uk_bin_collection 0.144.2__py3-none-any.whl → 0.144.4__py3-none-any.whl

uk_bin_collection/uk_bin_collection/councils/BristolCityCouncil.py

@@ -126,11 +126,14 @@ class CouncilClass(AbstractGetBinDataClass):
 
         collections = []
         for bin in collection_data:
+            if not bin["collection"]:
+                continue  # Skip if there are no collection dates
+
             bin_type = bin["containerName"]
             next_collection = datetime.strptime(
                 bin["collection"][0]["nextCollectionDate"], "%Y-%m-%dT%H:%M:%S"
             ).strftime(date_format)
-            # Could work out next date using the roundDescription and the is_holiday function in common.py
+
             collections.append((bin_type, next_collection))
 
         ordered_data = sorted(collections, key=lambda x: x[1])

uk_bin_collection/uk_bin_collection/councils/Hillingdon.py

@@ -0,0 +1,273 @@
+import json
+from datetime import datetime, timedelta
+from typing import Any, Dict
+
+from bs4 import BeautifulSoup
+from dateutil.parser import parse
+from selenium.common.exceptions import (
+    NoSuchElementException,
+    StaleElementReferenceException,
+    TimeoutException,
+)
+from selenium.webdriver.common.by import By
+from selenium.webdriver.common.keys import Keys
+from selenium.webdriver.remote.webdriver import WebDriver
+from selenium.webdriver.support import expected_conditions as EC
+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
+
+# Dictionary mapping day names to their weekday numbers (Monday=0, Sunday=6)
+DAYS_OF_WEEK = {
+    "Monday": 0,
+    "Tuesday": 1,
+    "Wednesday": 2,
+    "Thursday": 3,
+    "Friday": 4,
+    "Saturday": 5,
+    "Sunday": 6,
+}
+
+
+# This function checks for bank holiday collection changes,
+# but the page seems manually written so might break easily
+def get_bank_holiday_changes(driver: WebDriver) -> Dict[str, str]:
+    """Fetch and parse bank holiday collection changes from the council website."""
+    bank_holiday_url = "https://www.hillingdon.gov.uk/bank-holiday-collections"
+    driver.get(bank_holiday_url)
+
+    # Wait for page to load
+    wait = WebDriverWait(driver, 10)
+    wait.until(EC.presence_of_element_located((By.TAG_NAME, "table")))
+
+    # Parse the page
+    soup = BeautifulSoup(driver.page_source, features="html.parser")
+    changes: Dict[str, str] = {}
+
+    # Find all tables with collection changes
+    tables = soup.find_all("table")
+    for table in tables:
+        # Check if this is a collection changes table
+        headers = [th.text.strip() for th in table.find_all("th")]
+        if "Normal collection day" in headers and "Revised collection day" in headers:
+            # Process each row
+            for row in table.find_all("tr")[1:]:  # Skip header row
+                cols = row.find_all("td")
+                if len(cols) >= 2:
+                    normal_date = cols[0].text.strip()
+                    revised_date = cols[1].text.strip()
+
+                    # Parse dates
+                    try:
+                        normal_date = parse(normal_date, fuzzy=True).strftime(
+                            "%d/%m/%Y"
+                        )
+                        revised_date = parse(revised_date, fuzzy=True).strftime(
+                            "%d/%m/%Y"
+                        )
+                        changes[normal_date] = revised_date
+                    except Exception as e:
+                        print(f"Error parsing dates: {e}")
+                        continue
+
+    return changes
+
+
+class CouncilClass(AbstractGetBinDataClass):
+    def parse_data(self, page: str, **kwargs: Any) -> Dict[str, Any]:
+        driver = None
+        try:
+            data: Dict[str, Any] = {"bins": []}
+            user_paon = kwargs.get("paon")
+            user_postcode = kwargs.get("postcode")
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+            url = kwargs.get("url")
+
+            check_paon(user_paon)
+            check_postcode(user_postcode)
+
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            driver.get(url)
+
+            # Handle cookie banner if present
+            wait = WebDriverWait(driver, 30)
+            try:
+                cookie_button = wait.until(
+                    EC.element_to_be_clickable(
+                        (
+                            By.CLASS_NAME,
+                            "btn btn--cookiemessage btn--cancel btn--contrast",
+                        )
+                    )
+                )
+                cookie_button.click()
+            except (TimeoutException, NoSuchElementException):
+                pass
+
+            # Enter postcode
+            post_code_input = wait.until(
+                EC.element_to_be_clickable(
+                    (
+                        By.ID,
+                        "WASTECOLLECTIONDAYLOOKUPINCLUDEGARDEN_ADDRESSLOOKUPPOSTCODE",
+                    )
+                )
+            )
+            post_code_input.clear()
+            post_code_input.send_keys(user_postcode)
+            post_code_input.send_keys(Keys.TAB + Keys.ENTER)
+
+            # Wait for address options to populate
+            try:
+                # Wait for the address dropdown to be present and clickable
+                address_select = wait.until(
+                    EC.presence_of_element_located(
+                        (
+                            By.ID,
+                            "WASTECOLLECTIONDAYLOOKUPINCLUDEGARDEN_ADDRESSLOOKUPADDRESS",
+                        )
+                    )
+                )
+
+                # Wait for actual address options to appear
+                wait.until(
+                    lambda driver: len(driver.find_elements(By.TAG_NAME, "option")) > 1
+                )
+
+                # Find and select address
+                options = address_select.find_elements(By.TAG_NAME, "option")[
+                    1:
+                ]  # Skip placeholder
+                if not options:
+                    raise Exception(f"No addresses found for postcode: {user_postcode}")
+
+                # Normalize user input by keeping only alphanumeric characters
+                normalized_user_input = "".join(
+                    c for c in user_paon if c.isalnum()
+                ).lower()
+
+                # Find matching address in dropdown
+                for option in options:
+                    # Normalize option text by keeping only alphanumeric characters
+                    normalized_option = "".join(
+                        c for c in option.text if c.isalnum()
+                    ).lower()
+                    if normalized_user_input in normalized_option:
+                        option.click()
+                        break
+            except TimeoutException:
+                raise Exception("Timeout waiting for address options to populate")
+
+            # Wait for collection table and day text
+            wait.until(
+                EC.presence_of_element_located(
+                    (By.ID, "WASTECOLLECTIONDAYLOOKUPINCLUDEGARDEN_COLLECTIONTABLE")
+                )
+            )
+
+            # Wait for collection day text to be fully populated
+            wait.until(
+                lambda driver: len(
+                    driver.find_element(
+                        By.ID, "WASTECOLLECTIONDAYLOOKUPINCLUDEGARDEN_COLLECTIONTABLE"
+                    )
+                    .find_elements(By.TAG_NAME, "tr")[2]
+                    .find_elements(By.TAG_NAME, "td")[1]
+                    .text.strip()
+                    .split()
+                )
+                > 1
+            )
+
+            # Parse the table
+            soup = BeautifulSoup(driver.page_source, features="html.parser")
+            table = soup.find(
+                "div", id="WASTECOLLECTIONDAYLOOKUPINCLUDEGARDEN_COLLECTIONTABLE"
+            ).find("table")
+
+            # Get collection day
+            collection_day_text = table.find_all("tr")[2].find_all("td")[1].text.strip()
+            day_of_week = next(
+                (
+                    day
+                    for day in DAYS_OF_WEEK
+                    if day.lower() in collection_day_text.lower()
+                ),
+                None,
+            )
+            if not day_of_week:
+                raise Exception(
+                    f"Could not determine collection day from text: '{collection_day_text}'"
+                )
+
+            # Calculate next collection date
+            today = datetime.now()
+            days_ahead = (DAYS_OF_WEEK[day_of_week] - today.weekday()) % 7
+            if days_ahead == 0:  # If today is collection day, get next week's date
+                days_ahead = 7
+            next_collection = today + timedelta(days=days_ahead)
+
+            # Add collection dates for each bin type
+            bin_types = ["General Waste", "Recycling", "Food Waste"]
+            for bin_type in bin_types:
+                data["bins"].append(
+                    {
+                        "type": bin_type,
+                        "collectionDate": next_collection.strftime("%d/%m/%Y"),
+                    }
+                )
+
+            # Process collection details
+            bin_rows = soup.select("div.bin--row:not(:first-child)")
+            for row in bin_rows:
+                try:
+                    bin_type = row.select_one("div.col-md-3").text.strip()
+                    collection_dates_div = row.select("div.col-md-3")[1]
+                    next_collection_text = "".join(
+                        collection_dates_div.find_all(text=True, recursive=False)
+                    ).strip()
+                    cleaned_date_text = remove_ordinal_indicator_from_date_string(
+                        next_collection_text
+                    )
+                    parsed_date = parse(cleaned_date_text, fuzzy=True)
+                    bin_date = parsed_date.strftime("%d/%m/%Y")
+
+                    if bin_type and bin_date:
+                        data["bins"].append(
+                            {
+                                "type": bin_type,
+                                "collectionDate": bin_date,
+                            }
+                        )
+                except Exception as e:
+                    print(f"Error processing item: {e}")
+                    continue
+
+            # Get bank holiday changes
+            print("\nChecking for bank holiday collection changes...")
+            bank_holiday_changes = get_bank_holiday_changes(driver)
+
+            # Apply any bank holiday changes to collection dates
+            for bin_data in data["bins"]:
+                original_date = bin_data["collectionDate"]
+                if original_date in bank_holiday_changes:
+                    new_date = bank_holiday_changes[original_date]
+                    print(
+                        f"Bank holiday change: {bin_data['type']} collection moved from {original_date} to {new_date}"
+                    )
+                    bin_data["collectionDate"] = new_date
+
+        except Exception as e:
+            print(f"An error occurred: {e}")
+            raise
+        finally:
+            if driver:
+                driver.quit()
+
+        # Print the final data dictionary for debugging
+        print("\nFinal data dictionary:")
+        print(json.dumps(data, indent=2))
+
+        return data

{uk_bin_collection-0.144.2.dist-info → uk_bin_collection-0.144.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.144.2
+Version: 0.144.4
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.144.2.dist-info → uk_bin_collection-0.144.4.dist-info}/RECORD

@@ -1,9 +1,11 @@
+uk_bin_collection/Local_Authority_Boundaries.geojson,sha256=_j-hUiL0--t2ewd_s29-j7_AKRlhagRMmOhXyco-B6I,1175922
 uk_bin_collection/README.rst,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+uk_bin_collection/map.html,sha256=bBqCQkT4DjBeAL8hrjW5n8UHNxVUqc6XScpGMF60Vzw,3979
 uk_bin_collection/tests/check_selenium_url_in_input.json.py,sha256=Iecdja0I3XIiY76qmwPgcBqNgYv7n1-b5mg85JpMjg8,7817
 uk_bin_collection/tests/council_feature_input_parity.py,sha256=DO6Mk4ImYgM5ZCZ-cutwz5RoYYWZRLYx2tr6zIs_9Rc,3843
 uk_bin_collection/tests/features/environment.py,sha256=VQZjJdJI_kZn08M0j5cUgvKT4k3iTw8icJge1DGOkoA,127
 uk_bin_collection/tests/features/validate_council_outputs.feature,sha256=SJK-Vc737hrf03tssxxbeg_JIvAH-ddB8f6gU1LTbuQ,251
-uk_bin_collection/tests/input.json,sha256=khL_z76OZZqmFtagerGv_djRNUYZC5iGAaLNTvttV2o,122435
+uk_bin_collection/tests/input.json,sha256=fU6qt6mRnMu08OcFwdWhYoRbUImiqIUPE8RAYuEQsRA,132316
 uk_bin_collection/tests/output.schema,sha256=ZwKQBwYyTDEM4G2hJwfLUVM-5v1vKRvRK9W9SS1sd18,1086
 uk_bin_collection/tests/step_defs/step_helpers/file_handler.py,sha256=Ygzi4V0S1MIHqbdstUlIqtRIwnynvhu4UtpweJ6-5N8,1474
 uk_bin_collection/tests/step_defs/test_validate_council.py,sha256=VZ0a81sioJULD7syAYHjvK_-nT_Rd36tUyzPetSA0gk,3475
@@ -50,7 +52,7 @@ uk_bin_collection/uk_bin_collection/councils/BraintreeDistrictCouncil.py,sha256=
 uk_bin_collection/uk_bin_collection/councils/BrecklandCouncil.py,sha256=PX6A_pDvaN109aSNWmEhm88GFKfkClIkmbwGURWvsks,1744
 uk_bin_collection/uk_bin_collection/councils/BrentCouncil.py,sha256=ucwokxvASYi_KiOYSOVdaGfC1kfUbII0r6Zl2NE1hnU,4208
 uk_bin_collection/uk_bin_collection/councils/BrightonandHoveCityCouncil.py,sha256=k6qt4cds-Ejd97Z-__pw2BYvGVbFdc9SUfF73PPrTNA,5823
-uk_bin_collection/uk_bin_collection/councils/BristolCityCouncil.py,sha256=kJmmDJz_kQ45DHmG7ocrUpNJonEn0kuXYEDQyZaf9ks,5576
+uk_bin_collection/uk_bin_collection/councils/BristolCityCouncil.py,sha256=nQeRBKrDcZE2m_EzjUBr9dJ5tcUdGcUuA5FcnLkbLr4,5575
 uk_bin_collection/uk_bin_collection/councils/BroadlandDistrictCouncil.py,sha256=aelqhh503dx6O2EEmC3AT5tnY39Dc53qcouH8T-mek8,7613
 uk_bin_collection/uk_bin_collection/councils/BromleyBoroughCouncil.py,sha256=dii85JLmYU1uMidCEsWVo3stTcq_QqyC65DxG8u1UmE,4302
 uk_bin_collection/uk_bin_collection/councils/BromsgroveDistrictCouncil.py,sha256=PUfxP8j5Oh9wFHkdjbrJzQli9UzMHZzwrZ2hkThrvhI,1781
@@ -146,8 +148,8 @@ uk_bin_collection/uk_bin_collection/councils/HerefordshireCouncil.py,sha256=JpQh
 uk_bin_collection/uk_bin_collection/councils/HertsmereBoroughCouncil.py,sha256=ZbSsmqHStd2JtTMAq1Bhcvsj1BYp6ijELyOjZFX2GSw,6435
 uk_bin_collection/uk_bin_collection/councils/HighPeakCouncil.py,sha256=x7dfy8mdt2iGl8qJxHb-uBh4u0knmi9MJ6irOJw9WYA,4805
 uk_bin_collection/uk_bin_collection/councils/HighlandCouncil.py,sha256=GNxDU65QuZHV5va2IrKtcJ6TQoDdwmV03JvkVqOauP4,3291
+uk_bin_collection/uk_bin_collection/councils/Hillingdon.py,sha256=R1enDv5gjwCUT3HKgj8C87xWrwvrutAN6XLu5P7tef8,10532
 uk_bin_collection/uk_bin_collection/councils/HinckleyandBosworthBoroughCouncil.py,sha256=51vXTKrstfJhb7cLCcrsvA9qKCsptyNMZvy7ML9DasM,2344
-uk_bin_collection/uk_bin_collection/councils/HounslowCouncil.py,sha256=LXhJ47rujx7k3naz0tFiTT1l5k6gAYcVdekJN1t_HLY,4564
 uk_bin_collection/uk_bin_collection/councils/HullCityCouncil.py,sha256=UHcesBoctFVcXDYuwfag43KbcJcopkEDzJ-54NxtK0Q,1851
 uk_bin_collection/uk_bin_collection/councils/HuntingdonDistrictCouncil.py,sha256=dGyhhG6HRjQ2SPeiRwUPTGlk9dPIslagV2k0GjEOn1s,1587
 uk_bin_collection/uk_bin_collection/councils/IpswichBoroughCouncil.py,sha256=57lmDl_FprG68gUhKQYpOa1M2pudyb1utfoMhUXNwzs,2802
@@ -330,8 +332,8 @@ uk_bin_collection/uk_bin_collection/councils/YorkCouncil.py,sha256=I2kBYMlsD4bId
 uk_bin_collection/uk_bin_collection/councils/council_class_template/councilclasstemplate.py,sha256=EQWRhZ2pEejlvm0fPyOTsOHKvUZmPnxEYO_OWRGKTjs,1158
 uk_bin_collection/uk_bin_collection/create_new_council.py,sha256=m-IhmWmeWQlFsTZC4OxuFvtw5ZtB8EAJHxJTH4O59lQ,1536
 uk_bin_collection/uk_bin_collection/get_bin_data.py,sha256=YvmHfZqanwrJ8ToGch34x-L-7yPe31nB_x77_Mgl_vo,4545
-uk_bin_collection-0.144.2.dist-info/LICENSE,sha256=vABBUOzcrgfaTKpzeo-si9YVEun6juDkndqA8RKdKGs,1071
-uk_bin_collection-0.144.2.dist-info/METADATA,sha256=h2gau2rSpNnurR8hcPU1G1O4c69ZM0K3vMNL2tn85PM,19858
-uk_bin_collection-0.144.2.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-uk_bin_collection-0.144.2.dist-info/entry_points.txt,sha256=36WCSGMWSc916S3Hi1ZkazzDKHaJ6CD-4fCEFm5MIao,90
-uk_bin_collection-0.144.2.dist-info/RECORD,,
+uk_bin_collection-0.144.4.dist-info/LICENSE,sha256=vABBUOzcrgfaTKpzeo-si9YVEun6juDkndqA8RKdKGs,1071
+uk_bin_collection-0.144.4.dist-info/METADATA,sha256=C4p4EDGWkZ2ZkKT4U_iTeb7BH5tO15Mtfcqpo4LiHG8,19858
+uk_bin_collection-0.144.4.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+uk_bin_collection-0.144.4.dist-info/entry_points.txt,sha256=36WCSGMWSc916S3Hi1ZkazzDKHaJ6CD-4fCEFm5MIao,90
+uk_bin_collection-0.144.4.dist-info/RECORD,,

uk_bin_collection/uk_bin_collection/councils/HounslowCouncil.py

@@ -1,122 +0,0 @@
-import time
-from datetime import datetime
-
-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
-from selenium.webdriver.support.wait import WebDriverWait
-from selenium.webdriver.common.keys import Keys
-
-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_date(self, date_str):
-        date_formats = [
-            "This %A - %d %b %Y",  # Changed %B to %b to accommodate abbreviated month names
-            "Next %A - %d %b %Y",  # Same change here
-            "%A %d %b %Y",  # And here
-        ]
-        for format in date_formats:
-            try:
-                return datetime.strptime(date_str, format).strftime("%d/%m/%Y")
-            except ValueError:
-                continue
-        raise ValueError(f"Date format not recognized: {date_str}")
-
-    def parse_data(self, page: str, **kwargs) -> dict:
-        driver = None
-        try:
-            # Make a BS4 object
-
-            page = "https://www.hounslow.gov.uk/info/20272/recycling_and_waste_collection_day_finder"
-
-            user_postcode = kwargs.get("postcode")
-            user_uprn = kwargs.get("uprn")
-            user_paon = kwargs.get("paon")
-            web_driver = kwargs.get("web_driver")
-            headless = kwargs.get("headless")
-
-            driver = create_webdriver(web_driver, headless, None, __name__)
-            driver.get(page)
-
-            wait = WebDriverWait(driver, 60)
-
-            inputElement_postcodesearch = wait.until(
-                EC.element_to_be_clickable((By.ID, "Postcode"))
-            )
-
-            inputElement_postcodesearch.send_keys(user_postcode)
-
-            inputElement_postcodesearch_btn = wait.until(
-                EC.element_to_be_clickable((By.ID, "findAddress"))
-            )
-            inputElement_postcodesearch_btn.click()
-
-            inputElement_select_address = wait.until(
-                EC.element_to_be_clickable((By.ID, "UPRN"))
-            )
-
-            select_element = wait.until(
-                EC.visibility_of_element_located((By.ID, "UPRN"))
-            )  # Adjust this ID to your element's ID
-
-            # Create a Select object
-            select = Select(select_element)
-
-            # Fetch all options
-            options = select.options
-
-            # Loop through options to find the one that starts with the UPRN
-            for option in options:
-                if option.get_attribute("value").startswith(f"{user_uprn}|"):
-                    option.click()  # Select the matching option
-                    break
-
-            results = wait.until(
-                EC.element_to_be_clickable((By.CLASS_NAME, "bin_day_main_wrapper"))
-            )
-
-            soup = BeautifulSoup(driver.page_source, features="html.parser")
-            soup.prettify()
-
-            # Find all headers which include collection dates
-            collection_headers = soup.find_all("h4")
-            bins_data = []
-
-            # Process each collection date and corresponding bins
-            for header in collection_headers:
-                date_text = header.get_text(strip=True)
-                collection_date = self.parse_date(date_text)
-
-                # Get next sibling which should be the list of bins
-                bin_list = header.find_next_sibling("ul")
-                if bin_list:
-                    for item in bin_list.find_all("li", class_="list-group-item"):
-                        bin_type = item.get_text(strip=True)
-                        bins_data.append(
-                            {"type": bin_type, "collectionDate": collection_date}
-                        )
-
-            # Construct the final JSON object
-            json_data = {"bins": bins_data}
-
-        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 json_data