uk_bin_collection 0.84.2__tar.gz → 0.85.1__tar.gz

{uk_bin_collection-0.84.2 → uk_bin_collection-0.85.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.84.2
+Version: 0.85.1
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.84.2 → uk_bin_collection-0.85.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.84.2"
+version = "0.85.1"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.84.2 → uk_bin_collection-0.85.1}/uk_bin_collection/tests/input.json

@@ -68,6 +68,13 @@
         "wiki_name": "Bedfordshire Council",
         "wiki_note": "In order to use this parser, you must provide a valid postcode and a uprn retrieved from the councils website for your specific address"
     },
+    "BelfastCityCouncil": {
+        "skip_get_url": true,
+        "url": "https://online.belfastcity.gov.uk/find-bin-collection-day/Default.aspx",
+        "wiki_name": "BelfastCityCouncil",
+        "postcode": "BT10 0GY",
+        "uprn": "185086469"
+    },
     "BexleyCouncil": {
         "house_number": "1 Dorchester Avenue, Bexley",
         "postcode": "DA5 3AH",
@@ -352,6 +359,14 @@
         "url": "https://www.eastleigh.gov.uk/waste-bins-and-recycling/collection-dates/your-waste-bin-and-recycling-collections?uprn=",
         "wiki_name": "Eastleigh Borough Council"
     },
+    "EnfieldCouncil": {
+        "url": "https://www.enfield.gov.uk/services/rubbish-and-recycling/find-my-collection-day",
+        "wiki_name": "Enfield Council",
+        "skip_get_url": true,
+        "postcode": "N13 5AJ",
+        "house_number": "111",
+        "web_driver": "http://selenium:4444"
+    },
     "EnvironmentFirst": {
         "url": "https://environmentfirst.co.uk/house.php?uprn=100060055444",
         "wiki_command_url_override": "https://environmentfirst.co.uk/house.php?uprn=XXXXXXXXXX",

uk_bin_collection-0.85.1/uk_bin_collection/uk_bin_collection/councils/BelfastCityCouncil.py

@@ -0,0 +1,100 @@
+import logging
+from datetime import datetime
+
+import requests
+import urllib
+
+from bs4 import BeautifulSoup
+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 get_session_variable(self, soup, id) -> str:
+        """Extract ASP.NET variable from the HTML."""
+        element = soup.find("input", {"id": id})
+        if element:
+            return element.get("value")
+        else:
+            raise ValueError(f"Unable to find element with id: {id}")
+
+    def parse_data(self, page: str, **kwargs) -> dict:
+        bin_data = {"bins": []}
+        headers = {
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:129.0) Gecko/20100101 Firefox/119.0"
+        }
+
+        session = requests.Session()
+        session.headers.update(headers)
+        
+        user_uprn = kwargs.get("uprn")
+        user_postcode = kwargs.get("postcode")
+        URL = "https://online.belfastcity.gov.uk/find-bin-collection-day/Default.aspx"
+
+        # Build initial ASP.NET variables for Postcode Find address
+        response = session.get(URL)
+        response.raise_for_status()
+        soup = BeautifulSoup(response.text, "html.parser")
+        form_data = {
+            "__EVENTTARGET": "",
+            "__EVENTARGUMENT": "",
+            "__VIEWSTATE": self.get_session_variable(soup, "__VIEWSTATE"),
+            "__VIEWSTATEGENERATOR": self.get_session_variable(soup, "__VIEWSTATEGENERATOR"),
+            "__SCROLLPOSITIONX": "0",
+            "__SCROLLPOSITIONY": "0",
+            "__EVENTVALIDATION": self.get_session_variable(soup, "__EVENTVALIDATION"),
+            "ctl00$MainContent$searchBy_radio": "P",
+            "ctl00$MainContent$Street_textbox": "",
+            "ctl00$MainContent$Postcode_textbox": user_postcode,
+            "ctl00$MainContent$AddressLookup_button": "Find address"
+        }
+
+        # Build intermediate ASP.NET variables for uprn Select address
+        response = session.post(URL, data=form_data)
+        response.raise_for_status()
+        soup = BeautifulSoup(response.text, "html.parser")
+        form_data = {
+            "__EVENTTARGET": "",
+            "__EVENTARGUMENT": "",
+            "__VIEWSTATE": self.get_session_variable(soup, "__VIEWSTATE"),
+            "__VIEWSTATEGENERATOR": self.get_session_variable(soup, "__VIEWSTATEGENERATOR"),
+            "__SCROLLPOSITIONX": "0",
+            "__SCROLLPOSITIONY": "0",
+            "__EVENTVALIDATION": self.get_session_variable(soup, "__EVENTVALIDATION"),
+            "ctl00$MainContent$searchBy_radio": "P",
+            "ctl00$MainContent$Street_textbox": "",
+            "ctl00$MainContent$Postcode_textbox": user_postcode,
+            "ctl00$MainContent$lstAddresses": user_uprn,
+            "ctl00$MainContent$SelectAddress_button": "Select address"
+        }
+
+        # Actual http call to get Bins Data
+        response = session.post(URL, data=form_data)
+        response.raise_for_status()
+        soup = BeautifulSoup(response.text, "html.parser")
+        
+        # Find Bins table and data
+        table = soup.find("div", {"id": "binsGrid"})
+        if table:
+            rows = table.find_all("tr")
+            for row in rows:
+                columns = row.find_all("td")
+                if len(columns) >= 4:
+                    collection_type = columns[0].get_text(strip=True)
+                    collection_date_raw = columns[3].get_text(strip=True)
+                    # if the month number is a single digit there are 2 spaces, stripping all spaces to make it consistent
+                    collection_date = datetime.strptime(collection_date_raw.replace(" ", ""),'%a%b%d%Y')
+                    bin_entry = {
+                        "type": collection_type,
+                        "collectionDate": collection_date.strftime(date_format),
+                    }
+                    bin_data["bins"].append(bin_entry)
+        return bin_data

uk_bin_collection-0.85.1/uk_bin_collection/uk_bin_collection/councils/EnfieldCouncil.py

@@ -0,0 +1,156 @@
+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 pdb
+
+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.enfield.gov.uk/services/rubbish-and-recycling/find-my-collection-day"
+            driver.get(page)
+
+            time.sleep(5)
+
+            try:
+                accept_cookies = WebDriverWait(driver, timeout=10).until(
+                    EC.presence_of_element_located((By.ID, "ccc-notify-reject"))
+                )
+                accept_cookies.click()
+            except:
+                print(
+                    "Accept cookies banner not found or clickable within the specified time."
+                )
+                pass
+
+            postcode_input = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (By.CSS_SELECTOR, '[aria-label="Enter your address"]')
+                )
+            )
+
+            postcode_input.send_keys(user_postcode)
+
+            find_address_button = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (By.ID, 'submitButton0')
+                )
+            )
+            find_address_button.click()
+
+            time.sleep(15)
+            # Wait for address box to be visible
+            select_address_input = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (
+                        By.CSS_SELECTOR,
+                        '[aria-label="Select full address"]',
+                    )
+                )
+            )
+
+            # Select address based
+            select = Select(select_address_input)
+            # Grab the first option as a template
+            first_option = select.options[0].accessible_name
+            template_parts = first_option.split(", ")
+            template_parts[0] = user_paon  # Replace the first part with user_paon
+
+            addr_label =  ", ".join(template_parts)
+            for addr_option in select.options:
+                option_name = addr_option.accessible_name[0 : len(addr_label)]
+                if option_name == addr_label:
+                    break
+            select.select_by_value(addr_option.text)
+
+            time.sleep(10)
+            # Wait for the specified div to be present
+            target_div_id = "FinalResults"
+            target_div = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located((By.ID, target_div_id))
+            )
+
+            time.sleep(5)
+            soup = BeautifulSoup(driver.page_source, "html.parser")
+
+            # Find the div with the specified id
+            target_div = soup.find("div", {"id": target_div_id})
+
+
+            # Check if the div is found
+            if target_div:
+                bin_data = {"bins": []}
+
+                for bin_div in target_div.find_all(
+                    "div"
+                ):
+                    # Extract the collection date from the message
+                    try:
+                        bin_collection_message = bin_div.find("p").text.strip()
+                        date_pattern = r"\b\d{2}/\d{2}/\d{4}\b"
+
+                        collection_date_string = (
+                        re.search(date_pattern, bin_div.text)
+                        .group(0)
+                        .strip()
+                        .replace(",", "")
+                    )
+                    except AttributeError:
+                        continue
+
+                    current_date = datetime.now()
+                    parsed_date = datetime.strptime(
+                        collection_date_string, "%d/%m/%Y"
+                    )
+                    # Check if the parsed date is in the past and not today
+                    if parsed_date.date() < current_date.date():
+                        # If so, set the year to the next year
+                        parsed_date = parsed_date.replace(year=current_date.year + 1)
+                    else:
+                        # If not, set the year to the current year
+                        parsed_date = parsed_date.replace(year=current_date.year)
+                    formatted_date = parsed_date.strftime("%d/%m/%Y")
+                    contains_date(formatted_date)
+
+                    # Extract the bin type from the message
+                    bin_type_match = re.search(r"Your next (.*?) collection", bin_collection_message)
+                    if bin_type_match:
+                        bin_info = {"type": bin_type_match.group(1), "collectionDate": formatted_date}
+                        bin_data["bins"].append(bin_info)
+            else:
+                raise ValueError("Collection data not found.")
+
+        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 bin_data