uk_bin_collection 0.105.0__tar.gz → 0.106.0__tar.gz

{uk_bin_collection-0.105.0 → uk_bin_collection-0.106.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.105.0
+Version: 0.106.0
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.105.0 → uk_bin_collection-0.106.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.105.0"
+version = "0.106.0"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.105.0 → uk_bin_collection-0.106.0}/uk_bin_collection/tests/input.json

@@ -484,6 +484,20 @@
         "url": "https://www.fenland.gov.uk/article/13114/",
         "wiki_name": "Fenland District Council"
     },
+    "FifeCouncil": {
+        "url": "https://www.fife.gov.uk",
+        "wiki_command_url_override": "https://www.fife.gov.uk",
+        "uprn": "320203521",
+        "wiki_name": "Fife Council",
+        "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN."
+    },
+    "FlintshireCountyCouncil": {
+        "url": "https://digital.flintshire.gov.uk",
+        "wiki_command_url_override": "https://digital.flintshire.gov.uk",
+        "uprn": "100100213710",
+        "wiki_name": "Flintshire County Council",
+        "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN."
+    },
     "ForestOfDeanDistrictCouncil": {
         "house_number": "ELMOGAL, PARKEND ROAD, BREAM, LYDNEY",
         "postcode": "GL15 6JT",
@@ -754,10 +768,12 @@
         "wiki_note": "Pass the house name/number plus the name of the street with the postcode parameter, wrapped in double quotes.  Check the address in the web site first. This version will only pick the first SHOW button returned by the search or if it is fully unique.  The search is not very predictable (e.g. house number 4 returns 14,24,4,44 etc.)."
     },
     "MidlothianCouncil": {
-        "url": "https://www.midlothian.gov.uk/directory_record/92594377/glenesk_bonnyrigg_eh19_3je",
-        "wiki_command_url_override": "https://www.midlothian.gov.uk/directory_record/XXXXXX/XXXXXX",
+        "house_number": "52",
+        "postcode": "EH19 2EB",
+        "skip_get_url": true,
+        "url": "https://www.midlothian.gov.uk/info/1054/bins_and_recycling/343/bin_collection_days",
         "wiki_name": "Midlothian Council",
-        "wiki_note": "Follow the instructions [here](https://www.midlothian.gov.uk/info/1054/bins_and_recycling/343/bin_collection_days) until you get the page that shows the weekly collections for your address then copy the URL and replace the URL in the command."
+        "wiki_note": "Pass the house name/number wrapped in double quotes along with the postcode parameter"
     },
     "MidSussexDistrictCouncil": {
         "house_number": "OAKLANDS, OAKLANDS ROAD RH16 1SS",
@@ -1141,8 +1157,8 @@
         "wiki_name": "South Tyneside Council"
     },
     "SouthwarkCouncil": {
-        "url": "https://www.southwark.gov.uk/bins/lookup/",
-        "wiki_command_url_override": "https://www.southwark.gov.uk/bins/lookup/XXXXXXXX",
+        "url": "https://services.southwark.gov.uk/bins/lookup/",
+        "wiki_command_url_override": "https://services.southwark.gov.uk/bins/lookup/XXXXXXXX",
         "uprn": "200003469271",
         "wiki_name": "Southwark Council",
         "wiki_note": "Replace XXXXXXXX with UPRN. You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN."
@@ -1180,6 +1196,14 @@
         "wiki_name": "Stockport Borough Council",
         "wiki_note": "Replace XXXXXXXX with UPRN."
     },
+    "StocktonOnTeesCouncil": {
+        "house_number": "24",
+        "postcode": "TS20 2RD",
+        "skip_get_url": true,
+        "url": "https://www.stockton.gov.uk",
+        "web_driver": "http://selenium:4444",
+        "wiki_name": "Stockton On Tees Council"
+    },
     "StokeOnTrentCityCouncil": {
         "url": "https://www.stoke.gov.uk/jadu/custom/webserviceLookUps/BarTecWebServices_missed_bin_calendar.php?UPRN=3455121482",
         "wiki_command_url_override": "https://www.stoke.gov.uk/jadu/custom/webserviceLookUps/BarTecWebServices_missed_bin_calendar.php?UPRN=XXXXXXXXXX",

{uk_bin_collection-0.105.0 → uk_bin_collection-0.106.0}/uk_bin_collection/uk_bin_collection/councils/BarnsleyMBCouncil.py

@@ -1,4 +1,4 @@
-from typing import Dict, Any
+from typing import Dict, List, Any
 from bs4 import BeautifulSoup
 from dateutil.relativedelta import relativedelta
 import requests
@@ -11,6 +11,30 @@ from uk_bin_collection.uk_bin_collection.common import (
 from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
 
 
+def parse_bin_text(bin_type_str: str, bin_date_str: str) -> List[Dict[str, str]]:
+    """
+    Takes a raw bin and date string, parses the bin(s) and date, then returns
+    a list of bins with their date.
+    """
+
+    bins = []
+
+    if bin_date_str == "Today":
+        bin_date = datetime.today()
+    elif bin_date_str == "Tomorrow":
+        bin_date = datetime.today() + relativedelta(days=1)
+    else:
+        bin_date = datetime.strptime(bin_date_str, "%A, %B %d, %Y")
+
+    for bin_type in bin_type_str.split(", "):
+        bins.append({
+            "type": bin_type.strip() + " bin",
+            "collectionDate": bin_date.strftime(date_format)
+        })
+
+    return bins
+    
+
 class CouncilClass(AbstractGetBinDataClass):
     """
     Concrete classes have to implement all abstract operations of the
@@ -73,37 +97,29 @@ class CouncilClass(AbstractGetBinDataClass):
         bin_date_str = highlight_content.find(
             "em", {"class": "ui-bin-next-date"}
         ).text.strip()
-        bin_type = (
-            highlight_content.find("p", {"class": "ui-bin-next-type"}).text.strip()
-            + " bin"
-        )
+        bin_type_str = highlight_content.find(
+            "p", {"class": "ui-bin-next-type"}
+        ).text.strip()
 
-        if bin_date_str == "Today":
-            bin_date = datetime.today()
-        elif bin_date_str == "Tomorrow":
-            bin_date = datetime.today() + relativedelta(days=1)
-        else:
-            bin_date = datetime.strptime(bin_date_str, "%A, %B %d, %Y")
+        data["bins"].extend(parse_bin_text(bin_type_str, bin_date_str))
 
-        dict_data = {
-            "type": bin_type,
-            "collectionDate": bin_date.strftime(date_format),
-        }
-        data["bins"].append(dict_data)
+        # Hold bins we already got from next collection, to avoid re-adding
+        # from upcoming collections.
+        used_bins = set(bin["type"] for bin in data["bins"])
 
         # Upcoming collections
         upcoming_collections = results[1].find("tbody").find_all("tr")
         for row in upcoming_collections:
             columns = row.find_all("td")
             bin_date_str = columns[0].text.strip()
-            bin_types = columns[1].text.strip().split(", ")
-
-            for bin_type in bin_types:
-                bin_date = datetime.strptime(bin_date_str, "%A, %B %d, %Y")
-                dict_data = {
-                    "type": bin_type.strip() + " bin",
-                    "collectionDate": bin_date.strftime(date_format),
-                }
-                data["bins"].append(dict_data)
+            bin_type_str = columns[1].text.strip()
+
+            # Only add to bin list if not already present.
+            for bin in parse_bin_text(bin_type_str, bin_date_str):
+                if bin["type"] not in used_bins:
+                    data["bins"].append(bin)
+
+                    # Add to used bins, so future collections are not re-added.
+                    used_bins.add(bin["type"])
 
         return data

uk_bin_collection-0.106.0/uk_bin_collection/uk_bin_collection/councils/FifeCouncil.py

@@ -0,0 +1,68 @@
+from datetime import datetime
+
+import requests
+from bs4 import BeautifulSoup
+
+from uk_bin_collection.uk_bin_collection.common import *
+from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
+
+
+class CouncilClass(AbstractGetBinDataClass):
+    """
+    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_uprn = kwargs.get("uprn")
+        check_uprn(user_uprn)
+        bindata = {"bins": []}
+
+        API_URL = "https://www.fife.gov.uk/api/custom?action=powersuite_bin_calendar_collections&actionedby=bin_calendar&loadform=true&access=citizen&locale=en"
+        AUTH_URL = "https://www.fife.gov.uk/api/citizen?preview=false&locale=en"
+        AUTH_KEY = "Authorization"
+
+        r = requests.get(AUTH_URL)
+        r.raise_for_status()
+        auth_token = r.headers[AUTH_KEY]
+
+        post_data = {
+            "name": "bin_calendar",
+            "data": {
+                "uprn": user_uprn,
+            },
+            "email": "",
+            "caseid": "",
+            "xref": "",
+            "xref1": "",
+            "xref2": "",
+        }
+
+        headers = {
+            "referer": "https://www.fife.gov.uk/services/forms/bin-calendar",
+            "accept": "application/json",
+            "content-type": "application/json",
+            AUTH_KEY: auth_token,
+        }
+
+        r = requests.post(API_URL, data=json.dumps(post_data), headers=headers)
+        r.raise_for_status()
+
+        result = r.json()
+
+        for collection in result["data"]["tab_collections"]:
+            dict_data = {
+                "type": collection["colour"],
+                "collectionDate": datetime.strptime(
+                    collection["date"],
+                    "%A, %B %d, %Y",
+                ).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-0.106.0/uk_bin_collection/uk_bin_collection/councils/FlintshireCountyCouncil.py

@@ -0,0 +1,60 @@
+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://digital.flintshire.gov.uk/FCC_BinDay/Home/Details2/{user_uprn}"
+
+        # Make the GET request
+        response = requests.get(URI)
+
+        # Parse the HTML content
+        soup = BeautifulSoup(response.content, "html.parser")
+
+        # Adjust these tags and classes based on actual structure
+        # Example for finding collection dates and types
+        bin_collections = soup.find_all(
+            "div", class_="col-md-12 col-lg-12 col-sm-12 col-xs-12"
+        )  # Replace with actual class name
+
+        # Extracting and printing the schedule data
+        schedule = []
+        for collection in bin_collections:
+            dates = collection.find_all("div", class_="col-lg-2 col-md-2 col-sm-2")
+            bin_type = collection.find("div", class_="col-lg-3 col-md-3 col-sm-3")
+
+            if dates[0].text.strip() == "Date of Collection":
+                continue
+
+            bin_types = bin_type.text.strip().split(" / ")
+            date = dates[0].text.strip()
+
+            # Loop through the dates for each collection type
+            for bin_type in bin_types:
+
+                dict_data = {
+                    "type": bin_type,
+                    "collectionDate": 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-0.106.0/uk_bin_collection/uk_bin_collection/councils/MidlothianCouncil.py

@@ -0,0 +1,147 @@
+from urllib.parse import quote, urljoin
+
+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.
+    """
+
+    BASE_URL = "https://www.midlothian.gov.uk"
+    DIRECTORY_URL = f"{BASE_URL}/site/scripts/directory_search.php?directoryID=35&keywords={{}}&search=Search"
+    BIN_TYPES = {
+        "Next recycling collection": "Recycling",
+        "Next grey bin collection": "Grey Bin",
+        "Next brown bin collection": "Brown Bin",
+        "Next food bin collection": "Food Bin",
+    }
+
+    def parse_data(self, page: str, **kwargs) -> dict:
+
+        house_identifier = kwargs.get(
+            "paon", ""
+        ).strip()  # Could be house number or name
+        postcode = kwargs.get("postcode")
+
+        # Check if both house identifier and postcode are provided
+        if not house_identifier:
+            print("Error: House identifier (number or name) must be provided.")
+            return {"bins": []}
+
+        if not postcode:
+            print("Error: Postcode must be provided.")
+            return {"bins": []}
+
+        check_postcode(postcode)
+        check_paon(house_identifier)
+
+        data = {"bins": []}
+        search_url = self.DIRECTORY_URL.format(quote(postcode))
+
+        try:
+            search_results_html = requests.get(search_url)
+            search_results_html.raise_for_status()
+
+            soup = BeautifulSoup(search_results_html.text, "html.parser")
+            address_link = self._get_result_by_identifier(soup, house_identifier)
+
+            if address_link:
+                collections_url = urljoin(search_url, address_link["href"])
+                bin_collection_data = self._fetch_bin_collection_data(collections_url)
+
+                if bin_collection_data:
+                    data["bins"].extend(bin_collection_data)
+
+        except requests.RequestException as e:
+            print(f"Warning: Failed to fetch data from {search_url}. Error: {e}")
+
+        return data
+
+    def _get_result_by_identifier(self, soup, identifier: str) -> list:
+        """Extract the result link that matches the given house number or house name."""
+        try:
+            results_list = (
+                soup.find("article", class_="container")
+                .find("h2", text="Search results")
+                .find_next("ul", class_="item-list item-list__rich")
+            )
+
+            pattern = re.compile(re.escape(identifier.lower()) + r"[ ,]")
+
+            for item in results_list.find_all("li"):
+                address_link = item.find("a")
+                if address_link:
+                    link_text = address_link.text.strip().lower()
+                    if pattern.match(link_text):
+                        return address_link
+
+            print(f"Warning: No results found for identifier '{identifier}'.")
+            return None  # Return None if no match is found
+
+        except AttributeError as e:
+            print(f"Warning: Could not find the search results. Error: {e}")
+            return None  # Return None if no result found
+
+    def _fetch_bin_collection_data(self, url: str) -> list:
+        """Fetch and parse bin collection data from the given URL."""
+        try:
+            bin_collection_html = requests.get(url)
+            bin_collection_html.raise_for_status()
+
+            soup = BeautifulSoup(bin_collection_html.text, "html.parser")
+            bin_collections = soup.find("ul", class_="data-table")
+
+            if bin_collections:
+                return self._parse_bin_collection_items(
+                    bin_collections.find_all("li")[2:]  # Skip the first two items
+                )
+
+        except requests.RequestException as e:
+            print(
+                f"Warning: Failed to fetch bin collection data from {url}. Error: {e}"
+            )
+
+        return []  # Return an empty list on error
+
+    def _parse_bin_collection_items(self, bin_items: list) -> list:
+        """Parse bin collection items into a structured format."""
+        parsed_bins = []
+
+        for bin_item in bin_items:
+            bin_type = None
+            try:
+                if bin_item.h2 and bin_item.h2.text.strip() in self.BIN_TYPES:
+                    bin_type = self.BIN_TYPES[bin_item.h2.text.strip()]
+
+                bin_collection_date = None
+                if bin_item.div and bin_item.div.text.strip():
+                    try:
+                        bin_collection_date = datetime.strptime(
+                            bin_item.div.text.strip(), "%A %d/%m/%Y"
+                        ).strftime(date_format)
+                    except ValueError:
+                        print(
+                            f"Warning: Date parsing failed for {bin_item.div.text.strip()}."
+                        )
+
+                if bin_type and bin_collection_date:
+                    parsed_bins.append(
+                        {
+                            "type": bin_type,
+                            "collectionDate": bin_collection_date,
+                        }
+                    )
+                else:
+                    print(f"Warning: Missing data for bin item: {bin_item}")
+
+            except Exception as e:
+                print(f"Warning: An error occurred while parsing bin item. Error: {e}")
+
+        return parsed_bins

{uk_bin_collection-0.105.0 → uk_bin_collection-0.106.0}/uk_bin_collection/uk_bin_collection/councils/SouthwarkCouncil.py

@@ -19,7 +19,7 @@ class CouncilClass(AbstractGetBinDataClass):
         check_uprn(user_uprn)
         data = {"bins": []}
 
-        baseurl = "https://www.southwark.gov.uk/bins/lookup/"
+        baseurl = "https://services.southwark.gov.uk/bins/lookup/"
         url = baseurl + user_uprn
 
         headers = {
@@ -74,9 +74,13 @@ class CouncilClass(AbstractGetBinDataClass):
             data["bins"].append(dict_data)
 
         # Extract food waste collection information
-        food_section = soup.find("div", {"aria-labelledby": "organicsCollectionTitle"})
+        food_section = soup.find(
+            "div", {"aria-labelledby": "domesticFoodCollectionTitle"}
+        )
         if food_section:
-            food_title = food_section.find("p", {"id": "organicsCollectionTitle"}).text
+            food_title = food_section.find(
+                "p", {"id": "domesticFoodCollectionTitle"}
+            ).text
             food_next_collection = (
                 food_section.find(text=lambda text: "Next collection" in text)
                 .strip()

uk_bin_collection-0.106.0/uk_bin_collection/uk_bin_collection/councils/StocktonOnTeesCouncil.py

@@ -0,0 +1,159 @@
+import time
+
+from bs4 import BeautifulSoup
+from dateutil.relativedelta import relativedelta
+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:
+        driver = None
+        try:
+            data = {"bins": []}
+            collections = []
+            user_paon = kwargs.get("paon")
+            user_postcode = kwargs.get("postcode")
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+            check_paon(user_paon)
+            check_postcode(user_postcode)
+
+            # Create Selenium webdriver
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            driver.get("https://www.stockton.gov.uk/bin-collection-days")
+
+            # Wait for the postcode field to appear then populate it
+            inputElement_postcode = WebDriverWait(driver, 30).until(
+                EC.presence_of_element_located(
+                    (
+                        By.ID,
+                        "LOOKUPBINDATESBYADDRESSSKIPOUTOFREGION_ADDRESSLOOKUPPOSTCODE",
+                    )
+                )
+            )
+            inputElement_postcode.send_keys(user_postcode)
+
+            # Click search button
+            findAddress = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (
+                        By.ID,
+                        "LOOKUPBINDATESBYADDRESSSKIPOUTOFREGION_ADDRESSLOOKUPSEARCH",
+                    )
+                )
+            )
+            findAddress.click()
+
+            WebDriverWait(driver, 10).until(
+                EC.element_to_be_clickable(
+                    (
+                        By.XPATH,
+                        ""
+                        "//*[@id='LOOKUPBINDATESBYADDRESSSKIPOUTOFREGION_ADDRESSLOOKUPADDRESS']//option[contains(., '"
+                        + user_paon
+                        + "')]",
+                    )
+                )
+            ).click()
+
+            # Wait for the submit button to appear, then click it to get the collection dates
+            WebDriverWait(driver, 30).until(
+                EC.presence_of_element_located(
+                    (
+                        By.XPATH,
+                        '//*[@id="LOOKUPBINDATESBYADDRESSSKIPOUTOFREGION_COLLECTIONDETAILS2"]/div',
+                    )
+                )
+            )
+            time.sleep(2)
+
+            soup = BeautifulSoup(driver.page_source, features="html.parser")
+            soup.prettify()
+
+            rubbish_div = soup.find(
+                "p",
+                {
+                    "class": "myaccount-block__date myaccount-block__date--bin myaccount-block__date--waste"
+                },
+            )
+            rubbish_date = rubbish_div.text
+            if rubbish_date == "Today":
+                rubbish_date = datetime.now()
+            else:
+                rubbish_date = datetime.strptime(
+                    remove_ordinal_indicator_from_date_string(rubbish_date).strip(),
+                    "%a %d %B %Y",
+                ).replace(year=datetime.now().year)
+
+            recycling_div = soup.find(
+                "p",
+                {
+                    "class": "myaccount-block__date myaccount-block__date--bin myaccount-block__date--recycling"
+                },
+            )
+            recycling_date = recycling_div.text
+            if recycling_date == "Today":
+                recycling_date = datetime.now()
+            else:
+                recycling_date = datetime.strptime(
+                    remove_ordinal_indicator_from_date_string(recycling_date).strip(),
+                    "%a %d %B %Y",
+                )
+
+            garden_div = soup.find(
+                "div",
+                {
+                    "class": "myaccount-block__item myaccount-block__item--bin myaccount-block__item--garden"
+                },
+            )
+            garden_date = garden_div.find("strong")
+            if garden_date.text.strip() == "Date not available":
+                print("Garden waste unavailable")
+            else:
+                if garden_date.text == "Today":
+                    garden_date = datetime.now()
+                    collections.append(("Garden waste bin", garden_date))
+                else:
+                    garden_date = datetime.strptime(
+                        remove_ordinal_indicator_from_date_string(
+                            garden_date.text
+                        ).strip(),
+                        "%a %d %B %Y",
+                    )
+                    collections.append(("Garden waste bin", garden_date))
+
+            collections.append(("Rubbish bin", rubbish_date))
+            collections.append(("Recycling bin", recycling_date))
+
+            ordered_data = sorted(collections, key=lambda x: x[1])
+            for item in ordered_data:
+                dict_data = {
+                    "type": item[0].capitalize(),
+                    "collectionDate": item[1].strftime(date_format),
+                }
+                data["bins"].append(dict_data)
+
+            print()
+        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