(f"Error processing row: {e}")
         except Exception as e:
             # Here you can log the exception if needed
             print(f"An error occurred: {e}")

uk_bin_collection/uk_bin_collection/councils/GooglePublicCalendarCouncil.py

@@ -30,9 +30,8 @@ class CouncilClass(AbstractGetBinDataClass):
             except Exception:
                 continue
 
-            bindata["bins"].append({
-                "type": event.name,
-                "collectionDate": collection_date
-            })
+            bindata["bins"].append(
+                {"type": event.name, "collectionDate": collection_date}
+            )
 
         return bindata

uk_bin_collection/uk_bin_collection/councils/LondonBoroughOfRichmondUponThames.py

@@ -50,12 +50,18 @@ class CouncilClass(AbstractGetBinDataClass):
         for index, bin_type in enumerate(bin_types):
             # currently only handled weekly and garden collection, special collections like Christmas Day need to be added
             if index == WEEKLY_COLLECTION:
-                next_collection_date = get_next_day_of_week(collection_days[index].text.strip(), date_format)
+                next_collection_date = get_next_day_of_week(
+                    collection_days[index].text.strip(), date_format
+                )
             elif index == GARDEN_COLLECTION:
                 split_date_part = collection_days[index].text.split("More dates")[0]
-                next_collection_date = datetime.strptime(split_date_part.strip(), "%d %B %Y").strftime(date_format)
+                next_collection_date = datetime.strptime(
+                    split_date_part.strip(), "%d %B %Y"
+                ).strftime(date_format)
             else:
-                next_collection_date = datetime.strptime(collection_days[index].text.strip(), "%d %B %Y").strftime(date_format)
+                next_collection_date = datetime.strptime(
+                    collection_days[index].text.strip(), "%d %B %Y"
+                ).strftime(date_format)
 
             dict_data = {
                 "type": bin_type.text.strip(),
@@ -83,16 +89,12 @@ class CouncilClass(AbstractGetBinDataClass):
 
     def input_street_name(self, street_name, wait):
         input_element_postcodesearch = wait.until(
-            EC.visibility_of_element_located(
-                (By.ID, "Street")
-            )
+            EC.visibility_of_element_located((By.ID, "Street"))
         )
         input_element_postcodesearch.send_keys(street_name)
 
     def dismiss_cookie_banner(self, wait):
         cookie_banner = wait.until(
-            EC.visibility_of_element_located(
-                (By.ID, "ccc-dismiss-button")
-            )
+            EC.visibility_of_element_located((By.ID, "ccc-dismiss-button"))
         )
         cookie_banner.send_keys(Keys.ENTER)

uk_bin_collection/uk_bin_collection/councils/MiddlesbroughCouncil.py

@@ -12,6 +12,7 @@ from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataC
 
 import re
 
+
 class CouncilClass(AbstractGetBinDataClass):
     def parse_data(self, page: str, **kwargs) -> dict:
         try:
@@ -63,19 +64,27 @@ class CouncilClass(AbstractGetBinDataClass):
 
                 # **Regex to match "Wednesday, February 19" format**
                 match = re.match(r"([A-Za-z]+), ([A-Za-z]+) (\d{1,2})", raw_date)
-                
+
                 if match:
-                    day_name, month_name, day_number = match.groups()  # Extract components
+                    day_name, month_name, day_number = (
+                        match.groups()
+                    )  # Extract components
                     extracted_month = datetime.strptime(month_name, "%B").month
                     extracted_day = int(day_number)
 
                     # Handle Dec-Jan rollover: If month is before the current month, assume next year
-                    inferred_year = current_year + 1 if extracted_month < current_month else current_year
+                    inferred_year = (
+                        current_year + 1
+                        if extracted_month < current_month
+                        else current_year
+                    )
 
                     # **Correct the raw_date format before parsing**
                     raw_date = f"{day_name}, {month_name} {day_number}, {inferred_year}"
 
-                print(f"DEBUG: Final raw_date before parsing -> {raw_date}")  # Debugging output
+                print(
+                    f"DEBUG: Final raw_date before parsing -> {raw_date}"
+                )  # Debugging output
 
                 # Convert to required format (%d/%m/%Y)
                 try:

uk_bin_collection/uk_bin_collection/councils/MonmouthshireCountyCouncil.py

@@ -43,7 +43,11 @@ class CouncilClass(AbstractGetBinDataClass):
 
             # Extract collection date (e.g., "Monday 9th December")
             date_tag = panel.find("p")
-            if date_tag and "Your next collection date is" in date_tag.text.strip().replace("\r", "").replace("\n", ""):
+            if (
+                date_tag
+                and "Your next collection date is"
+                in date_tag.text.strip().replace("\r", "").replace("\n", "")
+            ):
                 collection_date = date_tag.find("strong").text.strip()
             else:
                 continue

uk_bin_collection/uk_bin_collection/councils/NewForestCouncil.py

@@ -127,9 +127,7 @@ class CouncilClass(AbstractGetBinDataClass):
             # Garden waste
             garden_waste = soup.find("div", class_="eb-2HIpCnWC-Override-EditorInput")
             if garden_waste:
-                match = re.search(
-                    r"(\d{2}/\d{2}/\d{4})", garden_waste.text
-                )
+                match = re.search(r"(\d{2}/\d{2}/\d{4})", garden_waste.text)
                 if match:
                     bins.append(
                         {"type": "Garden waste", "collectionDate": match.group(1)}

uk_bin_collection/uk_bin_collection/councils/NorthDevonCountyCouncil.py

@@ -0,0 +1,159 @@
+from time import sleep
+
+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 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")
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+            check_uprn(user_uprn)
+            check_postcode(user_postcode)
+
+            # Create Selenium webdriver
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            driver.get(
+                "https://my.northdevon.gov.uk/service/WasteRecyclingCollectionCalendar"
+            )
+
+            # Wait for iframe to load and switch to it
+            WebDriverWait(driver, 30).until(
+                EC.frame_to_be_available_and_switch_to_it((By.ID, "fillform-frame-1"))
+            )
+
+            # Wait for postcode entry box
+            postcode = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located((By.ID, "postcode_search"))
+            )
+            # Enter postcode
+            postcode.send_keys(user_postcode.replace(" ", ""))
+
+            # Wait for address selection dropdown to appear
+            address = Select(
+                WebDriverWait(driver, 10).until(
+                    EC.visibility_of_element_located((By.ID, "chooseAddress"))
+                )
+            )
+
+            # Wait for spinner to disappear (signifies options are loaded for select)
+            WebDriverWait(driver, 10).until(
+                EC.invisibility_of_element_located(
+                    (By.CLASS_NAME, "spinner-outer")
+                )  # row-fluid spinner-outer
+            )
+
+            # Sometimes the options aren't fully there despite the spinner being gone, wait another 2 seconds.
+            sleep(2)
+
+            # Select address by UPRN
+            address.select_by_value(user_uprn)
+
+            # Wait for spinner to disappear (signifies data is loaded)
+            WebDriverWait(driver, 10).until(
+                EC.invisibility_of_element_located((By.CLASS_NAME, "spinner-outer"))
+            )
+
+            sleep(2)
+
+            address_confirmation = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (By.XPATH, "//h2[contains(text(), 'Your address')]")
+                )
+            )
+
+            next_button = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (By.XPATH, "//button/span[contains(@class, 'nextText')]")
+                )
+            )
+
+            next_button.click()
+
+            results = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (By.XPATH, "//h4[contains(text(), 'Key')]")
+                )
+            )
+
+            # Find data table
+            data_table = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (
+                        By.XPATH,
+                        '//div[@data-field-name="html1"]/div[contains(@class, "fieldContent")]',
+                    )
+                )
+            )
+
+            # Make a BS4 object
+            soup = BeautifulSoup(
+                data_table.get_attribute("innerHTML"), features="html.parser"
+            )
+
+            # Initialize the data dictionary
+            data = {"bins": []}
+
+            # Loop through each list of waste dates
+            waste_sections = soup.find_all("ul", class_="wasteDates")
+
+            current_month_year = None
+
+            for section in waste_sections:
+                for li in section.find_all("li", recursive=False):
+                    if "MonthLabel" in li.get("class", []):
+                        # Extract month and year (e.g., "April 2025")
+                        header = li.find("h4")
+                        if header:
+                            current_month_year = header.text.strip()
+                    elif any(
+                        bin_class in li.get("class", [])
+                        for bin_class in ["BlackBin", "GreenBin", "Recycling"]
+                    ):
+                        bin_type = li.find("span", class_="wasteType").text.strip()
+                        day = li.find("span", class_="wasteDay").text.strip()
+                        weekday = li.find("span", class_="wasteName").text.strip()
+
+                        if current_month_year and day:
+                            try:
+                                full_date = f"{day} {current_month_year}"
+                                collection_date = datetime.strptime(
+                                    full_date, "%d %B %Y"
+                                ).strftime(date_format)
+                                dict_data = {
+                                    "type": bin_type,
+                                    "collectionDate": collection_date,
+                                }
+                                data["bins"].append(dict_data)
+                            except Exception as e:
+                                print(f"Skipping invalid date '{full_date}': {e}")
+
+            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/NorwichCityCouncil.py

@@ -53,7 +53,12 @@ class CouncilClass(AbstractGetBinDataClass):
         if alternateCheck:
             bin_types = strong[2].text.strip().replace(".", "").split(" and ")
             for bin in bin_types:
-                collections.append((bin.capitalize(), datetime.strptime(strong[1].text.strip(), date_format)))
+                collections.append(
+                    (
+                        bin.capitalize(),
+                        datetime.strptime(strong[1].text.strip(), date_format),
+                    )
+                )
 
         else:
             p_tag = soup.find_all("p")
@@ -63,11 +68,18 @@ class CouncilClass(AbstractGetBinDataClass):
                     p.text.split("Your ")[1].split(" is collected")[0].split(" and ")
                 )
                 for bin in bin_types:
-                    collections.append((bin.capitalize(), datetime.strptime(strong[1].text.strip(), date_format)))
+                    collections.append(
+                        (
+                            bin.capitalize(),
+                            datetime.strptime(strong[1].text.strip(), date_format),
+                        )
+                    )
                 i += 2
 
         if len(strong) > 3:
-            collections.append(("Garden", datetime.strptime(strong[4].text.strip(), date_format)))
+            collections.append(
+                ("Garden", datetime.strptime(strong[4].text.strip(), date_format))
+            )
 
         ordered_data = sorted(collections, key=lambda x: x[1])
         for item in ordered_data: