uk_bin_collection 0.81.0__py3-none-any.whl → 0.82.1__py3-none-any.whl

uk_bin_collection/tests/input.json

@@ -283,10 +283,10 @@
         "wiki_name": "Doncaster Council"
     },
     "DorsetCouncil": {
-        "url": "https://gi.dorsetcouncil.gov.uk/mapping/mylocal/viewresults/100040711049",
-        "wiki_command_url_override": "https://gi.dorsetcouncil.gov.uk/mapping/mylocal/viewresults/XXXXXXXX",
-        "wiki_name": "Dorset Council",
-        "wiki_note": "Replace XXXXXXXX with UPRN."
+        "skip_get_url": true,
+        "url": "https://www.dorsetcouncil.gov.uk/",
+        "uprn": "100040711049",
+        "wiki_name": "Dorset Council"
     },
     "DoverDistrictCouncil": {
         "url": "https://collections.dover.gov.uk/property/100060908340",
@@ -573,12 +573,13 @@
         "wiki_note": "Pass the house name/number plus the name of the street with the postcode parameter, wrapped in double quotes.  Check the address in the web site first. This version will only pick the first SHOW button returned by the search or if it is fully unique.  The search is not very predictable (e.g. house number 4 returns 14,24,4,44 etc.)."
     },
     "MidSussexDistrictCouncil": {
-        "house_number": "OAKLANDS",
+        "house_number": "OAKLANDS, OAKLANDS ROAD RH16 1SS",
         "postcode": "RH16 1SS",
         "skip_get_url": true,
         "url": "https://www.midsussex.gov.uk/waste-recycling/bin-collection/",
         "wiki_name": "Mid Sussex District Council",
-        "wiki_note": "Pass the name of the street with the house number parameter, wrapped in double quotes"
+        "wiki_note": "Pass the name of the street with the house number parameter, wrapped in double quotes",
+        "web_driver": "http://selenium:4444"
     },
     "MiltonKeynesCityCouncil": {
         "uprn": "Fullers Slade",

uk_bin_collection/tests/step_defs/test_validate_council.py

@@ -1,13 +1,13 @@
+import json
 import logging
 import traceback
-from typing import Any, Generator, Callable
-import json
-
-import pytest
-from pytest_bdd import scenario, given, when, then, parsers
 from functools import wraps
+from typing import Any, Callable, Generator
 
+import pytest
+from pytest_bdd import given, parsers, scenario, then, when
 from step_helpers import file_handler
+
 from uk_bin_collection.uk_bin_collection import collect_data
 
 logging.basicConfig(level=logging.INFO, format="%(levelname)s - %(message)s")

uk_bin_collection/uk_bin_collection/collect_data.py

@@ -11,8 +11,8 @@ from uk_bin_collection.uk_bin_collection.get_bin_data import (
 _LOGGER = logging.getLogger(__name__)
 
 
-# Dynamically importing the council processor
 def import_council_module(module_name, src_path="councils"):
+    """Dynamically import the council processor module."""
     module_path = os.path.realpath(os.path.join(os.path.dirname(__file__), src_path))
     if module_path not in sys.path:
         sys.path.append(module_path)
@@ -25,6 +25,7 @@ class UKBinCollectionApp:
         self.parsed_args = None
 
     def setup_arg_parser(self):
+        """Setup the argument parser for the script."""
         self.parser = argparse.ArgumentParser(
             description="UK Bin Collection Data Parser"
         )
@@ -38,8 +39,7 @@ class UKBinCollectionApp:
             "-p",
             "--postcode",
             type=str,
-            help="Postcode to parse - should include a space and be wrapped in "
-            "double-quotes",
+            help="Postcode to parse - should include a space and be wrapped in double quotes",
             required=False,
         )
         self.parser.add_argument(
@@ -58,6 +58,7 @@ class UKBinCollectionApp:
         self.parser.add_argument(
             "-w",
             "--web_driver",
+            type=str,
             help="URL for remote Selenium web driver - should be wrapped in double quotes",
             required=False,
         )
@@ -74,7 +75,13 @@ class UKBinCollectionApp:
             help="Should Selenium be headless. Defaults to true. Can be set to false to debug council",
         )
         self.parser.set_defaults(headless=True)
-
+        self.parser.add_argument(
+            "--local_browser",
+            dest="local_browser",
+            action="store_true",
+            help="Should Selenium be run on a remote server or locally. Defaults to false.",
+            required=False,
+        )
         self.parser.add_argument(
             "-d",
             "--dev_mode",
@@ -85,43 +92,37 @@ class UKBinCollectionApp:
         self.parsed_args = None
 
     def set_args(self, args):
+        """Parse the arguments from the command line."""
         self.parsed_args = self.parser.parse_args(args)
 
     def run(self):
-        council_module_str = self.parsed_args.module
-        council_module = import_council_module(council_module_str)
-        address_url = self.parsed_args.URL
-        postcode = self.parsed_args.postcode
-        paon = self.parsed_args.number
-        uprn = self.parsed_args.uprn
-        skip_get_url = self.parsed_args.skip_get_url
-        web_driver = self.parsed_args.web_driver
-        headless = self.parsed_args.headless
-        dev_mode = self.parsed_args.dev_mode
-
+        """Run the application with the provided arguments."""
+        council_module = import_council_module(self.parsed_args.module)
         return self.client_code(
             council_module.CouncilClass(),
-            address_url,
-            postcode=postcode,
-            paon=paon,
-            uprn=uprn,
-            skip_get_url=skip_get_url,
-            web_driver=web_driver,
-            headless=headless,
-            dev_mode=dev_mode,
-            council_module_str=council_module_str,
+            self.parsed_args.URL,
+            postcode=self.parsed_args.postcode,
+            paon=self.parsed_args.number,
+            uprn=self.parsed_args.uprn,
+            skip_get_url=self.parsed_args.skip_get_url,
+            web_driver=self.parsed_args.web_driver,
+            headless=self.parsed_args.headless,
+            local_browser=self.parsed_args.local_browser,
+            dev_mode=self.parsed_args.dev_mode,
+            council_module_str=self.parsed_args.module,
         )
 
-    def client_code(self, get_bin_data_class, address_url, **kwargs) -> None:
+    def client_code(self, get_bin_data_class, address_url, **kwargs):
         """
-        The client code calls the template method to execute the algorithm. Client
-        code does not have to know the concrete class of an object it works with,
-        as long as it works with objects through the interface of their base class.
+        Call the template method to execute the algorithm. Client code does not need
+        to know the concrete class of an object it works with, as long as it works with
+        objects through the interface of their base class.
         """
         return get_bin_data_class.template_method(address_url, **kwargs)
 
 
 def run():
+    """Set up logging and run the application."""
     global _LOGGER
     _LOGGER = setup_logging(LOGGING_CONFIG, None)
     app = UKBinCollectionApp()

uk_bin_collection/uk_bin_collection/common.py

@@ -1,18 +1,19 @@
 import calendar
-import holidays
 import json
 import os
-import pandas as pd
 import re
-import requests
 from datetime import datetime, timedelta
-from dateutil.parser import parse
 from enum import Enum
+
+import holidays
+import pandas as pd
+import requests
+from dateutil.parser import parse
 from selenium import webdriver
-from selenium.webdriver.chrome.service import Service as ChromeService
-from webdriver_manager.chrome import ChromeDriverManager
 from selenium.common.exceptions import WebDriverException
+from selenium.webdriver.chrome.service import Service as ChromeService
 from urllib3.exceptions import MaxRetryError
+from webdriver_manager.chrome import ChromeDriverManager
 
 date_format = "%d/%m/%Y"
 days_of_week = {

uk_bin_collection/uk_bin_collection/councils/DorsetCouncil.py

@@ -14,38 +14,22 @@ class CouncilClass(AbstractGetBinDataClass):
     def parse_data(self, page: str, **kwargs) -> dict:
         data = {"bins": []}
         collections = []
-
-        # Parse the page and find all the result boxes
-        soup = BeautifulSoup(page.text, features="html.parser")
-        soup.prettify()
-        results = soup.find_all("li", {"class": "resultListItem"})
-
-        # If the result box has a wanted string in, we can use it. Check the contents of each box and find the
-        # desired text and dates
-        for r in results:
-            if "Your next" in r.text:
-                if type(r.contents[10]) is element.NavigableString:
-                    bin_text = r.contents[10].text.split(" ")[2].title() + " bin"
-                    bin_date = datetime.strptime(
-                        remove_ordinal_indicator_from_date_string(
-                            r.contents[11].text.strip()
-                        ),
-                        "%A %d %B %Y",
-                    )
-                else:
-                    bin_text = r.contents[11].text.split(" ")[2].title() + " bin"
-                    bin_date = datetime.strptime(
-                        remove_ordinal_indicator_from_date_string(
-                            r.contents[12].text.strip()
-                        ),
-                        "%A %d %B %Y",
-                    )
-
-                if bin_date.date() >= datetime.now().date():
-                    collections.append((bin_text, bin_date))
-
-                # Sort the text and date elements by date
-                ordered_data = sorted(collections, key=lambda x: x[1])
+        url_base = "https://geoapi.dorsetcouncil.gov.uk/v1/services/"
+        url_types = ["recyclingday", "refuseday", "foodwasteday", "gardenwasteday"]
+
+        uprn = kwargs.get("uprn")
+        # Check the UPRN is valid
+        check_uprn(uprn)
+
+        for url_type in url_types:
+            response = requests.get(f"{url_base}{url_type}/{uprn}")
+            if response.status_code != 200:
+                raise ConnectionError(f"Could not fetch from {url_type} endpoint")
+            json_data = response.json()["values"][0]
+            collections.append((f"{json_data.get('type')} bin", datetime.strptime(json_data.get('dateNextVisit'), "%Y-%m-%d")))
+
+        # Sort the text and date elements by date
+        ordered_data = sorted(collections, key=lambda x: x[1])
 
         # Put the elements into the dictionary
         for item in ordered_data:

uk_bin_collection/uk_bin_collection/councils/MidSussexDistrictCouncil.py

@@ -1,80 +1,168 @@
-import re
-from datetime import datetime
+import logging
+import time
 
-import requests
 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
+from selenium.webdriver.support.wait import WebDriverWait
+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
 
-
-def get_token(res) -> str:
-    """
-    Get a UFPRT code for the form data to be processed
-        :param res:
-        :return:
-    """
-    soup = BeautifulSoup(res, features="html.parser")
-    soup.prettify()
-    token = soup.find("input", {"name": "ufprt"}).get("value")
-    return token
+# Set up logging
+logging.basicConfig(
+    level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+)
 
 
-# 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.
+    Concrete class for Mid-Sussex District Council implementing AbstractGetBinDataClass.
     """
 
     def parse_data(self, page: str, **kwargs) -> dict:
-        api_url = "https://www.midsussex.gov.uk/waste-recycling/bin-collection/"
-        user_postcode = kwargs.get("postcode")
-        user_paon = kwargs.get("paon")
-        postcode_re = "^([A-Za-z][A-Ha-hJ-Yj-y]?[0-9][A-Za-z0-9]? ?[0-9][A-Za-z]{2}|[Gg][Ii][Rr] ?0[Aa]{2})$"
-        user_full_addr = f"{user_paon} {user_postcode}"
-
-        check_postcode(user_postcode)
-        check_paon(user_paon)
-
-        form_data = {
-            "PostCodeStep.strAddressSearch": user_postcode,
-            "AddressStep.strAddressSelect": user_full_addr,
-            "Next": "true",
-            "StepIndex": "1",
-        }
-
-        # Get a ufprt by posting here (I have no idea how ufprt works, so may as well grab one from the server)
-        requests.packages.urllib3.disable_warnings()
-        init = requests.post(api_url, data=form_data)
-        ufprt = get_token(init.text)
-        form_data.update({"ufprt": ufprt})
-
-        response = requests.post(api_url, data=form_data)
-
-        # Make a BS4 object
-        soup = BeautifulSoup(response.text, features="html.parser")
-        soup.prettify()
-
-        data = {"bins": []}
-
-        table_element = soup.find("table", {"class": "collDates"})
-        table_rows = table_element.find_all_next("tr")
-
-        row_index = 0
-        for row in table_rows:
-            if row_index < 1:
-                row_index += 1
-                continue
+        driver = None
+        try:
+            data = {"bins": []}
+            collections = []
+            user_paon = kwargs.get("paon")
+            user_postcode = kwargs.get("postcode")
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+            check_postcode(user_postcode)
+
+            # Create Selenium webdriver
+            driver = create_webdriver(web_driver, headless, None, __name__)
+
+            driver.get("https://www.midsussex.gov.uk/waste-recycling/bin-collection/")
+            wait = WebDriverWait(driver, 60)
+
+            try:
+                logging.info("Cookies")
+                cookie_window = wait.until(
+                    EC.presence_of_element_located(
+                        (By.XPATH, '//div[@id="ccc-content"]')
+                    )
+                )
+                time.sleep(2)
+                accept_cookies = WebDriverWait(driver, timeout=10).until(
+                    EC.presence_of_element_located(
+                        (By.XPATH, '//button[@id="ccc-recommended-settings"]')
+                    )
+                )
+                accept_cookies.send_keys(Keys.ENTER)
+                accept_cookies.click()
+                accept_cookies_close = WebDriverWait(driver, timeout=10).until(
+                    EC.presence_of_element_located(
+                        (By.XPATH, '//button[@id="ccc-close"]')
+                    )
+                )
+                accept_cookies_close.send_keys(Keys.ENTER)
+                accept_cookies_close.click()
+            except:
+                print(
+                    "Accept cookies banner not found or clickable within the specified time."
+                )
+                pass
+
+            def click_element(by, value):
+                element = wait.until(EC.element_to_be_clickable((by, value)))
+                driver.execute_script("arguments[0].scrollIntoView();", element)
+                element.click()
+
+            logging.info("Entering postcode")
+            input_element_postcode = wait.until(
+                EC.presence_of_element_located(
+                    (By.XPATH, '//input[@id="PostCodeStep_strAddressSearch"]')
+                )
+            )
+
+            input_element_postcode.send_keys(user_postcode)
+
+            logging.info("Entering postcode")
+
+            click_element(By.XPATH, "//button[contains(text(), 'Search')]")
+
+            logging.info("Selecting address")
+            dropdown = wait.until(
+                EC.element_to_be_clickable((By.ID, "StrAddressSelect"))
+            )
+
+            dropdown_options = wait.until(
+                EC.presence_of_element_located(
+                    (By.XPATH, "//select[@id='StrAddressSelect']/option")
+                )
+            )
+            dropdownSelect = Select(dropdown)
+            dropdownSelect.select_by_visible_text(str(user_paon))
+
+            click_element(By.XPATH, "//button[contains(text(), 'Select')]")
+
+            logging.info("Waiting for bin schedule")
+            bin_results = wait.until(
+                EC.presence_of_element_located(
+                    (By.XPATH, f"//strong[contains(text(), '{user_paon}')]")
+                )
+            )
+
+            # Make a BS4 object
+            soup = BeautifulSoup(driver.page_source, features="html.parser")
+
+            # Find the table with bin collection data
+            table = soup.find("table", class_="collDates")
+            if table:
+                rows = table.find_all("tr")[1:]  # Skip the header row
             else:
-                details = row.find_all_next("td")
-                dict_data = {
-                    "type": details[1].get_text().replace("collection", "").strip(),
-                    "collectionDate": datetime.strptime(
-                        details[2].get_text(), "%A %d %B %Y"
-                    ).strftime(date_format),
-                }
-                data["bins"].append(dict_data)
-                row_index += 1
-
-        return data
+                rows = []
+
+            # Extract the data from the table and format it according to the JSON schema
+            bins = []
+            date_pattern = re.compile(r"(\d{2}) (\w+) (\d{4})")
+
+            for row in rows:
+                cols = row.find_all("td")
+                if len(cols) < 3:
+                    print("Skipping row, not enough columns:", row)
+                    continue  # Skip rows that do not have enough columns
+
+                collection_type = cols[1].text.strip()
+                collection_date = cols[2].text.strip()
+
+                # Convert the collection date to the required format
+                date_match = date_pattern.search(collection_date)
+                if date_match:
+                    day, month, year = date_match.groups()
+                    month_number = {
+                        "January": "01",
+                        "February": "02",
+                        "March": "03",
+                        "April": "04",
+                        "May": "05",
+                        "June": "06",
+                        "July": "07",
+                        "August": "08",
+                        "September": "09",
+                        "October": "10",
+                        "November": "11",
+                        "December": "12",
+                    }.get(month, "00")
+
+                    formatted_date = f"{day}/{month_number}/{year}"
+                    bins.append(
+                        {"type": collection_type, "collectionDate": formatted_date}
+                    )
+                else:
+                    print("Date pattern not found in:", collection_date)
+
+            # Create the final JSON structure
+            bin_data = {"bins": bins}
+            return bin_data
+        except Exception as e:
+            logging.error(f"An error occurred: {e}")
+            raise
+
+        finally:
+            if driver:
+                driver.quit()

uk_bin_collection/uk_bin_collection/councils/ThreeRiversDistrictCouncil.py

@@ -30,7 +30,7 @@ class CouncilClass(AbstractGetBinDataClass):
 
             # Create Selenium webdriver
             driver = create_webdriver(web_driver, headless, None, __name__)
-            if headless:
+            if not headless:
                 driver.set_window_size(1920, 1080)
 
             driver.get(

uk_bin_collection/uk_bin_collection/get_bin_data.py

@@ -1,16 +1,15 @@
-"""Module that contains an abstract class that can be imported to
-handle the data recieved from the provided council class.
+"""Get Bin Data
 
-Keyword arguments: None
+Keyword arguments:
+None
 """
 
 import json
-import logging
+import logging, logging.config
 from abc import ABC, abstractmethod
-from logging.config import dictConfig
 import os
-
 import requests
+import urllib3
 
 from uk_bin_collection.uk_bin_collection.common import update_input_json
 
@@ -27,6 +26,12 @@ LOGGING_CONFIG = dict(
 
 
 def setup_logging(logging_config, logger_name):
+    """Set up logging configuration.
+
+    Keyword arguments:
+    logging_config -- the logging configuration dictionary
+    logger_name -- the name of the logger
+    """
     try:
         logging.config.dictConfig(logging_config)
         logger = logging.getLogger(logger_name)
@@ -35,11 +40,8 @@ def setup_logging(logging_config, logger_name):
         raise exp
 
 
-# import the wonderful Beautiful Soup and the URL grabber
-
-
 class AbstractGetBinDataClass(ABC):
-    """An abstract class that can be imported to handle the data recieved from the provided
+    """An abstract class that can be imported to handle the data received from the provided
     council class.
 
     Keyword arguments: None
@@ -52,63 +54,58 @@ class AbstractGetBinDataClass(ABC):
         address_url -- the url to get the data from
         """
         this_url = address_url
-        this_postcode = kwargs.get("postcode", None)
-        this_paon = kwargs.get("paon", None)
-        this_uprn = kwargs.get("uprn", None)
-        this_usrn = kwargs.get("usrn", None)
-        this_web_driver = kwargs.get("web_driver", None)
-        this_headless = kwargs.get("headless", None)
-        skip_get_url = kwargs.get("skip_get_url", None)
-        dev_mode = kwargs.get("dev_mode", False)
-        council_module_str = kwargs.get("council_module_str", None)
-        if (
-            not skip_get_url or skip_get_url is False
-        ):  # we will not use the generic way to get data - needs a get data in the council class itself
-            page = self.get_data(address_url)
-            bin_data_dict = self.parse_data(
-                page,
-                postcode=this_postcode,
-                paon=this_paon,
-                uprn=this_uprn,
-                usrn=this_usrn,
-                web_driver=this_web_driver,
-                headless=this_headless,
-                url=this_url,
-            )
-            json_output = self.output_json(bin_data_dict)
-        else:
-            bin_data_dict = self.parse_data(
-                "",
-                postcode=this_postcode,
-                paon=this_paon,
-                uprn=this_uprn,
-                usrn=this_usrn,
-                web_driver=this_web_driver,
-                headless=this_headless,
-                url=this_url,
-            )
-            json_output = self.output_json(bin_data_dict)
+        this_local_browser = kwargs.get("local_browser", False)
+        if not this_local_browser:
+            kwargs["web_driver"] = kwargs.get("web_driver", None)
+
+        bin_data_dict = self.get_and_parse_data(this_url, **kwargs)
+        json_output = self.output_json(bin_data_dict)
 
         # if dev mode create/update council's entry in the input.json
-        if dev_mode is not None and dev_mode is True:
-            cwd = os.getcwd()
-            input_file_path = os.path.join(
-                cwd, "uk_bin_collection", "tests", "input.json"
-            )
-            update_input_json(
-                council_module_str,
-                this_url,
-                input_file_path,
-                postcode=this_postcode,
-                paon=this_paon,
-                uprn=this_uprn,
-                usrn=this_usrn,
-                web_driver=this_web_driver,
-                skip_get_url=skip_get_url,
+        if kwargs.get("dev_mode"):
+            self.update_dev_mode_data(
+                council_module_str=kwargs.get("council_module_str"),
+                this_url=this_url,
+                **kwargs,
             )
 
         return json_output
 
+    def get_and_parse_data(self, address_url, **kwargs):
+        """Get and parse data from the URL
+
+        Keyword arguments:
+        address_url -- the URL to get the data from
+        """
+        if not kwargs.get("skip_get_url"):
+            page = self.get_data(address_url)
+            bin_data_dict = self.parse_data(page, url=address_url, **kwargs)
+        else:
+            bin_data_dict = self.parse_data("", url=address_url, **kwargs)
+
+        return bin_data_dict
+
+    def update_dev_mode_data(self, council_module_str, this_url, **kwargs):
+        """Update input.json if in development mode
+
+        Keyword arguments:
+        council_module_str -- the council module string
+        this_url -- the URL used
+        """
+        cwd = os.getcwd()
+        input_file_path = os.path.join(cwd, "uk_bin_collection", "tests", "input.json")
+        update_input_json(
+            council_module_str,
+            this_url,
+            input_file_path,
+            postcode=kwargs.get("postcode"),
+            paon=kwargs.get("paon"),
+            uprn=kwargs.get("uprn"),
+            usrn=kwargs.get("usrn"),
+            web_driver=kwargs.get("web_driver"),
+            skip_get_url=kwargs.get("skip_get_url"),
+        )
+
     @classmethod
     def get_data(cls, url) -> str:
         """This method makes the request to the council
@@ -116,29 +113,18 @@ class AbstractGetBinDataClass(ABC):
         Keyword arguments:
         url -- the url to get the data from
         """
-        # Set a user agent so we look like a browser ;-)
         user_agent = (
             "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
             "Chrome/108.0.0.0 Safari/537.36"
         )
         headers = {"User-Agent": user_agent}
-        requests.packages.urllib3.disable_warnings()
+        urllib3.disable_warnings(category=urllib3.exceptions.InsecureRequestWarning)
 
-        # Make the Request - change the URL - find out your property number
         try:
-            full_page = requests.get(url, headers, verify=False)
+            full_page = requests.get(url, headers, verify=False, timeout=120)
             return full_page
-        except requests.exceptions.HTTPError as errh:
-            _LOGGER.error(f"Http Error: {errh}")
-            raise
-        except requests.exceptions.ConnectionError as errc:
-            _LOGGER.error(f"Error Connecting: {errc}")
-            raise
-        except requests.exceptions.Timeout as errt:
-            _LOGGER.error(f"Timeout Error: {errt}")
-            raise
         except requests.exceptions.RequestException as err:
-            _LOGGER.error(f"Oops: Something Else {err}")
+            _LOGGER.error(f"Request Error: {err}")
             raise
 
     @abstractmethod
@@ -154,12 +140,7 @@ class AbstractGetBinDataClass(ABC):
         """Method to output the json as a pretty printed string
 
         Keyword arguments:
-        bin_data_dict -- a dict parsed data
+        bin_data_dict -- a dict of parsed data
         """
-        # Form a JSON wrapper
-        # Make the JSON
-
         json_data = json.dumps(bin_data_dict, sort_keys=False, indent=4)
-
-        # Output the data
         return json_data

{uk_bin_collection-0.81.0.dist-info → uk_bin_collection-0.82.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.81.0
+Version: 0.82.1
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com
@@ -126,6 +126,124 @@ Install can be done via
 ## UPRN Finder
 Some councils make use of the UPRN (Unique property reference number) to identify your property. You can find yours [here](https://www.findmyaddress.co.uk/search) or [here](https://uprn.uk/).
 
+---
+## Selenium
+Some councils need Selenium to run the scrape on behalf of Home Assistant. The easiest way to do this is run Selenium as in a Docker container. However you do this the Home Assistant server must be able to reach the Selenium server
+
+### Instructions for Windows, Linux, and Mac
+
+#### Step 1: Install Docker
+
+##### Windows
+
+1.  **Download Docker Desktop for Windows:**
+    
+    *   Go to the Docker website: Docker Desktop for Windows
+    *   Download and install Docker Desktop.
+2.  **Run Docker Desktop:**
+    
+    *   After installation, run Docker Desktop.
+    *   Follow the on-screen instructions to complete the setup.
+    *   Ensure Docker is running by checking the Docker icon in the system tray.
+
+##### Linux
+
+1.  **Install Docker:**
+    
+    *   Open a terminal and run the following commands:
+                       
+        ```bash
+        sudo apt-get update
+        sudo apt-get install \
+            apt-transport-https \
+            ca-certificates \
+            curl \
+            gnupg \
+            lsb-release
+        curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg
+        echo \
+          "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/ubuntu \
+          $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
+        sudo apt-get update
+        sudo apt-get install docker-ce docker-ce-cli containerd.io 
+        ```
+        
+2.  **Start Docker:**
+    
+    *   Run the following command to start Docker:
+                        
+        ```bash
+        sudo systemctl start docker
+        ```
+        
+3.  **Enable Docker to start on boot:**
+    
+    bash
+    
+    Copy code
+    
+    ```bash
+    sudo systemctl enable docker
+    ```
+    
+
+##### Mac
+
+1.  **Download Docker Desktop for Mac:**
+    
+    *   Go to the Docker website: Docker Desktop for Mac
+    *   Download and install Docker Desktop.
+2.  **Run Docker Desktop:**
+    
+    *   After installation, run Docker Desktop.
+    *   Follow the on-screen instructions to complete the setup.
+    *   Ensure Docker is running by checking the Docker icon in the menu bar.
+
+#### Step 2: Pull and Run Selenium Standalone Chrome Docker Image
+
+1.  **Open a terminal or command prompt:**
+    
+2.  **Pull the Selenium Standalone Chrome image:**
+       
+    ```bash
+    docker pull selenium/standalone-chrome
+    ```
+    
+4.  **Run the Selenium Standalone Chrome container:**
+        
+    ```bash
+    docker run -d -p 4444:4444 --name selenium-chrome selenium/standalone-chrome
+    ```
+    
+
+#### Step 3: Test the Selenium Server
+
+1.  **Navigate to the Selenium server URL in your web browser:**
+    *   Open a web browser and go to `http://localhost:4444`
+    *   You should see the Selenium Grid console.
+
+#### Step 4: Supply the Selenium Server URL to UKBinCollectionData
+
+1.  **Find the `UKBinCollectionData` project:**
+    
+    *   Go to the GitHub repository: [UKBinCollectionData](https://github.com/robbrad/UKBinCollectionData)
+2.  **Supply the Selenium Server URL:**
+    
+    *   Typically, the URL will be `http://localhost:4444/wd/hub`
+    *   You might need to update a configuration file or environment variable in the project to use this URL. Check the project's documentation for specific instructions.
+
+### Summary of Commands
+
+**Windows/Linux/Mac:**
+
+```bash
+docker pull selenium/standalone-chrome docker run -d -p 4444:4444 --name selenium-chrome selenium/standalone-chrome
+```
+
+**Selenium Server URL:**
+
+*   `http://localhost:4444/wd/hub`
+
 ---
 
 ## Requesting your council

{uk_bin_collection-0.81.0.dist-info → uk_bin_collection-0.82.1.dist-info}/RECORD

@@ -2,14 +2,14 @@ uk_bin_collection/README.rst,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,
 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=tsLMMV6SegrudMLCU-F99uuUl3-RGY-dsG39rjeijhA,59231
+uk_bin_collection/tests/input.json,sha256=R_hD1z-Wyc5VMuuQpBay7xLoo-ALHNSZX4OrLxOp_VQ,59163
 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=zDLF5UUBp2n5S3ZlJod7AmYHt92TYQMMhHbX1keNn8U,3424
+uk_bin_collection/tests/step_defs/test_validate_council.py,sha256=LrOSt_loA1Mw3vTqaO2LpaDMu7rYJy6k5Kr-EOBln7s,3424
 uk_bin_collection/tests/test_collect_data.py,sha256=C5w1qfz_1CU37_T7UPdBk3nisMLobIeVHNl6EXrgfrQ,3316
 uk_bin_collection/tests/test_common_functions.py,sha256=IvTNmuFKm9u5j2A9PumMB6eScQS165sPknFakc0l-eg,11190
-uk_bin_collection/uk_bin_collection/collect_data.py,sha256=txdtYoPgWDHLPohGz_Wu9OLXOr8TpXyuIGn0WnsFbZQ,4383
-uk_bin_collection/uk_bin_collection/common.py,sha256=ZvylERlKexeHtqBRb2_fZhYxC8aoEpUtcGo0dzJnWUo,9837
+uk_bin_collection/uk_bin_collection/collect_data.py,sha256=dB7wWXsJX4fm5bIf84lexkvHIcO54CZ3JPxqmS-60YY,4654
+uk_bin_collection/uk_bin_collection/common.py,sha256=1dNfE6hlDhgnLhIdAq426Pji_F3tiO8V7aEAq1bFfpQ,9838
 uk_bin_collection/uk_bin_collection/councils/AdurAndWorthingCouncils.py,sha256=ppbrmm-MzB1wOulK--CU_0j4P-djNf3ozMhHnmQFqLo,1511
 uk_bin_collection/uk_bin_collection/councils/ArunCouncil.py,sha256=yfhthv9nuogP19VOZ3TYQrq51qqjiCZcSel4sXhiKjs,4012
 uk_bin_collection/uk_bin_collection/councils/AylesburyValeCouncil.py,sha256=LouqjspEMt1TkOGqWHs2zkxwOETIy3n7p64uKIlAgUg,2401
@@ -48,7 +48,7 @@ uk_bin_collection/uk_bin_collection/councils/CroydonCouncil.py,sha256=QJH27plySb
 uk_bin_collection/uk_bin_collection/councils/DartfordBoroughCouncil.py,sha256=SPirUUoweMwX5Txtsr0ocdcFtKxCQ9LhzTTJN20tM4w,1550
 uk_bin_collection/uk_bin_collection/councils/DerbyshireDalesDistrictCouncil.py,sha256=MQC1-jXezXczrxTcvPQvkpGgyyAbzSKlX38WsmftHak,4007
 uk_bin_collection/uk_bin_collection/councils/DoncasterCouncil.py,sha256=b7pxoToXu6dBBYXsXmlwfPXE8BjHxt0hjCOBNlNgvX8,3118
-uk_bin_collection/uk_bin_collection/councils/DorsetCouncil.py,sha256=sdSR5ryOSWHtK_0OKJ75LGOvMiUAnQCc3uwT3xfqZ_0,2304
+uk_bin_collection/uk_bin_collection/councils/DorsetCouncil.py,sha256=zfXQJpywfEQvBOhv5uPSkHdTrAg114yXIuTYDjHSXsA,1629
 uk_bin_collection/uk_bin_collection/councils/DoverDistrictCouncil.py,sha256=3Zgap6kaVpDXtRfBKEL1Ms6eb0iFIipYKNtOq3Hrdd4,1891
 uk_bin_collection/uk_bin_collection/councils/DurhamCouncil.py,sha256=6O8bNsQVYQbrCYQE9Rp0c_rtkcXuxR3s9J6jn4MK4_s,1695
 uk_bin_collection/uk_bin_collection/councils/EastCambridgeshireCouncil.py,sha256=aYUVE5QqTxdj8FHhCB4EiFVDJahWJD9Pq0d1upBEvXg,1501
@@ -89,7 +89,7 @@ uk_bin_collection/uk_bin_collection/councils/ManchesterCityCouncil.py,sha256=RFX
 uk_bin_collection/uk_bin_collection/councils/MansfieldDistrictCouncil.py,sha256=F5AiTxImrnjE1k3ry96bfstOf5XSNBJS_4qqmymmh3w,1386
 uk_bin_collection/uk_bin_collection/councils/MertonCouncil.py,sha256=3Y2Un4xXo1sCcMsudynODSzocV_mMofWkX2JqONDb5o,1997
 uk_bin_collection/uk_bin_collection/councils/MidAndEastAntrimBoroughCouncil.py,sha256=oOWwU5FSgGej2Mv7FQ66N-EzS5nZgmGsd0WnfLWUc1I,5238
-uk_bin_collection/uk_bin_collection/councils/MidSussexDistrictCouncil.py,sha256=TUKo2GIY-S2m_RDOQoWdLeBWqTbAjW8tovx1luTtJfE,2705
+uk_bin_collection/uk_bin_collection/councils/MidSussexDistrictCouncil.py,sha256=AZgC9wmDLEjUOtIFvf0ehF5LHturXTH4DkE3ioPSVBA,6254
 uk_bin_collection/uk_bin_collection/councils/MiltonKeynesCityCouncil.py,sha256=3olsWa77L34vz-c7NgeGK9xmNuR4Ws_oAk5D4UpIkPw,2005
 uk_bin_collection/uk_bin_collection/councils/MoleValleyDistrictCouncil.py,sha256=54-autRRGAM4pBxlqmUE6g825rmUF-gRqrcgHL_lkIk,3994
 uk_bin_collection/uk_bin_collection/councils/NeathPortTalbotCouncil.py,sha256=2DJ0gK385CWTdJzWyDdmNBTTrwX6F5YbIXg7di2oXDQ,5506
@@ -153,7 +153,7 @@ uk_bin_collection/uk_bin_collection/councils/TandridgeDistrictCouncil.py,sha256=
 uk_bin_collection/uk_bin_collection/councils/TelfordAndWrekinCouncil.py,sha256=p1ZS5R4EGxbEWlRBrkGXgKwE_lkyBT-R60yKFFhVObc,1844
 uk_bin_collection/uk_bin_collection/councils/TendringDistrictCouncil.py,sha256=DJbYI8m6lIISDrK5h8V5Jo-9kGG7kr9dz7GD8St4nc8,4274
 uk_bin_collection/uk_bin_collection/councils/TestValleyBoroughCouncil.py,sha256=Dtfkyrwt795W7gqFJxVGRR8t3R5WMNQZwTWJckLpZWE,8480
-uk_bin_collection/uk_bin_collection/councils/ThreeRiversDistrictCouncil.py,sha256=oZSW0Y5QHdqVy2fLys4sdB13tHgeNLha9WCUqG_R-gU,5527
+uk_bin_collection/uk_bin_collection/councils/ThreeRiversDistrictCouncil.py,sha256=RHt3e9oeKzwxjjY-M8aC0nk-ZXhHIoyC81JzxkPVxsE,5531
 uk_bin_collection/uk_bin_collection/councils/TonbridgeAndMallingBC.py,sha256=UlgnHDoi8ecav2H5-HqKNDpqW1J3RN-c___5c08_Q7I,4859
 uk_bin_collection/uk_bin_collection/councils/TorbayCouncil.py,sha256=JW_BS7wkfxFsmx6taQtPAQWdBp1AfLrxs0XRQ2XZcSw,2029
 uk_bin_collection/uk_bin_collection/councils/TorridgeDistrictCouncil.py,sha256=6gOO02pYU0cbj3LAHiBVNG4zkFMyIGbkE2jAye3KcGM,6386
@@ -180,9 +180,9 @@ uk_bin_collection/uk_bin_collection/councils/WyreCouncil.py,sha256=zDDa7n4K_zm5P
 uk_bin_collection/uk_bin_collection/councils/YorkCouncil.py,sha256=I2kBYMlsD4bIdsvmoSzBjJAvTTi6yPfJa8xjJx1ys2w,1490
 uk_bin_collection/uk_bin_collection/councils/council_class_template/councilclasstemplate.py,sha256=4s9ODGPAwPqwXc8SrTX5Wlfmizs3_58iXUtHc4Ir86o,1162
 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=9qppF2oPkhmOoK8-ZkRIU1M6vhBh-yUCWAZEEd07iLk,5414
-uk_bin_collection-0.81.0.dist-info/LICENSE,sha256=vABBUOzcrgfaTKpzeo-si9YVEun6juDkndqA8RKdKGs,1071
-uk_bin_collection-0.81.0.dist-info/METADATA,sha256=FY2xzwnZMQ0FiEomvCzrJHbqIVc1RuPvo9dPwPxexR4,12594
-uk_bin_collection-0.81.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-uk_bin_collection-0.81.0.dist-info/entry_points.txt,sha256=36WCSGMWSc916S3Hi1ZkazzDKHaJ6CD-4fCEFm5MIao,90
-uk_bin_collection-0.81.0.dist-info/RECORD,,
+uk_bin_collection/uk_bin_collection/get_bin_data.py,sha256=YvmHfZqanwrJ8ToGch34x-L-7yPe31nB_x77_Mgl_vo,4545
+uk_bin_collection-0.82.1.dist-info/LICENSE,sha256=vABBUOzcrgfaTKpzeo-si9YVEun6juDkndqA8RKdKGs,1071
+uk_bin_collection-0.82.1.dist-info/METADATA,sha256=eF66OGftcUZmlsUAk4B5mGDaJrfHErD-tINXzxW6Ta8,16231
+uk_bin_collection-0.82.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+uk_bin_collection-0.82.1.dist-info/entry_points.txt,sha256=36WCSGMWSc916S3Hi1ZkazzDKHaJ6CD-4fCEFm5MIao,90
+uk_bin_collection-0.82.1.dist-info/RECORD,,