uk_bin_collection 0.103.0__tar.gz → 0.104.0__tar.gz

{uk_bin_collection-0.103.0 → uk_bin_collection-0.104.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.103.0
+Version: 0.104.0
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.103.0 → uk_bin_collection-0.104.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.103.0"
+version = "0.104.0"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.103.0 → uk_bin_collection-0.104.0}/uk_bin_collection/tests/input.json

@@ -1,4 +1,11 @@
 {
+    "AberdeenshireCouncil": {
+        "url": "https://online.aberdeenshire.gov.uk",
+        "wiki_command_url_override": "https://online.aberdeenshire.gov.uk",
+        "uprn": "151176430",
+        "wiki_name": "Aberdeenshire Council",
+        "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN."
+    },
     "AdurAndWorthingCouncils": {
         "url": "https://www.adur-worthing.gov.uk/bin-day/?brlu-selected-address=100061878829",
         "wiki_command_url_override": "https://www.adur-worthing.gov.uk/bin-day/?brlu-selected-address=XXXXXXXX",
@@ -201,6 +208,13 @@
         "wiki_name": "Cannock Chase District Council",
         "wiki_note": "To get the UPRN, you can use [FindMyAddress](https://www.findmyaddress.co.uk/search)"
     },
+    "CanterburyCityCouncil": {
+        "url": "https://www.canterbury.gov.uk",
+        "wiki_command_url_override": "https://www.canterbury.gov.uk",
+        "uprn": "10094583181",
+        "wiki_name": "Canterbury City Council",
+        "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN."
+    },
     "CardiffCouncil": {
         "skip_get_url": true,
         "uprn": "100100112419",
@@ -681,6 +695,13 @@
         "wiki_name": "London Borough Redbridge",
         "wiki_note": "Follow the instructions [here](https://my.redbridge.gov.uk/RecycleRefuse) until you get the page listing your \"Address\" then copy the entire address text and use that in the house number field."
     },
+    "LutonBoroughCouncil": {
+        "url": "https://myforms.luton.gov.uk",
+        "wiki_command_url_override": "https://myforms.luton.gov.uk",
+        "uprn": "100080155778",
+        "wiki_name": "Luton Borough Council",
+        "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN."
+    },
     "MaldonDistrictCouncil": {
         "skip_get_url": true,
         "uprn": "100090557253",
@@ -1189,6 +1210,13 @@
         "url": "https://www1.swansea.gov.uk/recyclingsearch/",
         "wiki_name": "SwanseaCouncil"
     },
+    "SwindonBoroughCouncil": {
+        "url": "https://www.swindon.gov.uk",
+        "wiki_command_url_override": "https://www.swindon.gov.uk",
+        "uprn": "10022793351",
+        "wiki_name": "Swindon Borough Council",
+        "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN."
+    },
     "TamesideMBCouncil": {
         "skip_get_url": true,
         "uprn": "100012835362",
@@ -1369,6 +1397,15 @@
         "url": "https://www.northampton.gov.uk/info/200084/bins-waste-and-recycling/1602/check-your-collection-day",
         "wiki_name": "West Northamptonshire Council"
     },
+    "WestOxfordshireDistrictCouncil": {
+        "house_number": "24",
+        "postcode": "OX28 1YA",
+        "skip_get_url": true,
+        "url": "https://community.westoxon.gov.uk/s/waste-collection-enquiry",
+        "web_driver": "http://selenium:4444",
+        "wiki_name": "West Oxfordshire District Council",
+        "wiki_note": "Pass the full address in the house number and postcode in"
+    },
     "WestSuffolkCouncil": {
         "postcode": "IP28 6DR",
         "skip_get_url": true,

uk_bin_collection-0.104.0/uk_bin_collection/uk_bin_collection/councils/AberdeenshireCouncil.py

@@ -0,0 +1,52 @@
+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://online.aberdeenshire.gov.uk/Apps/Waste-Collections/Routes/Route/{user_uprn}"
+
+        # Make the GET request
+        response = requests.get(URI)
+
+        soup = BeautifulSoup(response.content, features="html.parser")
+        soup.prettify()
+
+        for collection in soup.find("table").find("tbody").find_all("tr"):
+            th = collection.find("th")
+            if th:
+                continue
+            td = collection.find_all("td")
+            collection_date = datetime.strptime(
+                td[0].text,
+                "%d/%m/%Y %A",
+            )
+            bin_type = td[1].text.split(" and ")
+
+            for bin in bin_type:
+                dict_data = {
+                    "type": bin,
+                    "collectionDate": collection_date.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-0.104.0/uk_bin_collection/uk_bin_collection/councils/CanterburyCityCouncil.py

@@ -0,0 +1,54 @@
+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": []}
+
+        data = {"uprn": user_uprn, "usrn": "1"}
+
+        URI = (
+            "https://zbr7r13ke2.execute-api.eu-west-2.amazonaws.com/Beta/get-bin-dates"
+        )
+
+        # Make the GET request
+        response = requests.post(URI, json=data)
+        response.raise_for_status()
+
+        # Parse the JSON response
+        bin_collection = json.loads(response.json()["dates"])
+        collections = {
+            "General": bin_collection["blackBinDay"],
+            "Recycling": bin_collection["recyclingBinDay"],
+            "Food": bin_collection["foodBinDay"],
+            "Garden": bin_collection["gardenBinDay"],
+        }
+        # Loop through each collection in bin_collection
+        for collection in collections:
+            print(collection)
+
+            if len(collections[collection]) <= 0:
+                continue
+            for date in collections[collection]:
+                date = (
+                    datetime.strptime(date, "%Y-%m-%dT%H:%M:%S").strftime("%d/%m/%Y"),
+                )
+                dict_data = {"type": collection, "collectionDate": date[0]}
+                bindata["bins"].append(dict_data)
+
+        return bindata

uk_bin_collection-0.104.0/uk_bin_collection/uk_bin_collection/councils/LutonBoroughCouncil.py

@@ -0,0 +1,81 @@
+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)
+        bindata = {"bins": []}
+
+        SESSION_URL = "https://myforms.luton.gov.uk/authapi/isauthenticated?uri=https%253A%252F%252Fmyforms.luton.gov.uk%252Fservice%252FFind_my_bin_collection_date&hostname=myforms.luton.gov.uk&withCredentials=true"
+
+        API_URL = "https://myforms.luton.gov.uk/apibroker/runLookup"
+
+        data = {
+            "formValues": {
+                "Find my bin collection date": {
+                    "id": {
+                        "value": f"1-{user_uprn}",
+                    },
+                },
+            }
+        }
+
+        headers = {
+            "Content-Type": "application/json",
+            "Accept": "application/json",
+            "User-Agent": "Mozilla/5.0",
+            "X-Requested-With": "XMLHttpRequest",
+            "Referer": "https://myforms.luton.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": "65cb710f8d525",
+            "repeat_against": "",
+            "noRetry": "true",
+            "getOnlyTokens": "undefined",
+            "log_id": "",
+            "app_name": "AF-Renderer::Self",
+            # unix_timestamp
+            "_": str(int(time.time() * 1000)),
+            "sid": sid,
+        }
+        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"][f"{user_uprn}"]
+
+        soup = BeautifulSoup(rows_data["html"], features="html.parser")
+        soup.prettify()
+        for collection in soup.find_all("tr"):
+            tds = collection.find_all("td")
+            bin_type = tds[1].text
+            collection_date = datetime.strptime(
+                tds[0].text,
+                "%A %d %b %Y",
+            )
+            dict_data = {
+                "type": bin_type,
+                "collectionDate": collection_date.strftime(date_format),
+            }
+            bindata["bins"].append(dict_data)
+
+        return bindata

uk_bin_collection-0.104.0/uk_bin_collection/uk_bin_collection/councils/SwindonBoroughCouncil.py

@@ -0,0 +1,56 @@
+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)
+        bindata = {"bins": []}
+
+        URI = f"https://www.swindon.gov.uk/info/20122/rubbish_and_recycling_collection_days?addressList={user_uprn}&uprnSubmit=Yes"
+
+        # Make the GET request
+        response = requests.get(URI)
+
+        # Parse the JSON response
+        soup = BeautifulSoup(response.text, "html.parser")
+
+        bin_collection_content = soup.find_all(
+            "div", {"class": "bin-collection-content"}
+        )
+        for content in bin_collection_content:
+            content_left = content.find("div", {"class": "content-left"})
+            content_right = content.find("div", {"class": "content-right"})
+            if content_left and content_right:
+
+                bin_types = content_left.find("h3").text.split(" and ")
+                for bin_type in bin_types:
+
+                    collection_date = datetime.strptime(
+                        content_right.find(
+                            "span", {"class": "nextCollectionDate"}
+                        ).text,
+                        "%A, %d %B %Y",
+                    ).strftime(date_format)
+
+                    dict_data = {
+                        "type": bin_type,
+                        "collectionDate": collection_date,
+                    }
+                    bindata["bins"].append(dict_data)
+
+        return bindata

uk_bin_collection-0.104.0/uk_bin_collection/uk_bin_collection/councils/WestOxfordshireDistrictCouncil.py

@@ -0,0 +1,113 @@
+import time
+from datetime import datetime
+
+from bs4 import BeautifulSoup
+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 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:
+            page = "https://community.westoxon.gov.uk/s/waste-collection-enquiry"
+
+            data = {"bins": []}
+
+            house_number = kwargs.get("paon")
+            postcode = kwargs.get("postcode")
+            full_address = f"{house_number}, {postcode}"
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+
+            # Create Selenium webdriver
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            driver.get(page)
+
+            # If you bang in the house number (or property name) and postcode in the box it should find your property
+            wait = WebDriverWait(driver, 60)
+            address_entry_field = wait.until(
+                EC.presence_of_element_located(
+                    (By.XPATH, '//*[@id="combobox-input-19"]')
+                )
+            )
+
+            address_entry_field.send_keys(str(full_address))
+
+            address_entry_field = wait.until(
+                EC.element_to_be_clickable((By.XPATH, '//*[@id="combobox-input-19"]'))
+            )
+            address_entry_field.click()
+            address_entry_field.send_keys(Keys.BACKSPACE)
+            address_entry_field.send_keys(str(full_address[len(full_address) - 1]))
+
+            first_found_address = wait.until(
+                EC.element_to_be_clickable(
+                    (By.XPATH, '//*[@id="dropdown-element-19"]/ul')
+                )
+            )
+
+            first_found_address.click()
+            # Wait for the 'Select your property' dropdown to appear and select the first result
+            next_btn = wait.until(
+                EC.element_to_be_clickable((By.XPATH, "//lightning-button/button"))
+            )
+            next_btn.click()
+            bin_data = wait.until(
+                EC.presence_of_element_located(
+                    (By.XPATH, "//span[contains(text(), 'Container')]")
+                )
+            )
+
+            soup = BeautifulSoup(driver.page_source, features="html.parser")
+
+            rows = soup.find_all("tr", class_="slds-hint-parent")
+            current_year = datetime.now().year
+
+            for row in rows:
+                columns = row.find_all("td")
+                if columns:
+                    container_type = row.find("th").text.strip()
+                    collection_day = re.sub(
+                        r"[^a-zA-Z0-9,\s]", "", columns[0].get_text()
+                    ).strip()
+
+                    # Parse the date from the string
+                    parsed_date = datetime.strptime(collection_day, "%a, %d %B")
+                    if parsed_date < datetime(
+                        parsed_date.year, parsed_date.month, parsed_date.day
+                    ):
+                        parsed_date = parsed_date.replace(year=current_year + 1)
+                    else:
+                        parsed_date = parsed_date.replace(year=current_year)
+                    # Format the date as %d/%m/%Y
+                    formatted_date = parsed_date.strftime("%d/%m/%Y")
+
+                    # Add the bin type and collection date to the 'data' dictionary
+                    data["bins"].append(
+                        {"type": container_type, "collectionDate": formatted_date}
+                    )
+        except Exception as e:
+            # Here you can log the exception if needed
+            print(f"An error occurred: {e}")
+            # Optionally, re-raise the exception if you want it to propagate
+            raise
+        finally:
+            # This block ensures that the driver is closed regardless of an exception
+            if driver:
+                driver.quit()
+        return data