uk_bin_collection 0.119.0__tar.gz → 0.120.0__tar.gz

{uk_bin_collection-0.119.0 → uk_bin_collection-0.120.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.119.0
+Version: 0.120.0
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.119.0 → uk_bin_collection-0.120.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.119.0"
+version = "0.120.0"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.119.0 → uk_bin_collection-0.120.0}/uk_bin_collection/tests/input.json

@@ -88,9 +88,10 @@
         "skip_get_url": true,
         "house_number": "Monday",
         "postcode": "Week 1",
+        "uprn": "Tuesday",
         "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. [OPTIONAL] Use the 'postcode' field to pass the WEEK for your garden collection. [Week 1/Week 2]"
+        "wiki_note": "Use the House Number field to pass the DAY of the week for your NORMAL collections. [Monday/Tuesday/Wednesday/Thursday/Friday]. [OPTIONAL] Use the 'postcode' field to pass the WEEK for your garden collection. [Week 1/Week 2]. [OPTIONAL] Use the 'uprn' field to pass the DAY for your garden collection. [Monday/Tuesday/Wednesday/Thursday/Friday]"
     },
     "BCPCouncil": {
         "skip_get_url": true,
@@ -468,6 +469,13 @@
         "wiki_name": "Croydon Council",
         "wiki_note": "Pass the house number and postcode in their respective parameters."
     },
+    "CumberlandAllerdaleCouncil": {
+        "house_number": "2",
+        "postcode": "CA13 0DE",
+        "url": "https://www.allerdale.gov.uk",
+        "wiki_name": "Cumberland Council - Allerdale District",
+        "wiki_note": "Pass the house number and postcode in their respective parameters."
+    },
     "DacorumBoroughCouncil": {
         "house_number": "13",
         "postcode": "HP3 9JY",
@@ -810,6 +818,12 @@
         "wiki_name": "Harrogate Borough Council",
         "wiki_note": "Pass the UPRN, which can be found at [this site](https://secure.harrogate.gov.uk/inmyarea). URL doesn't need to be passed."
     },
+    "HartlepoolBoroughCouncil": {
+        "url": "https://www.hartlepool.gov.uk",
+        "uprn": "100110019551",
+        "wiki_name": "Hartlepool Borough Council",
+        "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find your UPRN."
+    },
     "HertsmereBoroughCouncil": {
         "house_number": "1",
         "postcode": "WD7 9HZ",
@@ -950,6 +964,12 @@
         "wiki_name": "London Borough Harrow",
         "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN."
     },
+    "LondonBoroughHavering": {
+        "url": "https://www.havering.gov.uk",
+        "uprn": "100021380730",
+        "wiki_name": "London Borough Havering",
+        "wiki_note": "Pass the UPRN. You can find it using [FindMyAddress](https://www.findmyaddress.co.uk/search)."
+    },
     "LondonBoroughHounslow": {
         "skip_get_url": true,
         "uprn": "100021577765",
@@ -1047,9 +1067,10 @@
         "skip_get_url": true,
         "house_number": "Monday",
         "postcode": "Week 2",
+        "uprn": "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. [OPTIONAL] Use the 'postcode' field to pass the WEEK for your garden collection. [Week 1/Week 2]"
+        "wiki_note": "Use the House Number field to pass the DAY of the week for your NORMAL collections. [Monday/Tuesday/Wednesday/Thursday/Friday]. [OPTIONAL] Use the 'postcode' field to pass the WEEK for your garden collection. [Week 1/Week 2]. [OPTIONAL] Use the 'uprn' field to pass the DAY for your garden collection. [Monday/Tuesday/Wednesday/Thursday/Friday]"
     },
     "MidSussexDistrictCouncil": {
         "house_number": "OAKLANDS, OAKLANDS ROAD RH16 1SS",
@@ -1104,6 +1125,12 @@
         "wiki_name": "Newcastle City Council",
         "wiki_note": "Replace XXXXXXXX with your UPRN."
     },
+    "NewcastleUnderLymeCouncil": {
+        "url": "https://www.newcastle-staffs.gov.uk",
+        "uprn": "100031725433",
+        "wiki_name": "Newcastle Under Lyme Council",
+        "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find your UPRN."
+    },
     "NewhamCouncil": {
         "skip_get_url": true,
         "url": "https://bincollection.newham.gov.uk/Details/Index/000046029461",
@@ -1142,6 +1169,13 @@
         "wiki_name": "North East Lincolnshire Council",
         "wiki_note": "Replace XXXXXXXX with your UPRN."
     },
+    "NorthHertfordshireDistrictCouncil": {
+        "house_number": "2",
+        "postcode": "SG6 4BJ",
+        "url": "https://www.north-herts.gov.uk",
+        "wiki_name": "North Hertfordshire District Council",
+        "wiki_note": "Pass the house number and postcode in their respective parameters."
+    },
     "NorthKestevenDistrictCouncil": {
         "url": "https://www.n-kesteven.org.uk/bins/display?uprn=100030869513",
         "wiki_command_url_override": "https://www.n-kesteven.org.uk/bins/display?uprn=XXXXXXXX",

{uk_bin_collection-0.119.0 → uk_bin_collection-0.120.0}/uk_bin_collection/uk_bin_collection/councils/BaberghDistrictCouncil.py

@@ -24,6 +24,7 @@ class CouncilClass(AbstractGetBinDataClass):
 
         collection_day = kwargs.get("paon")
         garden_collection_week = kwargs.get("postcode")
+        garden_collection_day = kwargs.get("uprn")
         bindata = {"bins": []}
 
         days_of_week = [
@@ -42,6 +43,7 @@ class CouncilClass(AbstractGetBinDataClass):
         recyclingstartDate = datetime(2024, 11, 11)
 
         offset_days = days_of_week.index(collection_day)
+        offset_days_garden = days_of_week.index(garden_collection_day)
         if garden_collection_week:
             garden_collection = garden_week.index(garden_collection_week)
 
@@ -155,7 +157,7 @@ class CouncilClass(AbstractGetBinDataClass):
 
                 collection_date = (
                     datetime.strptime(gardenDate, "%d/%m/%Y")
-                    + timedelta(days=offset_days)
+                    + timedelta(days=offset_days_garden)
                 ).strftime("%d/%m/%Y")
 
                 garden_holiday = next(

uk_bin_collection-0.120.0/uk_bin_collection/uk_bin_collection/councils/CumberlandAllerdaleCouncil.py

@@ -0,0 +1,93 @@
+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_postcode = kwargs.get("postcode")
+        user_paon = kwargs.get("paon")
+        check_postcode(user_postcode)
+        check_paon(user_paon)
+        bindata = {"bins": []}
+
+        URI = "https://abc-wrp.whitespacews.com/"
+
+        session = requests.Session()
+
+        # get link from first page as has some kind of unique hash
+        r = session.get(
+            URI,
+        )
+        r.raise_for_status()
+        soup = BeautifulSoup(r.text, features="html.parser")
+
+        alink = soup.find("a", text="View My Collections")
+
+        if alink is None:
+            raise Exception("Initial page did not load correctly")
+
+        # greplace 'seq' query string to skip next step
+        nextpageurl = alink["href"].replace("seq=1", "seq=2")
+
+        data = {
+            "address_name_number": user_paon,
+            "address_postcode": user_postcode,
+        }
+
+        # get list of addresses
+        r = session.post(nextpageurl, data)
+        r.raise_for_status()
+
+        soup = BeautifulSoup(r.text, features="html.parser")
+
+        # get first address (if you don't enter enough argument values this won't find the right address)
+        alink = soup.find("div", id="property_list").find("a")
+
+        if alink is None:
+            raise Exception("Address not found")
+
+        nextpageurl = URI + alink["href"]
+
+        # get collection page
+        r = session.get(
+            nextpageurl,
+        )
+        r.raise_for_status()
+        soup = BeautifulSoup(r.text, features="html.parser")
+
+        if soup.find("span", id="waste-hint"):
+            raise Exception("No scheduled services at this address")
+
+        u1s = soup.find("section", id="scheduled-collections").find_all("u1")
+
+        for u1 in u1s:
+            lis = u1.find_all("li", recursive=False)
+
+            date = lis[1].text.replace("\n", "")
+            bin_type = lis[2].text.replace("\n", "")
+
+            dict_data = {
+                "type": bin_type,
+                "collectionDate": datetime.strptime(
+                    date,
+                    "%d/%m/%Y",
+                ).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-0.119.0 → uk_bin_collection-0.120.0}/uk_bin_collection/uk_bin_collection/councils/EnvironmentFirst.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
 
@@ -45,4 +46,17 @@ class CouncilClass(AbstractGetBinDataClass):
         }
         data["bins"].append(dict_data)
 
+        if len(page_text) > 5:
+            garden_day = datetime.strptime(
+                remove_ordinal_indicator_from_date_string(
+                    page_text[6].find_next("strong").text
+                ),
+                "%d %B %Y",
+            ).strftime(date_format)
+            dict_data = {
+                "type": "Garden",
+                "collectionDate": garden_day,
+            }
+            data["bins"].append(dict_data)
+
         return data

uk_bin_collection-0.120.0/uk_bin_collection/uk_bin_collection/councils/HartlepoolBoroughCouncil.py

@@ -0,0 +1,83 @@
+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://online.hartlepool.gov.uk/authapi/isauthenticated?uri=https%253A%252F%252Fonline.hartlepool.gov.uk%252Fservice%252FRefuse_and_recycling___check_bin_day&hostname=online.hartlepool.gov.uk&withCredentials=true"
+
+        API_URL = "https://online.hartlepool.gov.uk/apibroker/runLookup"
+
+        headers = {
+            "Content-Type": "application/json",
+            "Accept": "application/json",
+            "User-Agent": "Mozilla/5.0",
+            "X-Requested-With": "XMLHttpRequest",
+            "Referer": "https://online.hartlepool.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": "5ec67e019ffdd",
+            "repeat_against": "",
+            "noRetry": "true",
+            "getOnlyTokens": "undefined",
+            "log_id": "",
+            "app_name": "AF-Renderer::Self",
+            # unix_timestamp
+            "_": str(int(time.time() * 1000)),
+            "sid": sid,
+        }
+
+        data = {
+            "formValues": {
+                "Section 1": {
+                    "collectionLocationUPRN": {
+                        "value": user_uprn,
+                    },
+                },
+            },
+        }
+
+        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"]["0"]
+        if not isinstance(rows_data, dict):
+            raise ValueError("Invalid data returned from API")
+
+        soup = BeautifulSoup(rows_data["HTMLCollectionDatesText"], "html.parser")
+
+        # Find all div elements containing the bin schedule
+        for div in soup.find_all("div"):
+            # Extract bin type and date from the span tag
+            text = div.find("span").text.strip()
+            bin_type, date = text.split(" ", 1)
+            dict_data = {
+                "type": bin_type,
+                "collectionDate": date,
+            }
+            bindata["bins"].append(dict_data)
+
+        return bindata

uk_bin_collection-0.120.0/uk_bin_collection/uk_bin_collection/councils/LondonBoroughHavering.py

@@ -0,0 +1,75 @@
+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 = "https://lbhapiprod.azure-api.net"
+        endpoint = f"{URI}/whitespace/GetCollectionByUprnAndDate"
+        subscription_key = "2ea6a75f9ea34bb58d299a0c9f84e72e"
+
+        # Get today's date in 'YYYY-MM-DD' format
+        collection_date = datetime.now().strftime("%Y-%m-%d")
+
+        # Define the request headers
+        headers = {
+            "Content-Type": "application/json",
+            "Ocp-Apim-Subscription-Key": subscription_key,
+        }
+
+        # Define the request body
+        data = {
+            "getCollectionByUprnAndDate": {
+                "getCollectionByUprnAndDateInput": {
+                    "uprn": user_uprn,
+                    "nextCollectionFromDate": collection_date,
+                }
+            }
+        }
+        # Make the POST request
+        response = requests.post(endpoint, headers=headers, data=json.dumps(data))
+        response.raise_for_status()  # Raise an exception for HTTP errors
+
+        # Parse the JSON response
+        response_data = response.json()
+
+        collections = (
+            response_data.get("getCollectionByUprnAndDateResponse", {})
+            .get("getCollectionByUprnAndDateResult", {})
+            .get("Collections", [])
+        )
+
+        for collection in collections:
+            bin_type = collection["service"]
+            collection_date = collection["date"]
+
+            dict_data = {
+                "type": bin_type,
+                "collectionDate": datetime.strptime(
+                    collection_date,
+                    "%d/%m/%Y %H:%M:%S",
+                ).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-0.119.0 → uk_bin_collection-0.120.0}/uk_bin_collection/uk_bin_collection/councils/MidSuffolkDistrictCouncil.py

@@ -24,6 +24,7 @@ class CouncilClass(AbstractGetBinDataClass):
 
         collection_day = kwargs.get("paon")
         garden_collection_week = kwargs.get("postcode")
+        garden_collection_day = kwargs.get("uprn")
         bindata = {"bins": []}
 
         days_of_week = [
@@ -42,6 +43,7 @@ class CouncilClass(AbstractGetBinDataClass):
         recyclingstartDate = datetime(2024, 11, 4)
 
         offset_days = days_of_week.index(collection_day)
+        offset_days_garden = days_of_week.index(garden_collection_day)
         if garden_collection_week:
             garden_collection = garden_week.index(garden_collection_week)
 
@@ -155,7 +157,7 @@ class CouncilClass(AbstractGetBinDataClass):
 
                 collection_date = (
                     datetime.strptime(gardenDate, "%d/%m/%Y")
-                    + timedelta(days=offset_days)
+                    + timedelta(days=offset_days_garden)
                 ).strftime("%d/%m/%Y")
 
                 garden_holiday = next(

uk_bin_collection-0.120.0/uk_bin_collection/uk_bin_collection/councils/NewcastleUnderLymeCouncil.py

@@ -0,0 +1,66 @@
+import requests
+from bs4 import BeautifulSoup
+from dateutil.relativedelta import relativedelta
+
+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.newcastle-staffs.gov.uk/homepage/97/check-your-bin-day?uprn={user_uprn}"
+
+        # Make the GET request
+        response = requests.get(URI)
+        response.raise_for_status()
+        soup = BeautifulSoup(response.text, features="html.parser")
+        soup.prettify()
+
+        # Find the table
+        table = soup.find("table", {"class": "data-table"})
+
+        if table:
+            rows = table.find("tbody").find_all("tr")
+            for row in rows:
+                date = datetime.strptime(
+                    (
+                        row.find_all("td")[0]
+                        .get_text(strip=True)
+                        .replace("Date:", "")
+                        .strip()
+                    ),
+                    "%A %d %B",
+                ).replace(year=datetime.now().year)
+                if datetime.now().month > 10 and date.month < 3:
+                    date = date + relativedelta(years=1)
+                bin_types = (
+                    row.find_all("td")[1]
+                    .text.replace("Collection Type:", "")
+                    .splitlines()
+                )
+                for bin_type in bin_types:
+                    bin_type = bin_type.strip()
+                    if bin_type:
+                        dict_data = {
+                            "type": bin_type.strip(),
+                            "collectionDate": date.strftime("%d/%m/%Y"),
+                        }
+                        bindata["bins"].append(dict_data)
+
+        bindata["bins"].sort(
+            key=lambda x: datetime.strptime(x.get("collectionDate"), "%d/%m/%Y")
+        )
+
+        return bindata

uk_bin_collection-0.120.0/uk_bin_collection/uk_bin_collection/councils/NorthHertfordshireDistrictCouncil.py

@@ -0,0 +1,93 @@
+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_postcode = kwargs.get("postcode")
+        user_paon = kwargs.get("paon")
+        check_postcode(user_postcode)
+        check_paon(user_paon)
+        bindata = {"bins": []}
+
+        URI = "https://uhtn-wrp.whitespacews.com/"
+
+        session = requests.Session()
+
+        # get link from first page as has some kind of unique hash
+        r = session.get(
+            URI,
+        )
+        r.raise_for_status()
+        soup = BeautifulSoup(r.text, features="html.parser")
+
+        alink = soup.find("a", text="Find my bin collection day")
+
+        if alink is None:
+            raise Exception("Initial page did not load correctly")
+
+        # greplace 'seq' query string to skip next step
+        nextpageurl = alink["href"].replace("seq=1", "seq=2")
+
+        data = {
+            "address_name_number": user_paon,
+            "address_postcode": user_postcode,
+        }
+
+        # get list of addresses
+        r = session.post(nextpageurl, data)
+        r.raise_for_status()
+
+        soup = BeautifulSoup(r.text, features="html.parser")
+
+        # get first address (if you don't enter enough argument values this won't find the right address)
+        alink = soup.find("div", id="property_list").find("a")
+
+        if alink is None:
+            raise Exception("Address not found")
+
+        nextpageurl = URI + alink["href"]
+
+        # get collection page
+        r = session.get(
+            nextpageurl,
+        )
+        r.raise_for_status()
+        soup = BeautifulSoup(r.text, features="html.parser")
+
+        if soup.find("span", id="waste-hint"):
+            raise Exception("No scheduled services at this address")
+
+        u1s = soup.find("section", id="scheduled-collections").find_all("u1")
+
+        for u1 in u1s:
+            lis = u1.find_all("li", recursive=False)
+
+            date = lis[1].text.replace("\n", "")
+            bin_type = lis[2].text.replace("\n", "")
+
+            dict_data = {
+                "type": bin_type,
+                "collectionDate": datetime.strptime(
+                    date,
+                    "%d/%m/%Y",
+                ).strftime(date_format),
+            }
+            bindata["bins"].append(dict_data)
+
+        bindata["bins"].sort(
+            key=lambda x: datetime.strptime(x.get("collectionDate"), date_format)
+        )
+
+        return bindata