uk_bin_collection 0.147.2__tar.gz → 0.148.0__tar.gz

{uk_bin_collection-0.147.2 → uk_bin_collection-0.148.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.147.2
+Version: 0.148.0
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.147.2 → uk_bin_collection-0.148.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.147.2"
+version = "0.148.0"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.147.2 → uk_bin_collection-0.148.0}/uk_bin_collection/compare_lad_codes.py

@@ -1,6 +1,7 @@
 import json
 import geopandas as gpd
 
+
 def extract_lad_codes(input_json_path):
     with open(input_json_path, "r") as f:
         data = json.load(f)
@@ -21,6 +22,7 @@ def extract_lad_codes(input_json_path):
 
     return lad_codes, lad_code_to_council_input
 
+
 def compare_with_geojson(input_lad_codes, geojson_path):
     gdf = gpd.read_file(geojson_path)
     geojson_lad_codes = set(gdf["LAD24CD"].dropna().unique())
@@ -37,17 +39,22 @@ def compare_with_geojson(input_lad_codes, geojson_path):
 
     return matching, missing_in_input, extra_in_input, geojson_lad_map
 
+
 # --- Run the comparison ---
 input_json_path = "uk_bin_collection/tests/input.json"
 geojson_path = "uk_bin_collection/Local_Authority_Boundaries.geojson"
 
 input_lad_codes, input_name_map = extract_lad_codes(input_json_path)
-matching, missing, extra, geojson_name_map = compare_with_geojson(input_lad_codes, geojson_path)
+matching, missing, extra, geojson_name_map = compare_with_geojson(
+    input_lad_codes, geojson_path
+)
 
 # --- Print results ---
 print(f"✅ Matching LAD24CDs ({len(matching)}):")
 for code in sorted(matching):
-    print(f"  {code} → input.json: {input_name_map.get(code)} | geojson: {geojson_name_map.get(code)}")
+    print(
+        f"  {code} → input.json: {input_name_map.get(code)} | geojson: {geojson_name_map.get(code)}"
+    )
 
 print(f"\n🟡 LADs in GeoJSON but missing in input.json ({len(missing)}):")
 for code in sorted(missing):

{uk_bin_collection-0.147.2 → uk_bin_collection-0.148.0}/uk_bin_collection/tests/generate_map_test_results.py

@@ -4,16 +4,18 @@ import xml.etree.ElementTree as ET
 from collections import defaultdict
 import re
 
+
 def extract_council_name(testname):
     """
     Extracts the council name from the test name.
     E.g. "test_scenario_outline[BarnetCouncil]" => "barnetcouncil"
     """
-    match = re.search(r'\[(.*?)\]', testname)
+    match = re.search(r"\[(.*?)\]", testname)
     if match:
         return match.group(1).strip().lower()
     return None
 
+
 def parse_junit_xml(path):
     tree = ET.parse(path)
     root = tree.getroot()
@@ -31,6 +33,7 @@ def parse_junit_xml(path):
 
     return results
 
+
 def main():
     if len(sys.argv) != 2:
         print("Usage: python generate_test_results.py <junit.xml path>")

{uk_bin_collection-0.147.2 → uk_bin_collection-0.148.0}/uk_bin_collection/tests/input.json

@@ -45,8 +45,10 @@
     },
     "ArgyllandButeCouncil": {
         "skip_get_url": true,
-        "uprn": "125061759",
-        "url": "https://www.argyll-bute.gov.uk",
+        "postcode": "PA286LJ",
+        "uprn": "000125011723",
+        "url": "https://www.argyll-bute.gov.uk/rubbish-and-recycling/household-waste/bin-collection",
+        "web_driver": "http://selenium:4444",
         "wiki_name": "Argyll and Bute Council",
         "wiki_note": "Pass the UPRN. You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search).",
         "LAD24CD": "S12000035"
@@ -1169,6 +1171,16 @@
         "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN.",
         "LAD24CD": "E07000132"
     },
+    "HorshamDistrictCouncil": {
+        "postcode": "RH12 1AA",
+        "LAD24CD": "E07000227",
+        "skip_get_url": true,
+        "uprn": "010013792717",
+        "url": "https://www.horsham.gov.uk/waste-recycling-and-bins/household-bin-collections/check-your-bin-collection-day",
+        "web_driver": "http://selenium:4444",
+        "wiki_name": "Horsham District Council",
+        "wiki_note": "Pass the UPRN. You can find it using [FindMyAddress](https://www.findmyaddress.co.uk/search). This parser requires a Selenium webdriver."
+    },
     "HullCityCouncil": {
         "LAD24CD": "E06000010",
         "skip_get_url": true,
@@ -2649,6 +2661,17 @@
         "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN.",
         "LAD24CD": "E07000237"
     },
+    "WrexhamCountyBoroughCouncil": {
+        "house_number": "1",
+        "postcode": "LL12 7RW",
+        "uprn": "200002944225",
+        "skip_get_url": true,
+        "url": "https://www.wrexham.gov.uk/service/when-are-my-bins-collected",
+        "web_driver": "http://selenium:4444",
+        "wiki_name": "Wrexham County Borough Council",
+        "wiki_note": "Provide your house number in the `house_number` parameter and postcode in the `postcode` parameter.",
+        "LAD24CD": "W06000006"
+    },
     "WychavonDistrictCouncil": {
         "postcode": "WR3 7RU",
         "skip_get_url": true,

uk_bin_collection-0.148.0/uk_bin_collection/uk_bin_collection/councils/ArgyllandButeCouncil.py

@@ -0,0 +1,138 @@
+from bs4 import BeautifulSoup
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.support.ui import Select, WebDriverWait
+from datetime import datetime
+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://www.argyll-bute.gov.uk/rubbish-and-recycling/household-waste/bin-collection"
+
+            user_uprn = kwargs.get("uprn")
+            user_postcode = kwargs.get("postcode")
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+            check_uprn(user_uprn)
+            check_postcode(user_postcode)
+            # Create Selenium webdriver
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            driver.get(page)
+
+            # Accept cookies
+            try:
+                accept_cookies = WebDriverWait(driver, timeout=10).until(
+                    EC.element_to_be_clickable(
+                        (By.XPATH, "//button[@id='ccc-recommended-settings']")
+                    )
+                )
+                accept_cookies.click()
+            except:
+                print(
+                    "Accept cookies banner not found or clickable within the specified time."
+                )
+                pass
+            # Wait for postcode entry box
+
+            postcode_input = WebDriverWait(driver, timeout=15).until(
+                EC.presence_of_element_located(
+                    (By.XPATH, "//input[@id='edit-postcode']")
+                )
+            )
+
+            postcode_input.send_keys(user_postcode)
+
+            search_btn = WebDriverWait(driver, timeout=15).until(
+                EC.presence_of_element_located((By.ID, "edit-submit"))
+            )
+            search_btn.click()
+
+            address_results = Select(
+                WebDriverWait(driver, timeout=15).until(
+                    EC.presence_of_element_located(
+                        (By.XPATH, "//select[@id='edit-address']")
+                    )
+                )
+            )
+
+            address_results.select_by_value(user_uprn)
+            submit_btn = WebDriverWait(driver, timeout=15).until(
+                EC.presence_of_element_located(
+                    (By.XPATH, "//input[@value='Search for my bin collection details']")
+                )
+            )
+            submit_btn.click()
+
+            results = WebDriverWait(driver, timeout=15).until(
+                EC.presence_of_element_located(
+                    (
+                        By.XPATH,
+                        "//th[contains(text(),'Collection date')]/ancestor::table",
+                    )
+                )
+            )
+
+            soup = BeautifulSoup(
+                results.get_attribute("innerHTML"), features="html.parser"
+            )
+
+            today = datetime.today()
+            current_year = today.year
+            current_month = today.month
+
+            bin_data = {"bins": []}
+
+            # Skip header
+            for row in soup.find_all("tr")[1:]:
+                cells = row.find_all("td")
+                if len(cells) < 2:
+                    continue
+
+                bin_type = cells[0].get_text(strip=True)
+                raw_date = cells[1].get_text(strip=True)
+
+                try:
+                    # Parse day and month first to determine year
+                    partial_date = datetime.strptime(raw_date, "%A %d %B")
+                    month = partial_date.month
+
+                    # Determine correct year based on current month
+                    year = current_year + 1 if month < current_month else current_year
+
+                    # Re-parse with the correct year
+                    full_date_str = f"{raw_date} {year}"
+                    parsed_date = datetime.strptime(full_date_str, "%A %d %B %Y")
+                    date_str = parsed_date.strftime(date_format)
+                except ValueError:
+                    continue
+
+                bin_data["bins"].append({"type": bin_type, "collectionDate": date_str})
+
+            # Sort by date
+            bin_data["bins"].sort(
+                key=lambda x: datetime.strptime(x["collectionDate"], date_format)
+            )
+
+        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 bin_data

uk_bin_collection-0.148.0/uk_bin_collection/uk_bin_collection/councils/HorshamDistrictCouncil.py

@@ -0,0 +1,123 @@
+from time import sleep
+
+from bs4 import BeautifulSoup
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.support.ui import Select, 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://www.horsham.gov.uk/waste-recycling-and-bins/household-bin-collections/check-your-bin-collection-day"
+
+            bin_data = {"bins": []}
+
+            user_uprn = kwargs.get("uprn")
+            user_postcode = kwargs.get("postcode")
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+            check_uprn(user_uprn)
+            check_postcode(user_postcode)
+            # Create Selenium webdriver
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            driver.get(page)
+
+            # Accept cookies
+            try:
+                accept_cookies = WebDriverWait(driver, timeout=10).until(
+                    EC.element_to_be_clickable(
+                        (By.XPATH, "//button[@id='ccc-notify-accept']")
+                    )
+                )
+                accept_cookies.click()
+            except:
+                print(
+                    "Accept cookies banner not found or clickable within the specified time."
+                )
+                pass
+            # Wait for postcode entry box
+
+            postcode_input = WebDriverWait(driver, timeout=15).until(
+                EC.presence_of_element_located(
+                    (By.XPATH, "//input[@value='Enter your postcode']")
+                )
+            )
+
+            postcode_input.send_keys(user_postcode)
+            search_btn = WebDriverWait(driver, timeout=15).until(
+                EC.presence_of_element_located((By.ID, "Submit1"))
+            )
+            search_btn.click()
+
+            address_results = Select(
+                WebDriverWait(driver, timeout=15).until(
+                    EC.presence_of_element_located(
+                        (
+                            By.XPATH,
+                            "//option[contains(text(),'Please select address...')]/parent::select",
+                        )
+                    )
+                )
+            )
+
+            address_results.select_by_value(user_uprn)
+
+            results = WebDriverWait(driver, timeout=15).until(
+                EC.presence_of_element_located(
+                    (
+                        By.XPATH,
+                        "//th[contains(text(),'COLLECTION TYPE')]/ancestor::table",
+                    )
+                )
+            )
+
+            soup = BeautifulSoup(
+                results.get_attribute("innerHTML"), features="html.parser"
+            )
+
+            # Skip the header, loop through each row in tbody
+            for row in soup.find_all("tbody")[0].find_all("tr"):
+                cells = row.find_all("td")
+                if len(cells) < 3:
+                    continue
+                date_str = cells[1].get_text(strip=True)
+                collection_type = cells[2].get_text(strip=True)
+
+                try:
+                    date = datetime.strptime(date_str, "%d/%m/%Y").strftime(date_format)
+                except ValueError:
+                    continue  # Skip if date is invalid
+
+                bin_data["bins"].append(
+                    {"type": collection_type, "collectionDate": date}
+                )
+
+            # Sort by date
+            bin_data["bins"].sort(
+                key=lambda x: datetime.strptime(x["collectionDate"], date_format)
+            )
+
+        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 bin_data

uk_bin_collection-0.148.0/uk_bin_collection/uk_bin_collection/councils/WrexhamCountyBoroughCouncil.py

@@ -0,0 +1,123 @@
+from time import sleep
+
+from bs4 import BeautifulSoup
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.support.ui import Select, 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://www.wrexham.gov.uk/service/when-are-my-bins-collected"
+
+            bin_data = {"bins": []}
+
+            user_uprn = kwargs.get("uprn")
+            user_postcode = kwargs.get("postcode")
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+            check_uprn(user_uprn)
+            check_postcode(user_postcode)
+            # Create Selenium webdriver
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            driver.get(page)
+
+            start_now_btn = WebDriverWait(driver, timeout=15).until(
+                EC.presence_of_element_located(
+                    (By.XPATH, "//a[contains(text(),'Start now')]")
+                )
+            )
+            start_now_btn.click()
+
+            continue_without_signup_btn = WebDriverWait(driver, timeout=15).until(
+                EC.presence_of_element_located(
+                    (
+                        By.XPATH,
+                        "//a[contains(text(),'or, continue without an account')]",
+                    )
+                )
+            )
+            continue_without_signup_btn.click()
+
+            iframe_presense = WebDriverWait(driver, 30).until(
+                EC.presence_of_element_located((By.ID, "fillform-frame-1"))
+            )
+
+            driver.switch_to.frame(iframe_presense)
+
+            inputElement_postcodesearch = WebDriverWait(driver, 30).until(
+                EC.element_to_be_clickable((By.ID, "LocationSearch"))
+            )
+
+            inputElement_postcodesearch.send_keys(user_postcode)
+
+            # Wait for the 'Select address' dropdown to be updated
+
+            # Wait for 'Searching for...' to be removed from page
+            WebDriverWait(driver, timeout=15).until(
+                EC.none_of(EC.presence_of_element_located((By.CLASS_NAME, "spinner")))
+            )
+
+            dropdown = WebDriverWait(driver, 30).until(
+                EC.element_to_be_clickable((By.ID, "ChooseAddress"))
+            )
+            # Create a 'Select' for it, then select the first address in the list
+            # (Index 0 is "Select...")
+            dropdownSelect = Select(dropdown)
+            dropdownSelect.select_by_value(str(user_uprn))
+
+            results_wait = WebDriverWait(driver, 30).until(
+                EC.presence_of_element_located(
+                    (By.XPATH, "//th[contains(text(),'Collection')]")
+                )
+            )
+
+            results = WebDriverWait(driver, 30).until(
+                EC.presence_of_element_located(
+                    (By.XPATH, "//table[@id='wcbc_collection_details']")
+                )
+            )
+
+            soup = BeautifulSoup(
+                results.get_attribute("innerHTML"), features="html.parser"
+            )
+
+            for row in soup.find_all("tr")[1:]:  # Skip the header row
+                date_cell, collection_cell = row.find_all("td")
+                date = datetime.strptime(date_cell.text.strip(), "%d/%m/%Y").strftime(
+                    date_format
+                )
+
+                for bin_item in collection_cell.find_all("li"):
+                    bin_type = bin_item.text.strip()
+                    bin_data["bins"].append({"type": bin_type, "collectionDate": date})
+
+            # Optional: sort by date
+            bin_data["bins"].sort(
+                key=lambda x: datetime.strptime(x["collectionDate"], date_format)
+            )
+
+        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 bin_data

uk_bin_collection-0.147.2/uk_bin_collection/uk_bin_collection/councils/ArgyllandButeCouncil.py

@@ -1,67 +0,0 @@
-import time
-
-import requests
-from bs4 import BeautifulSoup
-
-from uk_bin_collection.uk_bin_collection.common import *
-from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
-
-
-# import the wonderful Beautiful Soup and the URL grabber
-class CouncilClass(AbstractGetBinDataClass):
-    """
-    Concrete classes have to implement all abstract operations of the
-    base class. They can also override some operations with a default
-    implementation.
-    """
-
-    def parse_data(self, page: str, **kwargs) -> dict:
-
-        user_uprn = kwargs.get("uprn")
-        check_uprn(user_uprn)
-        user_uprn = user_uprn.zfill(12)
-        bindata = {"bins": []}
-
-        URI = "https://www.argyll-bute.gov.uk/rubbish-and-recycling/household-waste/bin-collection"
-
-        data = {"addressSelect": user_uprn}
-
-        s = requests.session()
-        r = s.post(URI, data=data)
-        r.raise_for_status()
-
-        soup = BeautifulSoup(r.content, features="html.parser")
-        soup.prettify()
-
-        # Find the table and extract the rows with bin schedule information
-        table = soup.find("table", class_="table table-bordered")
-        rows = table.find_all("tr")[1:]  # Skip the header row
-
-        current_year = datetime.now().year
-        # Loop through each row and extract the bin type and collection date
-        for row in rows:
-            cells = row.find_all("td")
-            bin_type = cells[0].get_text(strip=True)
-            collection_date = cells[1].get_text(strip=True)
-
-            collection_date = datetime.strptime(
-                collection_date,
-                "%A %d %B",
-            )
-
-            if collection_date.month == 1:
-                collection_date = collection_date.replace(year=current_year + 1)
-            else:
-                collection_date = collection_date.replace(year=current_year)
-
-            dict_data = {
-                "type": bin_type,
-                "collectionDate": collection_date.strftime(date_format),
-            }
-            bindata["bins"].append(dict_data)
-
-        bindata["bins"].sort(
-            key=lambda x: datetime.strptime(x.get("collectionDate"), date_format)
-        )
-
-        return bindata