uk_bin_collection 0.74.0__py3-none-any.whl

uk_bin_collection/uk_bin_collection/councils/TestValleyBoroughCouncil.py

@@ -0,0 +1,203 @@
+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")
+        check_postcode(user_postcode)
+        user_uprn = kwargs.get("uprn")
+        check_uprn(user_uprn)
+
+        headers = {
+            "User-Agent": "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) "
+            "Chrome/87.0.4280.141 Safari/537.36"
+        }
+
+        requests.packages.urllib3.disable_warnings()
+        with requests.Session() as s:
+            # Set Headers
+            s.headers = headers
+
+            # Get the first page - This is the Search for property by Post Code page
+            resource = s.get(
+                "https://iweb.itouchvision.com/portal/f?p=customer:BIN_DAYS:::NO:RP:UID:13353F039C4B1454827EE05536414091A8C058F4"
+            )
+            # Create a BeautifulSoup object from the page's HTML
+            soup = BeautifulSoup(resource.text, "html.parser")
+
+            # The page contains a number of values that must be passed into subsequent requests - extract them here
+            payload = {
+                i["name"]: i.get("value", "") for i in soup.select("input[name]")
+            }
+            payload2 = {
+                i["data-for"]: i.get("value", "")
+                for i in soup.select("input[data-for]")
+            }
+            payload_salt = soup.select_one('input[id="pSalt"]').get("value")
+            payload_protected = soup.select_one('input[id="pPageItemsProtected"]').get(
+                "value"
+            )
+
+            # Add the PostCode and 'SEARCH' to the payload
+            payload["p_request"] = "SEARCH"
+            payload["P153_POST_CODE"] = user_postcode
+
+            # Manipulate the lists and build the JSON that must be submitted in further requests - some data is nested
+            merged_list = {**payload, **payload2}
+            new_list = []
+            other_list = {}
+            for key in merged_list.keys():
+                temp_list = {}
+                val = merged_list[key]
+                if key in [
+                    "P153_UPRN",
+                    "P153_TEMP",
+                    "P153_SYSDATE",
+                    "P0_LANGUAGE",
+                    "P153_POST_CODE",
+                ]:
+                    temp_list = {"n": key, "v": val}
+                    new_list.append(temp_list)
+                elif key in [
+                    "p_flow_id",
+                    "p_flow_step_id",
+                    "p_instance",
+                    "p_page_submission_id",
+                    "p_request",
+                    "p_reload_on_submit",
+                ]:
+                    other_list[key] = val
+                else:
+                    temp_list = {"n": key, "v": "", "ck": val}
+                    new_list.append(temp_list)
+
+            json_builder = {
+                "pageItems": {
+                    "itemsToSubmit": new_list,
+                    "protected": payload_protected,
+                    "rowVersion": "",
+                    "formRegionChecksums": [],
+                },
+                "salt": payload_salt,
+            }
+            json_object = json.dumps(json_builder, separators=(",", ":"))
+            other_list["p_json"] = json_object
+
+            # Set Referrer header
+            s.headers.update(
+                {
+                    "referer": "https://iweb.itouchvision.com/portal/f?p=customer:BIN_DAYS:::NO:RP:UID:13353F039C4B1454827EE05536414091A8C058F4"
+                }
+            )
+
+            # Generate POST including all the JSON we just built
+            s.post(
+                "https://iweb.itouchvision.com/portal/wwv_flow.accept", data=other_list
+            )
+
+            # The second page on the portal would normally allow you to select your property from a dropdown list of
+            # those that are at the postcode entered on the previous page
+            # The required cookies are stored within the session so re-use the session to keep them
+            resource = s.get(
+                "https://iweb.itouchvision.com/portal/itouchvision/r/customer/bin_days"
+            )
+
+            # Create a BeautifulSoup object from the page's HTML
+            soup = BeautifulSoup(resource.text, "html.parser")
+
+            # The page contains a number of values that must be passed into subsequent requests - extract them here
+            payload = {
+                i["name"]: i.get("value", "") for i in soup.select("input[name]")
+            }
+            payload2 = {
+                i["data-for"]: i.get("value", "")
+                for i in soup.select("input[data-for]")
+            }
+            payload_salt = soup.select_one('input[id="pSalt"]').get("value")
+            payload_protected = soup.select_one('input[id="pPageItemsProtected"]').get(
+                "value"
+            )
+
+            # Add the UPRN and 'SUBMIT' to the payload
+            payload["p_request"] = "SUBMIT"
+            payload["P153_UPRN"] = user_uprn
+
+            # Manipulate the lists and build the JSON that must be submitted in further requests - some data is nested
+            merged_list = {**payload, **payload2}
+            new_list = []
+            other_list = {}
+            for key in merged_list.keys():
+                temp_list = {}
+                val = merged_list[key]
+                if key in ["P153_UPRN", "P153_TEMP", "P153_SYSDATE", "P0_LANGUAGE"]:
+                    temp_list = {"n": key, "v": val}
+                    new_list.append(temp_list)
+                elif key in ["P153_ZABY"]:
+                    temp_list = {"n": key, "v": "1", "ck": val}
+                    new_list.append(temp_list)
+                elif key in ["P153_POST_CODE"]:
+                    temp_list = {"n": key, "v": user_postcode, "ck": val}
+                    new_list.append(temp_list)
+                elif key in [
+                    "p_flow_id",
+                    "p_flow_step_id",
+                    "p_instance",
+                    "p_page_submission_id",
+                    "p_request",
+                    "p_reload_on_submit",
+                ]:
+                    other_list[key] = val
+                else:
+                    temp_list = {"n": key, "v": "", "ck": val}
+                    new_list.append(temp_list)
+
+            json_builder = {
+                "pageItems": {
+                    "itemsToSubmit": new_list,
+                    "protected": payload_protected,
+                    "rowVersion": "",
+                    "formRegionChecksums": [],
+                },
+                "salt": payload_salt,
+            }
+
+            json_object = json.dumps(json_builder, separators=(",", ":"))
+            other_list["p_json"] = json_object
+
+            # Generate POST including all the JSON we just built
+            s.post(
+                "https://iweb.itouchvision.com/portal/wwv_flow.accept", data=other_list
+            )
+
+            # The third and final page on the portal shows the detail of the waste collection services
+            # The required cookies are stored within the session so re-use the session to keep them
+            resource = s.get(
+                "https://iweb.itouchvision.com/portal/itouchvision/r/customer/bin_days"
+            )
+
+            # Create a BeautifulSoup object from the page's HTML
+            soup = BeautifulSoup(resource.text, "html.parser")
+            data = {"bins": []}
+
+            # Loop through the items on the page and build a JSON object for ingestion
+            for item in soup.select(".t-MediaList-item"):
+                for value in item.select(".t-MediaList-body"):
+                    dict_data = {
+                        "type": value.select("span")[1].get_text(strip=True).title(),
+                        "collectionDate": datetime.strptime(
+                            value.select(".t-MediaList-desc")[0].get_text(strip=True),
+                            "%A, %d %B, %Y",
+                        ).strftime(date_format),
+                    }
+                    data["bins"].append(dict_data)
+
+            return data

uk_bin_collection/uk_bin_collection/councils/TonbridgeAndMallingBC.py

@@ -0,0 +1,101 @@
+from datetime import *
+
+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:
+        # Get UPRN and postcode from the parsed args
+        user_uprn = kwargs.get("uprn")
+        user_postcode = kwargs.get("postcode")
+        check_uprn(user_uprn)
+        check_postcode(user_postcode)
+
+        requests.packages.urllib3.disable_warnings()
+
+        # Set up some form data, then POST for the form and scrape the result
+        headers = {
+            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8",
+            "Accept-Language": "en-GB,en;q=0.6",
+            "Cache-Control": "no-cache",
+            "Connection": "keep-alive",
+            "Content-Type": "multipart/form-data; boundary=----WebKitFormBoundaryI1XYcX9fNeKxm4LB",
+            # 'Cookie': 'PHPSESSID=-3mn6j-vkWcY4xPPXbT3Ggk1gSQJLId%2CztSoQV5-f8Pi7Cju1wwE151qtwdUyE1c',
+            "Origin": "https://www.tmbc.gov.uk",
+            "Pragma": "no-cache",
+            "Referer": "https://www.tmbc.gov.uk/xfp/form/167",
+            "Sec-Fetch-Dest": "document",
+            "Sec-Fetch-Mode": "navigate",
+            "Sec-Fetch-Site": "same-origin",
+            "Sec-Fetch-User": "?1",
+            "Sec-GPC": "1",
+            "Upgrade-Insecure-Requests": "1",
+            "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",
+            "sec-ch-ua": '"Not?A_Brand";v="8", "Chromium";v="108", "Brave";v="108"',
+            "sec-ch-ua-mobile": "?0",
+            "sec-ch-ua-platform": '"Windows"',
+        }
+        data = (
+            f"------WebKitFormBoundaryI1XYcX9fNeKxm4LB\r\nContent-Disposition: form-data; "
+            f'name="__token"\r\n\r\ns_flSv1eIvJDeCwbFaYxclM3UTomdpWgg2cMWzZckaU\r\n'
+            f"------WebKitFormBoundaryI1XYcX9fNeKxm4LB\r\nContent-Disposition: form-data; "
+            f'name="page"\r\n\r\n128\r\n------WebKitFormBoundaryI1XYcX9fNeKxm4LB\r\nContent-Disposition: '
+            f'form-data; name="locale"\r\n\r\nen_GB\r\n------WebKitFormBoundaryI1XYcX9fNeKxm4LB\r\nContent'
+            f'-Disposition: form-data; name="q752eec300b2ffef2757e4536b77b07061842041a_0_0"\r\n\r\n'
+            f"{user_postcode}\r\n------WebKitFormBoundaryI1XYcX9fNeKxm4LB\r\nContent-Disposition: form-data; "
+            f'name="q752eec300b2ffef2757e4536b77b07061842041a_1_0"\r\n\r\n'
+            f"{user_uprn}\r\n------WebKitFormBoundaryI1XYcX9fNeKxm4LB\r\nContent-Disposition: form-data; "
+            f'name="next"\r\n\r\nNext\r\n------WebKitFormBoundaryI1XYcX9fNeKxm4LB--\r\n '
+        )
+
+        response = requests.post(
+            "https://www.tmbc.gov.uk/xfp/form/167", headers=headers, data=data
+        )
+        soup = BeautifulSoup(response.text, features="html.parser")
+        soup.prettify()
+
+        data = {"bins": []}
+        last_date = datetime.now()
+
+        # Find the table on the page and get data from each row (we don't care about the headings)
+        table = soup.find(
+            "table", {"class": "data-table waste-collections-table"}
+        ).find("tbody")
+        for row in table.find_all("tr"):
+            bin_date = row.find_next("td").text.strip()
+            collection_types = row.find("div", {"class": "collections"}).find_all("p")
+
+            # For each collection type in the list, parse the time
+            for item in collection_types:
+                curr_bin_date = datetime.strptime(bin_date, "%a %d %B")
+
+                # The calendar doesn't include the year, so using this to try to mitigate year change (note: it's
+                # currently January, so no idea if it will work until the end of the year lol)
+                if last_date.date().isocalendar()[1] < 52:
+                    curr_bin_date = datetime(
+                        last_date.year, curr_bin_date.month, curr_bin_date.day
+                    )
+                else:
+                    curr_bin_date = datetime(
+                        last_date.year + 1, curr_bin_date.month, curr_bin_date.day
+                    )
+
+                # Add each collection to the dictionary
+                dict_data = {
+                    "type": item.text.strip(),
+                    "collectionDate": curr_bin_date.strftime(date_format),
+                }
+                data["bins"].append(dict_data)
+                last_date = curr_bin_date
+
+        return data

uk_bin_collection/uk_bin_collection/councils/TorbayCouncil.py

@@ -0,0 +1,51 @@
+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:
+        uprn = kwargs.get("uprn")
+        check_uprn(uprn)
+
+        headers = {
+            "Accept": "*/*",
+            "Accept-Encoding": "gzip, deflate, br",
+            "Accept-Language": "en-GB,en-US;q=0.9,en;q=0.8",
+            "Connection": "keep-alive",
+            "Host": "online.torbay.gov.uk",
+            "Origin": "https://www.torbay.gov.uk",
+            "Referer": "https://www.torbay.gov.uk/",
+            "sec-ch-ua": '"Chromium";v="110", "Not A(Brand";v="24", "Google Chrome";v="110"',
+            "sec-ch-ua-mobile": "?0",
+            "sec-ch-ua-platform": '"Windows"',
+            "Sec-Fetch-Dest": "empty",
+            "Sec-Fetch-Mode": "cors",
+            "Sec-Fetch-Site": "same-site",
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36",
+        }
+        requests.packages.urllib3.disable_warnings()
+        response = requests.get(
+            f"https://online.torbay.gov.uk/services.bartec/collections?uprn={uprn}",
+            headers=headers,
+        )
+        if response.status_code != 200:
+            raise ValueError("No bin data found for provided UPRN.")
+        json_data = json.loads(response.text)
+
+        data = {"bins": []}
+        for c in json_data:
+            dict_data = {
+                "type": c["Service"].replace("Empty ", "").strip(),
+                "collectionDate": datetime.strptime(
+                    c["NextCollection"].strip(), "%d %B %Y"
+                ).strftime(date_format),
+            }
+            data["bins"].append(dict_data)
+
+        return data

uk_bin_collection/uk_bin_collection/councils/TorridgeDistrictCouncil.py

@@ -0,0 +1,154 @@
+from xml.etree import ElementTree
+
+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
+    baseclass. They can also override some
+    operations with a default implementation.
+    """
+
+    def get_data(cls, **kwargs) -> str:
+        """This method makes the request to the council
+
+        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 6.1; Win64; x64)"
+        headers = {"User-Agent": user_agent, "Content-Type": "text/xml"}
+
+        uprn = kwargs.get("uprn")
+        try:
+            if uprn is None or uprn == "":
+                raise ValueError("Invalid UPRN")
+        except Exception as ex:
+            print(f"Exception encountered: {ex}")
+            print(
+                "Please check the provided UPRN. If this error continues, please first trying setting the "
+                "UPRN manually on line 115 before raising an issue."
+            )
+
+        # Make the Request - change the URL - find out your property number
+        # URL
+        url = "https://collections-torridge.azurewebsites.net/WebService2.asmx"
+        # Post data
+        post_data = (
+            '<?xml version="1.0" encoding="utf-8"?><soap:Envelope xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:soap="http://schemas.xmlsoap.org/soap/envelope/"><soap:Body><getRoundCalendarForUPRN xmlns="http://tempuri2.org/"><council>TOR</council><UPRN>'
+            + uprn
+            + "</UPRN><PW>wax01653</PW></getRoundCalendarForUPRN></soap:Body></soap:Envelope>"
+        )
+        requests.packages.urllib3.disable_warnings()
+        full_page = requests.post(url, headers=headers, data=post_data)
+
+        return full_page
+
+    def parse_data(self, page, **kwargs) -> dict:
+        """This method makes the request to the council
+
+        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 6.1; Win64; x64)"
+        headers = {"User-Agent": user_agent, "Content-Type": "text/xml"}
+
+        uprn = kwargs.get("uprn")
+        try:
+            if uprn is None or uprn == "":
+                raise ValueError("Invalid UPRN")
+        except Exception as ex:
+            print(f"Exception encountered: {ex}")
+            print(
+                "Please check the provided UPRN. If this error continues, please first trying setting the "
+                "UPRN manually on line 115 before raising an issue."
+            )
+
+        # Make the Request - change the URL - find out your property number
+        # URL
+        url = "https://collections-torridge.azurewebsites.net/WebService2.asmx"
+        # Post data
+        post_data = (
+            '<?xml version="1.0" encoding="utf-8"?><soap:Envelope xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:soap="http://schemas.xmlsoap.org/soap/envelope/"><soap:Body><getRoundCalendarForUPRN xmlns="http://tempuri2.org/"><council>TOR</council><UPRN>'
+            + uprn
+            + "</UPRN><PW>wax01653</PW></getRoundCalendarForUPRN></soap:Body></soap:Envelope>"
+        )
+        requests.packages.urllib3.disable_warnings()
+        page = requests.post(url, headers=headers, data=post_data)
+
+        # Remove the soap wrapper
+        namespaces = {
+            "soap": "http://schemas.xmlsoap.org/soap/envelope/",
+            "a": "http://tempuri2.org/",
+        }
+        dom = ElementTree.fromstring(page.text)
+        page = dom.find(
+            "./soap:Body"
+            "/a:getRoundCalendarForUPRNResponse"
+            "/a:getRoundCalendarForUPRNResult",
+            namespaces,
+        )
+        # Make a BS4 object
+        soup = BeautifulSoup(page.text, features="html.parser")
+        soup.prettify()
+
+        data = {"bins": []}
+
+        b_el = soup.find("b", string="GardenBin")
+        if b_el:
+            results = re.search(
+                "([A-Za-z]+ \\d\\d? [A-Za-z]+) (.*?)", b_el.next_sibling.split(": ")[1]
+            )
+            if results and results.groups()[0]:
+                date = results.groups()[0] + " " + datetime.today().strftime("%Y")
+                data["bins"].append(
+                    {
+                        "type": "GardenBin",
+                        "collectionDate": get_next_occurrence_from_day_month(
+                            datetime.strptime(date, "%a %d %b %Y")
+                        ).strftime(date_format),
+                    }
+                )
+
+        b_el = soup.find("b", string="Refuse")
+        if b_el:
+            results = re.search(
+                "([A-Za-z]+ \\d\\d? [A-Za-z]+) (.*?)", b_el.next_sibling.split(": ")[1]
+            )
+            if results and results.groups()[0]:
+                date = results.groups()[0] + " " + datetime.today().strftime("%Y")
+                data["bins"].append(
+                    {
+                        "type": "Refuse",
+                        "collectionDate": get_next_occurrence_from_day_month(
+                            datetime.strptime(date, "%a %d %b %Y")
+                        ).strftime(date_format),
+                    }
+                )
+
+        b_el = soup.find("b", string="Recycling")
+        if b_el:
+            results = re.search(
+                "([A-Za-z]+ \\d\\d? [A-Za-z]+) (.*?)", b_el.next_sibling.split(": ")[1]
+            )
+            if results and results.groups()[0]:
+                date = results.groups()[0] + " " + datetime.today().strftime("%Y")
+                data["bins"].append(
+                    {
+                        "type": "Recycling",
+                        "collectionDate": get_next_occurrence_from_day_month(
+                            datetime.strptime(date, "%a %d %b %Y")
+                        ).strftime(date_format),
+                    }
+                )
+
+        data["bins"].sort(
+            key=lambda x: datetime.strptime(x.get("collectionDate"), date_format)
+        )
+
+        return data

uk_bin_collection/uk_bin_collection/councils/ValeofGlamorganCouncil.py

@@ -0,0 +1,119 @@
+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:
+        requests.packages.urllib3.disable_warnings()
+        user_uprn = kwargs.get("uprn")
+        check_uprn(user_uprn)
+        headers = {
+            "Accept": "*/*",
+            "Accept-Language": "en-GB,en;q=0.6",
+            "Connection": "keep-alive",
+            "Referer": "https://www.valeofglamorgan.gov.uk/",
+            "Sec-Fetch-Dest": "script",
+            "Sec-Fetch-Mode": "no-cors",
+            "Sec-Fetch-Site": "same-site",
+            "Sec-GPC": "1",
+            "sec-ch-ua": '"Not?A_Brand";v="8", "Chromium";v="108", "Brave";v="108"',
+            "sec-ch-ua-mobile": "?0",
+            "sec-ch-ua-platform": '"Windows"',
+        }
+        params = {
+            "RequestType": "LocalInfo",
+            "ms": "ValeOfGlamorgan/AllMaps",
+            "group": "Community and Living|Refuse HIDE2",
+            "type": "json",
+            "callback": "AddressInfoCallback",
+            "uid": user_uprn,
+            "import": "jQuery35108514154283927682_1673022974838",
+            "_": "1673022974840",
+        }
+
+        # Get a response from the council
+        response = requests.get(
+            "https://myvale.valeofglamorgan.gov.uk/getdata.aspx",
+            params=params,
+            headers=headers,
+        ).text
+
+        # Load the JSON and seek out the bin week text, then add it to the calendar URL. Also take the weekly
+        # collection type and generate dates for it. Then make a GET request for the calendar
+        bin_week = str(
+            json.loads(response)["Results"]["Refuse_HIDE2"]["Your_Refuse_round_is"]
+        ).replace(" ", "-")
+        weekly_collection = str(
+            json.loads(response)["Results"]["Refuse_HIDE2"]["Recycling__type"]
+        ).capitalize()
+        weekly_dates = get_weekday_dates_in_period(
+            datetime.now(), days_of_week.get(bin_week.split("-")[0].strip()), amount=48
+        )
+        schedule_url = f"https://www.valeofglamorgan.gov.uk/en/living/Recycling-and-Waste/collections/Black-Bag-Collections/{bin_week}.aspx"
+        response = requests.get(schedule_url, verify=False)
+
+        # BS4 parses the calendar
+        soup = BeautifulSoup(response.text, features="html.parser")
+        soup.prettify()
+
+        # Some scraper variables
+        collections = []
+
+        # Get the calendar table and find the headers
+        table = soup.find("table", {"class": "TableStyle_Activities"}).find("tbody")
+        table_headers = table.find("tr").find_all("th")
+        # For all rows below the header, find all details in th next row
+        for tr in soup.find_all("tr")[1:]:
+            row = tr.find_all("td")
+            # Parse month and year - month needs converting from text to number
+            month_and_year = row[0].text.split()
+            if month_and_year[0] in list(calendar.month_abbr):
+                collection_month = datetime.strptime(month_and_year[0], "%b").month
+            elif month_and_year[0] == "Sept":
+                collection_month = int(9)
+            else:
+                collection_month = datetime.strptime(month_and_year[0], "%B").month
+            collection_year = datetime.strptime(month_and_year[1], "%Y").year
+
+            # Get the collection dates column, remove anything that's not a number or space and then convert to dates
+            for day in remove_alpha_characters(row[1].text.strip()).split():
+                try:
+                    bin_date = datetime(collection_year, collection_month, int(day))
+                    collections.append(
+                        (
+                            table_headers[1]
+                            .text.strip()
+                            .replace(" collection date", ""),
+                            bin_date,
+                        )
+                    )
+                except Exception as ex:
+                    continue
+
+        # Add in weekly dates to the tuple
+        for date in weekly_dates:
+            collections.append(
+                (weekly_collection, datetime.strptime(date, date_format))
+            )
+
+        # Order all the data, only including future dates
+        ordered_data = sorted(collections, key=lambda x: x[1])
+        data = {"bins": []}
+        for item in ordered_data:
+            collection_date = item[1]
+            if collection_date.date() >= datetime.now().date():
+                dict_data = {
+                    "type": item[0],
+                    "collectionDate": collection_date.strftime(date_format),
+                }
+                data["bins"].append(dict_data)
+
+        return data