uk_bin_collection 0.79.1__py3-none-any.whl → 0.81.0__py3-none-any.whl

uk_bin_collection/tests/input.json

@@ -263,9 +263,9 @@
         "wiki_name": "Croydon Council"
     },
     "DartfordBoroughCouncil": {
+        "uprn": "010094157511",
         "url": "https://windmz.dartford.gov.uk/ufs/WS_CHECK_COLLECTIONS.eb?UPRN=010094157511",
         "wiki_name": "DartfordBoroughCouncil",
-        "uprn": "010094157511",
         "wiki_note": "Use https://uprn.uk/ to find your UPRN "
     },
     "DerbyshireDalesDistrictCouncil": {
@@ -602,6 +602,14 @@
         "web_driver": "http://selenium:4444",
         "wiki_name": "Neath Port Talbot Council"
     },
+    "NewForestCouncil": {
+        "postcode": "SO41 0GJ",
+        "skip_get_url": true,
+        "uprn": "100060482345",
+        "url": "https://forms.newforest.gov.uk/id/FIND_MY_COLLECTION",
+        "web_driver": "http://selenium:4444",
+        "wiki_name": "New Forest Council"
+    },
     "NewarkAndSherwoodDC": {
         "url": "http://app.newark-sherwooddc.gov.uk/bincollection/calendar?pid=200004258529",
         "wiki_command_url_override": "http://app.newark-sherwooddc.gov.uk/bincollection/calendar?pid=XXXXXXXX",
@@ -909,6 +917,12 @@
         "url": "https://www.sthelens.gov.uk/",
         "wiki_name": "St Helens Borough Council"
     },
+    "StaffordBoroughCouncil": {
+        "uprn": "100032203010",
+        "url": "https://www.staffordbc.gov.uk/address/100032203010",
+        "wiki_name": "StaffordBoroughCouncil",
+        "wiki_note": "The URL needs to be https://www.staffordbc.gov.uk/address/<Your_UPRN>"
+    },
     "StaffordshireMoorlandsDistrictCouncil": {
         "postcode": "ST8 6HN",
         "skip_get_url": true,
@@ -959,6 +973,13 @@
         "url": "https://swale.gov.uk/bins-littering-and-the-environment/bins/collection-days",
         "wiki_name": "Swale Borough Council"
     },
+    "SwanseaCouncil": {
+        "postcode": "SA43PQ",
+        "skip_get_url": true,
+        "uprn": "100100324821",
+        "url": "https://www1.swansea.gov.uk/recyclingsearch/",
+        "wiki_name": "SwanseaCouncil"
+    },
     "TamesideMBCouncil": {
         "skip_get_url": true,
         "uprn": "100012835362",
@@ -992,6 +1013,14 @@
         "url": "https://testvalley.gov.uk/wasteandrecycling/when-are-my-bins-collected",
         "wiki_name": "Test Valley Borough Council"
     },
+    "ThreeRiversDistrictCouncil": {
+        "postcode": "WD3 7AZ",
+        "skip_get_url": true,
+        "uprn": "100080913662",
+        "url": "https://my.threerivers.gov.uk/en/AchieveForms/?mode=fill&consentMessage=yes&form_uri=sandbox-publish://AF-Process-52df96e3-992a-4b39-bba3-06cfaabcb42b/AF-Stage-01ee28aa-1584-442c-8d1f-119b6e27114a/definition.json&process=1&process_uri=sandbox-processes://AF-Process-52df96e3-992a-4b39-bba3-06cfaabcb42b&process_id=AF-Process-52df96e3-992a-4b39-bba3-06cfaabcb42b&noLoginPrompt=1",
+        "web_driver": "http://selenium:4444",
+        "wiki_name": "Three Rivers District Council"
+    },
     "TonbridgeAndMallingBC": {
         "postcode": "ME19 4JS",
         "skip_get_url": true,
@@ -1011,6 +1040,15 @@
         "url": "https://collections-torridge.azurewebsites.net/WebService2.asmx",
         "wiki_name": "Torridge District Council"
     },
+    "UttlesfordDistrictCouncil": {
+        "house_number": "72, Birchanger Lane",
+        "postcode": "CM23 5QF",
+        "skip_get_url": true,
+        "uprn": "100090643434",
+        "url": "https://bins.uttlesford.gov.uk/",
+        "web_driver": "http://selenium:4444",
+        "wiki_name": "UttlesfordDistrictCouncil"
+    },
     "ValeofGlamorganCouncil": {
         "skip_get_url": true,
         "uprn": "64029020",
@@ -1137,6 +1175,14 @@
         "wiki_name": "Woking Borough Council/Joint Waste Solutions",
         "wiki_note": "Works with all collection areas that use Joint Waste Solutions. Just use the correct URL."
     },
+    "WychavonDistrictCouncil": {
+        "url": "https://selfservice.wychavon.gov.uk/wdcroundlookup/wdc_search.jsp",
+        "wiki_name": "WychavonDistrictCouncil",
+        "web_driver": "http://selenium:4444",
+        "skip_get_url": true,
+        "postcode": "WR3 7RU", 
+        "uprn": "100120716273"
+    },
     "WyreCouncil": {
         "postcode": "FY6 8HG",
         "skip_get_url": true,

uk_bin_collection/uk_bin_collection/common.py

@@ -5,7 +5,7 @@ import os
 import pandas as pd
 import re
 import requests
-from datetime import datetime
+from datetime import datetime, timedelta
 from dateutil.parser import parse
 from enum import Enum
 from selenium import webdriver
@@ -242,6 +242,28 @@ def save_data(file_path, data):
         json.dump(data, file, sort_keys=True, indent=4)
 
 
+def get_next_day_of_week(day_name):
+    days_of_week = [
+        "Monday",
+        "Tuesday",
+        "Wednesday",
+        "Thursday",
+        "Friday",
+        "Saturday",
+        "Sunday",
+    ]
+    today = datetime.now()
+    today_idx = today.weekday()  # Monday is 0 and Sunday is 6
+    target_idx = days_of_week.index(day_name)
+
+    days_until_target = (target_idx - today_idx) % 7
+    if days_until_target == 0:
+        days_until_target = 7  # Ensure it's the next instance of the day, not today if today is that day
+
+    next_day = today + timedelta(days=days_until_target)
+    return next_day.strftime(date_format)
+
+
 def contains_date(string, fuzzy=False) -> bool:
     """
     Return whether the string can be interpreted as a date.

uk_bin_collection/uk_bin_collection/councils/BedfordshireCouncil.py

@@ -2,6 +2,7 @@ from datetime import datetime
 
 import requests
 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
 
@@ -22,7 +23,7 @@ class CouncilClass(AbstractGetBinDataClass):
 
         # Start a new session to walk through the form
         requests.packages.urllib3.disable_warnings()
-        s = requests.session()
+        s = requests.Session()
 
         headers = {
             "Origin": "https://www.centralbedfordshire.gov.uk",

uk_bin_collection/uk_bin_collection/councils/BirminghamCityCouncil.py

@@ -1,6 +1,14 @@
-from dateutil.relativedelta import relativedelta
+from typing import Dict, List, Any, Optional
 from bs4 import BeautifulSoup
-from uk_bin_collection.uk_bin_collection.common import *
+from dateutil.relativedelta import relativedelta
+import requests
+import logging
+import re
+from datetime import datetime
+from uk_bin_collection.common import *
+from dateutil.parser import parse
+
+from uk_bin_collection.uk_bin_collection.common import check_uprn, check_postcode
 from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
 
 
@@ -23,7 +31,7 @@ class CouncilClass(AbstractGetBinDataClass):
     implementation.
     """
 
-    def get_data(self, url) -> str:
+    def get_data(self, url: str) -> str:
         """This method makes the request to the council
 
         Keyword arguments:
@@ -44,21 +52,27 @@ class CouncilClass(AbstractGetBinDataClass):
             full_page = session.get(url)
             return full_page
         except requests.exceptions.HTTPError as errh:
-            _LOGGER.error(f"Http Error: {errh}")
+            logging.error(f"Http Error: {errh}")
             raise
         except requests.exceptions.ConnectionError as errc:
-            _LOGGER.error(f"Error Connecting: {errc}")
+            logging.error(f"Error Connecting: {errc}")
             raise
         except requests.exceptions.Timeout as errt:
-            _LOGGER.error(f"Timeout Error: {errt}")
+            logging.error(f"Timeout Error: {errt}")
             raise
         except requests.exceptions.RequestException as err:
-            _LOGGER.error(f"Oops: Something Else {err}")
+            logging.error(f"Oops: Something Else {err}")
             raise
 
-    def parse_data(self, page: str, **kwargs) -> dict:
-        uprn = kwargs.get("uprn")
-        postcode = kwargs.get("postcode")
+    def parse_data(self, page: str, **kwargs: Any) -> Dict[str, List[Dict[str, str]]]:
+        uprn: Optional[str] = kwargs.get("uprn")
+        postcode: Optional[str] = kwargs.get("postcode")
+
+        if uprn is None:
+            raise ValueError("UPRN is required and must be a non-empty string.")
+        if postcode is None:
+            raise ValueError("Postcode is required and must be a non-empty string.")
+
         check_uprn(uprn)
         check_postcode(postcode)
 
@@ -84,7 +98,7 @@ class CouncilClass(AbstractGetBinDataClass):
         rows = soup.find("table").find_all("tr")
 
         # Form a JSON wrapper
-        data = {"bins": []}
+        data: Dict[str, List[Dict[str, str]]] = {"bins": []}
 
         # Loops the Rows
         for row in rows:
@@ -93,13 +107,13 @@ class CouncilClass(AbstractGetBinDataClass):
                 bin_type = cells[0].get_text(strip=True)
                 collection_next = cells[1].get_text(strip=True)
 
-                collection_date = re.findall("\(.*?\)", collection_next)
+                collection_date = re.findall(r"\(.*?\)", collection_next)
 
                 if len(collection_date) != 1:
                     continue
 
                 collection_date_obj = parse(
-                    re.sub("[()]", "", collection_date[0])
+                    re.sub(r"[()]", "", collection_date[0])
                 ).date()
 
                 # since we only have the next collection day, if the parsed date is in the past,

uk_bin_collection/uk_bin_collection/councils/BracknellForestCouncil.py

@@ -64,7 +64,7 @@ def get_csrf_token(s: requests.session, base_url: str) -> str:
     """
     Gets a CSRF token
         :rtype: str
-        :param s: requests.session() to use
+        :param s: requests.Session() to use
         :param base_url: Base URL to use
         :return: CSRF token
     """
@@ -95,7 +95,7 @@ def get_address_id(
     """
     Gets the address ID
         :rtype: str
-        :param s: requests.session() to use
+        :param s: requests.Session() to use
         :param base_url: Base URL to use
         :param csrf_token: CSRF token to use
         :param postcode: Postcode to use
@@ -156,7 +156,7 @@ def get_collection_data(
     """
     Gets the collection data
         :rtype: str
-        :param s: requests.session() to use
+        :param s: requests.Session() to use
         :param base_url: Base URL to use
         :param csrf_token: CSRF token to use
         :param address_id: Address id to use
@@ -203,7 +203,7 @@ class CouncilClass(AbstractGetBinDataClass):
 
     def parse_data(self, page: str, **kwargs) -> dict:
         requests.packages.urllib3.disable_warnings()
-        s = requests.session()
+        s = requests.Session()
         base_url = "https://selfservice.mybfc.bracknell-forest.gov.uk"
         paon = kwargs.get("paon")
         postcode = kwargs.get("postcode")

uk_bin_collection/uk_bin_collection/councils/BristolCityCouncil.py

@@ -2,6 +2,7 @@ import ast
 
 import requests
 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
 
@@ -19,7 +20,7 @@ class CouncilClass(AbstractGetBinDataClass):
         check_uprn(user_uprn)
 
         requests.packages.urllib3.disable_warnings()
-        s = requests.session()
+        s = requests.Session()
 
         service_type_headers = {
             "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,"

uk_bin_collection/uk_bin_collection/councils/BromleyBoroughCouncil.py

@@ -1,17 +1,14 @@
 # This script pulls (in one hit) the data from Bromley Council Bins Data
 import datetime
-import time
 from datetime import datetime
 
 from bs4 import BeautifulSoup
 from dateutil.relativedelta import relativedelta
 from selenium.webdriver.common.by import By
-from selenium.webdriver.common.keys import Keys
 from selenium.webdriver.support import expected_conditions as EC
-from selenium.webdriver.support.ui import Select
-from selenium.webdriver.support.wait import WebDriverWait
+from selenium.webdriver.support.ui import WebDriverWait
 
-from uk_bin_collection.uk_bin_collection.common import *
+from uk_bin_collection.uk_bin_collection.common import create_webdriver
 from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
 
 
@@ -28,7 +25,6 @@ class CouncilClass(AbstractGetBinDataClass):
         driver = None
         try:
             bin_data_dict = {"bins": []}
-            collections = []
             web_driver = kwargs.get("web_driver")
             headless = kwargs.get("headless")
 
@@ -39,18 +35,14 @@ class CouncilClass(AbstractGetBinDataClass):
             driver.get(kwargs.get("url"))
 
             wait = WebDriverWait(driver, 30)
-            results = wait.until(
+            wait.until(
                 EC.presence_of_element_located((By.CLASS_NAME, "waste-service-image"))
             )
-            # Search for the specific bins in the table using BS
-            # Parse the HTML content
-            # Find all elements with the class 'container-name' to extract bin types
+
             # Parse the HTML content
             soup = BeautifulSoup(driver.page_source, "html.parser")
-            soup.prettify
 
             # Find all elements with class 'govuk-summary-list'
-            bin_info = []
             waste_services = soup.find_all(
                 "h3", class_="govuk-heading-m waste-service-name"
             )
@@ -58,7 +50,7 @@ class CouncilClass(AbstractGetBinDataClass):
             for service in waste_services:
                 service_title = service.get_text(strip=True)
                 next_collection = service.find_next_sibling().find(
-                    "dt", text="Next collection"
+                    "dt", string="Next collection"
                 )
 
                 if next_collection:
@@ -69,8 +61,7 @@ class CouncilClass(AbstractGetBinDataClass):
                     next_collection_date_parse = next_collection_date.split(",")[
                         1
                     ].strip()
-                    day = next_collection_date_parse.split()[0]
-                    month = next_collection_date_parse.split()[1]
+                    day, month = next_collection_date_parse.split()[:2]
 
                     # Remove the suffix (e.g., 'th', 'nd', 'rd', 'st') from the day
                     if day.endswith(("th", "nd", "rd", "st")):

uk_bin_collection/uk_bin_collection/councils/BuckinghamshireCouncil.py

@@ -1,11 +1,11 @@
 import time
-
 import pandas as pd
 from selenium.webdriver.common.by import By
 from selenium.webdriver.common.keys import Keys
 from selenium.webdriver.support.ui import Select
+from io import StringIO
 
-from uk_bin_collection.uk_bin_collection.common import *
+from uk_bin_collection.uk_bin_collection.common import create_webdriver
 from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
 
 
@@ -16,7 +16,7 @@ class CouncilClass(AbstractGetBinDataClass):
     implementation.
     """
 
-    def get_data(self, df) -> dict:
+    def get_data(self, df: pd.DataFrame) -> dict:
         # Create dictionary of data to be returned
         data = {"bins": []}
 
@@ -69,7 +69,7 @@ class CouncilClass(AbstractGetBinDataClass):
             time.sleep(4)
 
             # Submit address information and wait
-            inputElement_bn = driver.find_element(
+            driver.find_element(
                 By.ID, "COPYOFECHOCOLLECTIONDATES_ADDRESSSELECTION_NAV1_NEXT"
             ).click()
 
@@ -79,8 +79,10 @@ class CouncilClass(AbstractGetBinDataClass):
             table = driver.find_element(
                 By.ID, "COPYOFECHOCOLLECTIONDATES_PAGE1_DATES2"
             ).get_attribute("outerHTML")
-            df = pd.read_html(table, header=[1])
-            df = df[0]
+
+            # Wrap the HTML table in a StringIO object to address the warning
+            table_io = StringIO(table)
+            df = pd.read_html(table_io, header=[1])[0]
 
             # Parse data into dict
             data = self.get_data(df)

uk_bin_collection/uk_bin_collection/councils/CroydonCouncil.py

@@ -1,6 +1,7 @@
 import time
 
 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
 
@@ -75,7 +76,7 @@ def get_csrf_token(s: requests.session, base_url: str) -> str:
     """
     Gets a CSRF token
         :rtype: str
-        :param s: requests.session() to use
+        :param s: requests.Session() to use
         :param base_url: Base URL to use
         :return: CSRF token
     """
@@ -106,7 +107,7 @@ def get_address_id(
     """
     Gets the address ID
         :rtype: str
-        :param s: requests.session() to use
+        :param s: requests.Session() to use
         :param base_url: Base URL to use
         :param csrf_token: CSRF token to use
         :param postcode: Postcode to use
@@ -171,7 +172,7 @@ def get_collection_data(
     """
     Gets the collection data
         :rtype: str
-        :param s: requests.session() to use
+        :param s: requests.Session() to use
         :param base_url: Base URL to use
         :param csrf_token: CSRF token to use
         :param address_id: Address id to use
@@ -240,7 +241,7 @@ class CouncilClass(AbstractGetBinDataClass):
 
     def parse_data(self, page: str, **kwargs) -> dict:
         requests.packages.urllib3.disable_warnings()
-        s = requests.session()
+        s = requests.Session()
         base_url = "https://service.croydon.gov.uk"
         paon = kwargs.get("paon")
         postcode = kwargs.get("postcode")

uk_bin_collection/uk_bin_collection/councils/DartfordBoroughCouncil.py

@@ -17,27 +17,25 @@ class CouncilClass(AbstractGetBinDataClass):
         soup.prettify()
 
         # Extract data
-        bin_data = {
-            "bins": []
-        }
+        bin_data = {"bins": []}
 
         # Find the table containing the bin collection data
-        table = soup.find('table', {'class': 'eb-EVDNdR1G-tableContent'})
+        table = soup.find("table", {"class": "eb-EVDNdR1G-tableContent"})
 
         if table:
-            rows = table.find_all('tr', class_='eb-EVDNdR1G-tableRow')
-            
+            rows = table.find_all("tr", class_="eb-EVDNdR1G-tableRow")
+
             for row in rows:
-                columns = row.find_all('td')
+                columns = row.find_all("td")
                 if len(columns) >= 4:
                     collection_type = columns[1].get_text(strip=True)
                     collection_date = columns[3].get_text(strip=True)
-                    
+
                     # Validate collection_date format
                     if re.match(r"\d{2}/\d{2}/\d{4}", collection_date):
                         bin_entry = {
                             "type": collection_type,
-                            "collectionDate": collection_date
+                            "collectionDate": collection_date,
                         }
                         bin_data["bins"].append(bin_entry)
 

uk_bin_collection/uk_bin_collection/councils/EastCambridgeshireCouncil.py

@@ -1,4 +1,5 @@
 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
 
@@ -21,7 +22,7 @@ class CouncilClass(AbstractGetBinDataClass):
 
         # Make Request
         requests.packages.urllib3.disable_warnings()
-        s = requests.session()
+        s = requests.Session()
         page = s.get(url)
 
         # Make a BS4 object

uk_bin_collection/uk_bin_collection/councils/HaringeyCouncil.py

@@ -1,6 +1,10 @@
 from bs4 import BeautifulSoup
+import requests
+import logging
+import re
+from typing import Dict, List, Any, Optional
 
-from uk_bin_collection.uk_bin_collection.common import *
+from uk_bin_collection.uk_bin_collection.common import check_uprn
 from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
 
 
@@ -11,10 +15,14 @@ class CouncilClass(AbstractGetBinDataClass):
     implementation.
     """
 
-    def parse_data(self, page: str, **kwargs) -> dict:
-        data = {"bins": []}
+    def parse_data(self, page: str, **kwargs: Any) -> Dict[str, List[Dict[str, str]]]:
+        data: Dict[str, List[Dict[str, str]]] = {"bins": []}
+
+        uprn: Optional[str] = kwargs.get("uprn")
+
+        if uprn is None:
+            raise ValueError("UPRN is required and must be a non-empty string.")
 
-        uprn = kwargs.get("uprn")
         check_uprn(uprn)  # Assuming check_uprn() raises an exception if UPRN is invalid
 
         try:
@@ -42,7 +50,7 @@ class CouncilClass(AbstractGetBinDataClass):
 
                 if service_name_element and next_service_element:
                     service = service_name_element.text
-                    next_collection = next_service_element.find(text=date_regex)
+                    next_collection = next_service_element.find(string=date_regex)
 
                     if next_collection:
                         dict_data = {

uk_bin_collection/uk_bin_collection/councils/LancasterCityCouncil.py

@@ -1,8 +1,10 @@
-from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
-from uk_bin_collection.uk_bin_collection.common import *
-from bs4 import BeautifulSoup
 from datetime import datetime
+
 import requests
+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
 
 
 class CouncilClass(AbstractGetBinDataClass):
@@ -19,7 +21,7 @@ class CouncilClass(AbstractGetBinDataClass):
         # start session
         # note: this ignores the given url
         base_url = "https://lcc-wrp.whitespacews.com"
-        session = requests.session()
+        session = requests.Session()
         response = session.get(base_url + "/#!")
         links = [
             a["href"]

uk_bin_collection/uk_bin_collection/councils/LisburnCastlereaghCityCouncil.py

@@ -3,6 +3,7 @@ from datetime import date, datetime
 
 import requests
 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
 

uk_bin_collection/uk_bin_collection/councils/ManchesterCityCouncil.py

@@ -2,6 +2,7 @@ from datetime import datetime
 
 import requests
 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
 
@@ -20,7 +21,7 @@ class CouncilClass(AbstractGetBinDataClass):
 
         # Start a new session to walk through the form
         requests.packages.urllib3.disable_warnings()
-        s = requests.session()
+        s = requests.Session()
 
         # There's a cookie that makes the whole thing valid when you search for a postcode,
         # but postcode and UPRN is a hassle imo, so this makes a request for the session to get a cookie