uk_bin_collection 0.115.0__tar.gz → 0.116.0__tar.gz

{uk_bin_collection-0.115.0 → uk_bin_collection-0.116.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.115.0
+Version: 0.116.0
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.115.0 → uk_bin_collection-0.116.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.115.0"
+version = "0.116.0"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.115.0 → uk_bin_collection-0.116.0}/uk_bin_collection/tests/input.json

@@ -32,6 +32,13 @@
         "wiki_name": "Ards and North Down Council",
         "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN."
     },
+    "ArgyllandButeCouncil": {
+        "uprn": "125061759",
+        "skip_get_url": true,
+        "url": "https://www.argyll-bute.gov.uk",
+        "wiki_name": "Argyll and Bute Council",
+        "wiki_note": "Pass the UPRN. You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search)."
+    },
     "ArmaghBanbridgeCraigavonCouncil": {
         "url": "https://www.armaghbanbridgecraigavon.gov.uk/",
         "wiki_command_url_override": "https://www.armaghbanbridgecraigavon.gov.uk/",
@@ -48,13 +55,13 @@
         "wiki_name": "Arun Council",
         "wiki_note": "Pass the house name/number and postcode in their respective parameters, both wrapped in double quotes. This parser requires a Selenium webdriver."
     },
-    "AshfordBoroughCouncil": {
-        "url": "https://ashford.gov.uk",
-        "wiki_command_url_override": "https://ashford.gov.uk",
-        "postcode": "TN23 7SP",
-        "uprn": "100060777899",
-        "wiki_name": "Ashford Borough Council",
-        "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN."
+    "AshfieldDistrictCouncil": {
+        "url": "https://www.ashfield.gov.uk",
+        "postcode": "NG16 6RH",
+        "house_number": "1",
+        "web_driver": "http://selenium:4444",
+        "wiki_name": "Ashfield District Council",
+        "wiki_note": "Pass the house name/number and postcode in their respective parameters, both wrapped in double quotes. This parser requires a Selenium webdriver"
     },
     "AshfordBoroughCouncil": {
         "url": "https://ashford.gov.uk",
@@ -71,6 +78,13 @@
         "wiki_name": "Aylesbury Vale Council (Buckinghamshire)",
         "wiki_note": "To get the UPRN, please use [FindMyAddress](https://www.findmyaddress.co.uk/search). Returns all published collections in the past, present, future."
     },
+    "BaberghDistrictCouncil": {
+        "skip_get_url": true,
+        "house_number": "Monday",
+        "url": "https://www.babergh.gov.uk",
+        "wiki_name": "Babergh District Council",
+        "wiki_note": "Use the House Number field to pass the DAY of the week for your collections. Monday/Tuesday/Wednesday/Thursday/Friday"
+    },
     "BCPCouncil": {
         "skip_get_url": true,
         "uprn": "100040810214",
@@ -335,26 +349,19 @@
         "wiki_note": "Both the UPRN and a one-line address are passed in the URL, which needs to be wrapped in double quotes. The one-line address is made up of the house number, street name, and postcode. Use the form [here](https://online.cheshireeast.gov.uk/mycollectionday/) to find them, then take the first line and postcode and replace all spaces with `%20`."
     },
     "CheshireWestAndChesterCouncil": {
-        "house_number": "Hill View House",
-        "postcode": "CH3 9ER",
+        "uprn": "100012346655",
         "skip_get_url": true,
-        "url": "https://www.cheshirewestandchester.gov.uk/residents/waste-and-recycling/your-bin-collection/collection-day",
+        "url": "https://my.cheshirewestandchester.gov.uk",
         "wiki_name": "Cheshire West and Chester Council",
-        "wiki_note": "Pass the house name/number and postcode in their respective parameters."
+        "wiki_note": "Pass the UPRN. You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search)."
     },
     "ChesterfieldBoroughCouncil": {
         "uprn": "74008234",
         "skip_get_url": true,
-        "url": "https://www.cheshirewestandchester.gov.uk/residents/waste-and-recycling/your-bin-collection/collection-day",
+        "url": "https://www.chesterfield.gov.uk",
         "wiki_name": "Chesterfield Borough Council",
         "wiki_note": "Pass the UPRN. You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search)."
     },
-    "ChesterfieldBoroughCouncil": {
-        "uprn": "74008234",
-        "skip_get_url": true,
-        "url": "https://www.cheshirewestandchester.gov.uk/residents/waste-and-recycling/your-bin-collection/collection-day",
-        "wiki_name": "Chesterfield Borough Council"
-    },
     "ChichesterDistrictCouncil": {
         "house_number": "7, Plaistow Road, Kirdford, Billingshurst, West Sussex",
         "postcode": "RH14 0JT",
@@ -449,6 +456,12 @@
         "wiki_name": "Dartford Borough Council",
         "wiki_note": "Use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find your UPRN."
     },
+    "DerbyCityCouncil": {
+        "url": "https://www.derby.gov.uk",
+        "uprn": "10010684240",
+        "wiki_name": "Derby City Council",
+        "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN."
+    },
     "DerbyshireDalesDistrictCouncil": {
         "postcode": "DE4 3AS",
         "skip_get_url": true,
@@ -702,6 +715,13 @@
         "wiki_name": "Gloucester City Council",
         "wiki_note": "Pass the house number, postcode, and UPRN in their respective parameters. This parser requires a Selenium webdriver."
     },
+    "GraveshamBoroughCouncil": {
+        "uprn": "100060927046",
+        "skip_get_url": true,
+        "url": "https://www.gravesham.gov.uk",
+        "wiki_name": "Gravesham Borough Council",
+        "wiki_note": "Pass the UPRN. You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search)."
+    },
     "GuildfordCouncil": {
         "house_number": "THE LODGE, PUTTENHAM HILL HOUSE, PUTTENHAM HILL, PUTTENHAM, GUILDFORD, GU3 1AH",
         "postcode": "GU3 1AH",
@@ -982,6 +1002,13 @@
         "wiki_name": "Midlothian Council",
         "wiki_note": "Pass the house name/number wrapped in double quotes along with the postcode parameter."
     },
+    "MidSuffolkDistrictCouncil": {
+        "skip_get_url": true,
+        "house_number": "Monday",
+        "url": "https://www.midsuffolk.gov.uk",
+        "wiki_name": "Mid Suffolk District Council",
+        "wiki_note": "Use the House Number field to pass the DAY of the week for your collections. Monday/Tuesday/Wednesday/Thursday/Friday"
+    },
     "MidSussexDistrictCouncil": {
         "house_number": "OAKLANDS, OAKLANDS ROAD RH16 1SS",
         "postcode": "RH16 1SS",
@@ -992,10 +1019,10 @@
         "wiki_note": "Pass the name of the street with the house number parameter, wrapped in double quotes. This parser requires a Selenium webdriver."
     },
     "MiltonKeynesCityCouncil": {
-        "uprn": "Fullers Slade",
-        "url": "https://www.milton-keynes.gov.uk/waste-and-recycling/collection-days",
+        "uprn": "25109551",
+        "url": "https://mycouncil.milton-keynes.gov.uk/en/service/Waste_Collection_Round_Checker",
         "wiki_name": "Milton Keynes City Council",
-        "wiki_note": "Pass the name of the estate with the UPRN parameter, wrapped in double quotes."
+        "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN."
     },
     "MoleValleyDistrictCouncil": {
         "postcode": "RH4 1SJ",

uk_bin_collection-0.116.0/uk_bin_collection/uk_bin_collection/councils/ArgyllandButeCouncil.py

@@ -0,0 +1,67 @@
+import time
+
+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
+
+
+# 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:
+
+        user_uprn = kwargs.get("uprn")
+        check_uprn(user_uprn)
+        user_uprn = user_uprn.zfill(12)
+        bindata = {"bins": []}
+
+        URI = "https://www.argyll-bute.gov.uk/rubbish-and-recycling/household-waste/bin-collection"
+
+        data = {"addressSelect": user_uprn}
+
+        s = requests.session()
+        r = s.post(URI, data=data)
+        r.raise_for_status()
+
+        soup = BeautifulSoup(r.content, features="html.parser")
+        soup.prettify()
+
+        # Find the table and extract the rows with bin schedule information
+        table = soup.find("table", class_="table table-bordered")
+        rows = table.find_all("tr")[1:]  # Skip the header row
+
+        current_year = datetime.now().year
+        # Loop through each row and extract the bin type and collection date
+        for row in rows:
+            cells = row.find_all("td")
+            bin_type = cells[0].get_text(strip=True)
+            collection_date = cells[1].get_text(strip=True)
+
+            collection_date = datetime.strptime(
+                collection_date,
+                "%A %d %B",
+            )
+
+            if collection_date.month == 1:
+                collection_date = collection_date.replace(year=current_year + 1)
+            else:
+                collection_date = collection_date.replace(year=current_year)
+
+            dict_data = {
+                "type": bin_type,
+                "collectionDate": collection_date.strftime(date_format),
+            }
+            bindata["bins"].append(dict_data)
+
+        bindata["bins"].sort(
+            key=lambda x: datetime.strptime(x.get("collectionDate"), date_format)
+        )
+
+        return bindata

uk_bin_collection-0.116.0/uk_bin_collection/uk_bin_collection/councils/AshfieldDistrictCouncil.py

@@ -0,0 +1,105 @@
+import time
+from datetime import datetime
+
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.support.wait import WebDriverWait
+
+from uk_bin_collection.uk_bin_collection.common import *
+from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
+
+
+class CouncilClass(AbstractGetBinDataClass):
+    """
+    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:
+        # Get and check UPRN
+        user_postcode = kwargs.get("postcode")
+        user_paon = kwargs.get("paon")
+        check_paon(user_paon)
+        check_postcode(user_postcode)
+        web_driver = kwargs.get("web_driver")
+        headless = kwargs.get("headless")
+        bindata = {"bins": []}
+
+        API_URL = "https://portal.digital.ashfield.gov.uk/w/webpage/raise-case?service=bin_calendar"
+
+        # Create Selenium webdriver
+        driver = create_webdriver(web_driver, headless, None, __name__)
+        driver.get(API_URL)
+
+        title = WebDriverWait(driver, 10).until(
+            EC.presence_of_element_located((By.ID, "sub_page_title"))
+        )
+
+        # Wait for the postcode field to appear then populate it
+        WebDriverWait(driver, 10).until(
+            EC.presence_of_element_located(
+                (By.CSS_SELECTOR, "input.relation_path_type_ahead_search")
+            )
+        )
+
+        inputElement_postcode = WebDriverWait(driver, 10).until(
+            EC.presence_of_element_located(
+                (By.CSS_SELECTOR, "input.relation_path_type_ahead_search")
+            )
+        )
+        inputElement_postcode.clear()
+        inputElement_postcode.send_keys(user_postcode)
+
+        # Wait for the 'Select your property' dropdown to appear and select the first result
+        dropdown = WebDriverWait(driver, 10).until(
+            EC.element_to_be_clickable(
+                (
+                    By.CLASS_NAME,
+                    "result_list ",
+                )
+            )
+        )
+
+        address_element = (
+            WebDriverWait(driver, 10)
+            .until(
+                EC.element_to_be_clickable(
+                    (By.XPATH, f"//li[starts-with(@aria-label, '{user_paon}')]")
+                )
+            )
+            .click()
+        )
+
+        search_button = WebDriverWait(driver, 10).until(
+            EC.element_to_be_clickable(
+                (By.XPATH, "//input[@type='submit' and @value='Search']")
+            )
+        )
+        search_button.click()
+
+        time.sleep(10)
+
+        soup = BeautifulSoup(driver.page_source, features="html.parser")
+        soup.prettify()
+
+        # Find the table by class name
+        table = soup.find("table", {"class": "table listing table-striped"})
+
+        # Iterate over each row in the tbody of the table
+        for row in table.find("tbody").find_all("tr"):
+            # Extract the service, day, and date for each row
+            service = row.find_all("td")[0].get_text(strip=True)
+            date = row.find_all("td")[2].get_text(strip=True)
+
+            dict_data = {
+                "type": service,
+                "collectionDate": datetime.strptime(date, "%a, %d %b %Y").strftime(
+                    date_format
+                ),
+            }
+            bindata["bins"].append(dict_data)
+
+        return bindata

uk_bin_collection-0.116.0/uk_bin_collection/uk_bin_collection/councils/BaberghDistrictCouncil.py

@@ -0,0 +1,132 @@
+import re
+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 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:
+
+        collection_day = kwargs.get("paon")
+        bindata = {"bins": []}
+
+        days_of_week = [
+            "Monday",
+            "Tuesday",
+            "Wednesday",
+            "Thursday",
+            "Friday",
+            "Saturday",
+            "Sunday",
+        ]
+
+        refusestartDate = datetime(2024, 11, 4)
+        recyclingstartDate = datetime(2024, 11, 11)
+
+        offset_days = days_of_week.index(collection_day)
+
+        refuse_dates = get_dates_every_x_days(refusestartDate, 14, 28)
+        recycling_dates = get_dates_every_x_days(recyclingstartDate, 14, 28)
+
+        bank_holidays = [
+            ("25/12/2024", 2),
+            ("26/12/2024", 2),
+            ("27/12/2024", 3),
+            ("30/12/2024", 1),
+            ("31/12/2024", 2),
+            ("01/01/2025", 2),
+            ("02/01/2025", 2),
+            ("03/01/2025", 3),
+            ("06/01/2025", 1),
+            ("07/01/2025", 1),
+            ("08/01/2025", 1),
+            ("09/01/2025", 1),
+            ("10/01/2025", 1),
+            ("18/04/2025", 1),
+            ("21/04/2025", 1),
+            ("22/04/2025", 1),
+            ("23/04/2025", 1),
+            ("24/04/2025", 1),
+            ("25/04/2025", 1),
+            ("05/05/2025", 1),
+            ("06/05/2025", 1),
+            ("07/05/2025", 1),
+            ("08/05/2025", 1),
+            ("09/05/2025", 1),
+            ("26/05/2025", 1),
+            ("27/05/2025", 1),
+            ("28/05/2025", 1),
+            ("29/05/2025", 1),
+            ("30/05/2025", 1),
+            ("25/08/2025", 1),
+            ("26/08/2025", 1),
+            ("27/08/2025", 1),
+            ("28/08/2025", 1),
+            ("29/08/2025", 1),
+        ]
+
+        for refuseDate in refuse_dates:
+
+            collection_date = (
+                datetime.strptime(refuseDate, "%d/%m/%Y") + timedelta(days=offset_days)
+            ).strftime("%d/%m/%Y")
+
+            holiday_offset = next(
+                (value for date, value in bank_holidays if date == collection_date), 0
+            )
+
+            if holiday_offset > 0:
+                collection_date = (
+                    datetime.strptime(collection_date, "%d/%m/%Y")
+                    + timedelta(days=holiday_offset)
+                ).strftime("%d/%m/%Y")
+
+            dict_data = {
+                "type": "Refuse Bin",
+                "collectionDate": collection_date,
+            }
+            bindata["bins"].append(dict_data)
+
+        for recyclingDate in recycling_dates:
+
+            collection_date = (
+                datetime.strptime(recyclingDate, "%d/%m/%Y")
+                + timedelta(days=offset_days)
+            ).strftime("%d/%m/%Y")
+
+            holiday_offset = next(
+                (value for date, value in bank_holidays if date == collection_date), 0
+            )
+
+            if holiday_offset > 0:
+                collection_date = (
+                    datetime.strptime(collection_date, "%d/%m/%Y")
+                    + timedelta(days=holiday_offset)
+                ).strftime("%d/%m/%Y")
+
+            dict_data = {
+                "type": "Recycling Bin",
+                "collectionDate": collection_date,
+            }
+            bindata["bins"].append(dict_data)
+
+        bindata["bins"].sort(
+            key=lambda x: datetime.strptime(x.get("collectionDate"), "%d/%m/%Y")
+        )
+
+        return bindata

uk_bin_collection-0.116.0/uk_bin_collection/uk_bin_collection/councils/CheshireWestAndChesterCouncil.py

@@ -0,0 +1,105 @@
+import time
+
+import requests
+
+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:
+
+        user_uprn = kwargs.get("uprn")
+        check_uprn(user_uprn)
+        bindata = {"bins": []}
+
+        SESSION_URL = "https://my.cheshirewestandchester.gov.uk/authapi/isauthenticated?uri=https://my.cheshirewestandchester.gov.uk/fillform/?iframe_id=fillform-frame-1&db_id=&hostname=my.cheshirewestandchester.gov.uk&withCredentials=true"
+
+        API_URL = "https://my.cheshirewestandchester.gov.uk/apibroker/runLookup"
+
+        headers = {
+            "Content-Type": "application/json",
+            "Accept": "application/json",
+            "User-Agent": "Mozilla/5.0",
+            "X-Requested-With": "XMLHttpRequest",
+            "Referer": "https://mycouncil.milton-keynes.gov.uk/fillform/?iframe_id=fillform-frame-1&db_id=",
+        }
+        s = requests.session()
+        r = s.get(SESSION_URL)
+        r.raise_for_status()
+        session_data = r.json()
+        sid = session_data["auth-session"]
+        params = {
+            "id": "609b918c7dd6d",
+            "repeat_against": "",
+            "noRetry": "false",
+            "getOnlyTokens": "undefined",
+            "log_id": "",
+            "app_name": "AchieveForms",
+            # unix_timestamp
+            "_": str(int(time.time() * 1000)),
+            "sid": sid,
+        }
+
+        r = s.post(API_URL, headers=headers, params=params)
+        r.raise_for_status()
+
+        data = r.json()
+        rows_data = data["integration"]["transformed"]["rows_data"]["0"]
+        AuthenticateResponse = rows_data["AuthenticateResponse"]
+
+        params = {
+            "id": "6101d23110243",
+            "repeat_against": "",
+            "noRetry": "false",
+            "getOnlyTokens": "undefined",
+            "log_id": "",
+            "app_name": "AchieveForms",
+            # unix_timestamp
+            "_": str(int(time.time() * 1000)),
+            "sid": sid,
+        }
+
+        data = {
+            "formValues": {
+                "Section 1": {
+                    "UPRN": {
+                        "value": user_uprn,
+                    },
+                    "AuthenticateResponse": {
+                        "value": AuthenticateResponse,
+                    },
+                }
+            },
+        }
+
+        r = s.post(API_URL, json=data, headers=headers, params=params)
+        r.raise_for_status()
+
+        data = r.json()
+        rows_data = data["integration"]["transformed"]["rows_data"]
+        if not isinstance(rows_data, dict):
+            raise ValueError("Invalid data returned from API")
+
+        # Extract each service's relevant details for the bin schedule
+        for item in rows_data.values():
+            dict_data = {
+                "type": item["serviceType"],
+                "collectionDate": datetime.strptime(
+                    item["collectionDateTime"], "%Y-%m-%dT%H:%M:%S"
+                ).strftime(date_format),
+            }
+            bindata["bins"].append(dict_data)
+
+        bindata["bins"].sort(
+            key=lambda x: datetime.strptime(x.get("collectionDate"), "%d/%m/%Y")
+        )
+
+        return bindata

uk_bin_collection-0.116.0/uk_bin_collection/uk_bin_collection/councils/DerbyCityCouncil.py

@@ -0,0 +1,55 @@
+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
+
+
+# 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:
+
+        user_uprn = kwargs.get("uprn")
+        check_uprn(user_uprn)
+        bindata = {"bins": []}
+
+        URI = f"https://secure.derby.gov.uk/binday/Binday?search.PremisesId={user_uprn}"
+
+        # Make the GET request
+        session = requests.Session()
+        response = session.get(URI)
+
+        soup = BeautifulSoup(response.content, "html.parser")
+
+        # Find all divs with class "binresult" which contain the bin collection information
+        bin_results = soup.find_all("div", class_="binresult")
+
+        # Loop through each bin result to extract date and bin type
+        for result in bin_results:
+            # Find the collection date
+            date_text = result.find("p").strong.get_text(strip=True)
+
+            # Find the bin type by looking at the 'alt' attribute of the img tag
+            bin_type = result.find("img")["alt"]
+
+            if bin_type != "No bins":
+                dict_data = {
+                    "type": bin_type,
+                    "collectionDate": datetime.strptime(
+                        date_text,
+                        "%A, %d %B %Y:",
+                    ).strftime(date_format),
+                }
+                bindata["bins"].append(dict_data)
+
+        bindata["bins"].sort(
+            key=lambda x: datetime.strptime(x.get("collectionDate"), "%d/%m/%Y")
+        )
+
+        return bindata