uk_bin_collection 0.150.1__tar.gz → 0.151.0__tar.gz

{uk_bin_collection-0.150.1 → uk_bin_collection-0.151.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.150.1
+Version: 0.151.0
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.150.1 → uk_bin_collection-0.151.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.150.1"
+version = "0.151.0"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.150.1 → uk_bin_collection-0.151.0}/uk_bin_collection/tests/input.json

@@ -1935,6 +1935,7 @@
         "skip_get_url": true,
         "uprn": "100070182634",
         "url": "https://www.rugby.gov.uk/check-your-next-bin-day",
+        "web_driver": "http://selenium:4444",
         "wiki_name": "Rugby",
         "wiki_note": "Provide your UPRN and postcode. You can find your UPRN using [FindMyAddress](https://www.findmyaddress.co.uk/search).",
         "LAD24CD": "E07000220"

{uk_bin_collection-0.150.1 → uk_bin_collection-0.151.0}/uk_bin_collection/uk_bin_collection/councils/ArgyllandButeCouncil.py

@@ -8,8 +8,6 @@ from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataC
 
 
 # import the wonderful Beautiful Soup and the URL grabber
-
-
 class CouncilClass(AbstractGetBinDataClass):
     """
     Concrete classes have to implement all abstract operations of the

{uk_bin_collection-0.150.1 → uk_bin_collection-0.151.0}/uk_bin_collection/uk_bin_collection/councils/BrentCouncil.py

@@ -74,42 +74,56 @@ class CouncilClass(AbstractGetBinDataClass):
                     )
 
                     if service_details:
-
-                        # Extract next collection date
+                        # Extract next collection date only
                         next_collection_row = service_details.find(
                             "dt", string="Next collection"
                         )
-                        next_collection = (
-                            next_collection_row.find_next_sibling("dd").get_text(
-                                strip=True
-                            )
-                            if next_collection_row
-                            else "Unknown"
-                        )
-
-                        # Parse dates into standard dd/mm/yyyy format
-                        next_collection_date = datetime.strptime(
-                            remove_ordinal_indicator_from_date_string(next_collection),
-                            "%A, %d %B",
-                        )
-
-                        if (datetime.now().month == 12) and (
-                            next_collection.month == 1
-                        ):
-                            next_collection_date = next_collection_date.replace(
-                                year=next_year
+                        if next_collection_row:
+                            next_collection = next_collection_row.find_next_sibling(
+                                "dd"
+                            ).get_text(strip=True)
+
+                            # Remove the adjusted collection time message
+                            if (
+                                "(this collection has been adjusted from its usual time)"
+                                in next_collection
+                            ):
+                                next_collection = next_collection.replace(
+                                    "(this collection has been adjusted from its usual time)",
+                                    "",
+                                ).strip()
+
+                            # Parse date from format like "Wednesday, 7th May"
+                            next_collection = remove_ordinal_indicator_from_date_string(
+                                next_collection
                             )
-                        else:
-                            next_collection_date = next_collection_date.replace(
-                                year=current_year
-                            )
-
-                        dict_data = {
-                            "type": collection_type.strip(),
-                            "collectionDate": next_collection_date.strftime(
-                                date_format
-                            ),
-                        }
-                        data["bins"].append(dict_data)
+                            try:
+                                next_collection_date = datetime.strptime(
+                                    next_collection, "%A, %d %B"
+                                )
+
+                                # Handle year rollover
+                                if (
+                                    datetime.now().month == 12
+                                    and next_collection_date.month == 1
+                                ):
+                                    next_collection_date = next_collection_date.replace(
+                                        year=next_year
+                                    )
+                                else:
+                                    next_collection_date = next_collection_date.replace(
+                                        year=current_year
+                                    )
+
+                                dict_data = {
+                                    "type": collection_type.strip(),
+                                    "collectionDate": next_collection_date.strftime(
+                                        date_format
+                                    ),
+                                }
+                                data["bins"].append(dict_data)
+                                print(dict_data)
+                            except ValueError as e:
+                                print(f"Error parsing date {next_collection}: {e}")
 
         return data

uk_bin_collection-0.151.0/uk_bin_collection/uk_bin_collection/councils/MaidstoneBoroughCouncil.py

@@ -0,0 +1,115 @@
+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 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://my.maidstone.gov.uk/service/Find-your-bin-day"
+            bin_data = {"bins": []}
+            user_paon = kwargs.get("paon")
+            user_postcode = kwargs.get("postcode")
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+            check_postcode(user_postcode)
+            
+            # Create Selenium webdriver
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            driver.get(page)
+
+            iframe_presense = WebDriverWait(driver, 30).until(
+                EC.presence_of_element_located((By.ID, "fillform-frame-1"))
+            )
+            driver.switch_to.frame(iframe_presense)
+
+            wait = WebDriverWait(driver, 60)
+            
+            # Postal code input
+            inputElement_postcodesearch = wait.until(
+                EC.element_to_be_clickable((By.NAME, "postcode"))
+            )
+            inputElement_postcodesearch.send_keys(user_postcode)
+            
+            # Wait for the 'Select address' dropdown to be updated
+            dropdown_select = wait.until(
+                EC.presence_of_element_located((By.XPATH, "//span[contains(text(), 'Select...')]"))
+            )
+            dropdown_select.click()
+            
+            dropdown = wait.until(
+                EC.element_to_be_clickable((By.XPATH, f"//div[contains(text(), ' {user_paon}')]"))
+            )
+            dropdown.click()
+
+            # Wait for 'Searching for...' to be added to page
+            WebDriverWait(driver, timeout=15).until(
+                EC.text_to_be_present_in_element(
+                    (By.CSS_SELECTOR, "span[data-name=html1]"), "Searching"
+                )
+            )
+
+            # Wait for 'Searching for...' to be removed from page
+            WebDriverWait(driver, timeout=15).until(
+                EC.none_of(
+                    EC.text_to_be_present_in_element(
+                        (By.CSS_SELECTOR, "span[data-name=html1]"), "Searching"
+                    )
+                )
+            )
+
+            # Even then it can still be adding data to the page...
+            time.sleep(5)
+
+            soup = BeautifulSoup(driver.page_source, features="html.parser")
+
+            # This is ugly but there is literally no consistency to the HTML
+            def is_a_collection_date(t):
+                return any("Next collection" in c for c in t.children)
+
+            for next_collection in soup.find_all(is_a_collection_date):
+                bin_info = list(
+                    next_collection.parent.select_one("div:nth-child(1)").children
+                )
+                if not bin_info:
+                    continue
+                bin = bin_info[0].get_text()
+                date = next_collection.select_one("strong").get_text(strip=True)
+                bin_date = datetime.strptime(date, "%d %b %Y")
+                dict_data = {
+                    "type": bin,
+                    "collectionDate": bin_date.strftime(date_format),
+                }
+                bin_data["bins"].append(dict_data)
+
+            bin_data["bins"].sort(
+                key=lambda x: datetime.strptime(x.get("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-0.151.0/uk_bin_collection/uk_bin_collection/councils/RugbyBoroughCouncil.py

@@ -0,0 +1,146 @@
+import time
+
+from bs4 import BeautifulSoup
+from selenium.webdriver.common.by import By
+from selenium.webdriver.common.keys import Keys
+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:
+            user_postcode = kwargs.get("postcode")
+            if not user_postcode:
+                raise ValueError("No postcode provided.")
+            check_postcode(user_postcode)
+
+            user_uprn = kwargs.get("uprn")
+            check_uprn(user_uprn)
+
+            headless = kwargs.get("headless")
+            web_driver = kwargs.get("web_driver")
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            page = "https://www.rugby.gov.uk/check-your-next-bin-day"
+
+            driver.get(page)
+
+            wait = WebDriverWait(driver, 60)
+            accept_cookies_button = wait.until(
+                EC.element_to_be_clickable(
+                    (
+                        By.ID,
+                        "ccc-recommended-settings",
+                    )
+                )
+            )
+            accept_cookies_button.click()
+
+            postcode_input = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (
+                        By.XPATH,
+                        '//*[@id="_com_placecube_digitalplace_local_waste_portlet_CollectionDayFinderPortlet_postcode"]',
+                    )
+                )
+            )
+            postcode_input.send_keys(user_postcode + Keys.TAB + Keys.ENTER)
+
+            time.sleep(5)
+            # Wait for address box to be visible
+            select_address_input = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (
+                        By.ID,
+                        "_com_placecube_digitalplace_local_waste_portlet_CollectionDayFinderPortlet_uprn",
+                    )
+                )
+            )
+
+            # Select address based
+            select = Select(select_address_input)
+            for option in select.options:
+                if option.get_attribute("value") == str(user_uprn):
+                    select.select_by_value(str(user_uprn))
+                    break
+            else:
+                raise ValueError(f"UPRN {user_uprn} not found in address options")
+
+            select_address_input.send_keys(Keys.TAB + Keys.ENTER)
+
+            # Wait for the specified table to be present
+            target_table = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (
+                        By.XPATH,
+                        '//*[@id="portlet_com_placecube_digitalplace_local_waste_portlet_CollectionDayFinderPortlet"]/div/div/div/div/table',
+                    )
+                )
+            )
+
+            soup = BeautifulSoup(driver.page_source, "html.parser")
+
+            # Initialize bin data dictionary
+            bin_data = {"bins": []}
+
+            # Find the table
+            table = soup.find("table", class_="table")
+            if table:
+                # Find all rows in tbody
+                rows = table.find("tbody").find_all("tr")
+
+                for row in rows:
+                    # Get all cells in the row
+                    cells = row.find_all("td")
+                    if len(cells) >= 4:  # Ensure we have enough cells
+                        bin_type = cells[0].text.strip()
+                        next_collection = cells[1].text.strip()
+                        following_collection = cells[3].text.strip()
+
+                        # Parse the dates
+                        for collection_date in [next_collection, following_collection]:
+                            try:
+                                # Convert date from "Friday 09 May 2025" format
+                                parsed_date = datetime.strptime(
+                                    collection_date, "%A %d %B %Y"
+                                )
+                                formatted_date = parsed_date.strftime("%d/%m/%Y")
+
+                                bin_info = {
+                                    "type": bin_type,
+                                    "collectionDate": formatted_date,
+                                }
+                                bin_data["bins"].append(bin_info)
+                            except ValueError as e:
+                                print(f"Error parsing date {collection_date}: {e}")
+            else:
+                raise ValueError("Collection data table not found")
+
+            # Sort the collections by date
+            bin_data["bins"].sort(
+                key=lambda x: datetime.strptime(x["collectionDate"], "%d/%m/%Y")
+            )
+
+            print(bin_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 bin_data

uk_bin_collection-0.150.1/uk_bin_collection/uk_bin_collection/councils/RugbyBoroughCouncil.py

@@ -1,89 +0,0 @@
-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:
-        data = {"bins": []}
-        collections = []
-
-        user_postcode = kwargs.get("postcode")
-        user_uprn = kwargs.get("uprn")
-
-        check_uprn(user_uprn)
-        check_postcode(user_postcode)
-
-        headers = {
-            "authority": "www.rugby.gov.uk",
-            "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
-            "accept-language": "en-GB,en;q=0.9",
-            "cache-control": "no-cache",
-            "content-type": "application/x-www-form-urlencoded",
-            # 'cookie': 'JSESSIONID=7E90CAB54B649C3DCC7F6B5DA0897C63; COOKIE_SUPPORT=true; GUEST_LANGUAGE_ID=en_GB; AWSELB=D941E98916B5759862ED6C39DA9FB3FD9880491851D200C98112ABEC3223D52B19A2A2C6B37A89D3650D44FA5728FCAFEDE7BB2592D948FFF9C7B18D76C41AF02C308B0F3A2DE17F1585E9959BCE68CC83BC3AC753; CookieControl={"necessaryCookies":[],"optionalCookies":{},"statement":{},"consentDate":1701710876715,"consentExpiry":90,"interactedWith":true,"user":"8FED8810-3C3E-4D50-A9DC-42655030B3B1"}',
-            "origin": "https://www.rugby.gov.uk",
-            "pragma": "no-cache",
-            "referer": "https://www.rugby.gov.uk/check-your-next-bin-day",
-            "sec-ch-ua": '"Chromium";v="118", "Opera GX";v="104", "Not=A?Brand";v="99"',
-            "sec-ch-ua-mobile": "?0",
-            "sec-ch-ua-platform": '"Windows"',
-            "sec-fetch-dest": "document",
-            "sec-fetch-mode": "navigate",
-            "sec-fetch-site": "same-origin",
-            "sec-fetch-user": "?1",
-            "upgrade-insecure-requests": "1",
-            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.5993.118 Safari/537.36",
-        }
-        params = {
-            "p_p_id": "com_placecube_digitalplace_local_waste_portlet_CollectionDayFinderPortlet",
-            "p_p_lifecycle": "0",
-            "p_p_state": "normal",
-            "p_p_mode": "view",
-            "_com_placecube_digitalplace_local_waste_portlet_CollectionDayFinderPortlet_mvcRenderCommandName": "/collection_day_finder/get_days",
-        }
-        data = {
-            "_com_placecube_digitalplace_local_waste_portlet_CollectionDayFinderPortlet_formDate": f"{datetime.now().timestamp().__floor__()}",
-            "_com_placecube_digitalplace_local_waste_portlet_CollectionDayFinderPortlet_postcode": f"{user_postcode}",
-            "_com_placecube_digitalplace_local_waste_portlet_CollectionDayFinderPortlet_uprn": f"{user_uprn}",
-        }
-
-        response = requests.post(
-            "https://www.rugby.gov.uk/check-your-next-bin-day",
-            params=params,
-            headers=headers,
-            data=data,
-        )
-
-        soup = BeautifulSoup(response.text, features="html.parser")
-        soup.prettify()
-
-        table_rows = soup.find("table", {"class": "table"}).find("tbody").find_all("tr")
-
-        for row in table_rows:
-            row_text = row.text.strip().split("\n")
-            bin_text = row_text[0].split(" ")
-            bin_type = " ".join(bin_text[1:]).capitalize()
-            collections.append(
-                (bin_type, datetime.strptime(row_text[1], "%A %d %b %Y"))
-            )
-            collections.append(
-                (bin_type, datetime.strptime(row_text[3], "%A %d %b %Y"))
-            )
-
-        ordered_data = sorted(collections, key=lambda x: x[1])
-        data = {"bins": []}
-        for item in ordered_data:
-            dict_data = {
-                "type": item[0],
-                "collectionDate": item[1].strftime(date_format),
-            }
-            data["bins"].append(dict_data)
-
-        return data