uk_bin_collection 0.74.0__py3-none-any.whl

uk_bin_collection/uk_bin_collection/councils/EastRidingCouncil.py

@@ -0,0 +1,142 @@
+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
+
+from bs4 import BeautifulSoup
+from datetime import datetime
+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
+
+import pandas as pd
+import urllib.request
+
+
+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_paon = kwargs.get("paon")
+            user_postcode = kwargs.get("postcode")
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+
+            # Create Selenium webdriver
+            page = f"https://www.eastriding.gov.uk/environment/bins-rubbish-recycling/bins-and-collections/bin-collection-dates/"
+
+            driver = create_webdriver(web_driver, headless)
+            driver.get(page)
+
+            wait = WebDriverWait(driver, 60)
+
+            try:
+                accept_cookies = wait.until(
+                    EC.element_to_be_clickable(
+                        (By.XPATH, '//*[@id="er-cookie-placeholder-settings"]/div/a[1]')
+                    )
+                )
+
+                accept_cookies.click()
+            except:
+                print(
+                    "Cookies acceptance element not found or clickable within the specified time."
+                )
+                pass
+
+            expand_postcode_box = wait.until(
+                EC.element_to_be_clickable(
+                    (By.ID, "when-and-where-should-i-put-my-bin-out")
+                )
+            )
+
+            expand_postcode_box.click()
+
+            postcode_box = wait.until(
+                EC.element_to_be_clickable(
+                    (By.XPATH, "//input[@placeholder='Enter your postcode']")
+                )
+            )
+            postcode_box.send_keys(user_postcode)
+
+            postcode_search_btn = wait.until(
+                EC.element_to_be_clickable((By.XPATH, "//button[text()='Search']"))
+            )
+            postcode_search_btn.send_keys(Keys.ENTER)
+
+            dropdown = wait.until(
+                EC.presence_of_element_located(
+                    (
+                        By.XPATH,
+                        "//div[@class='er-select-wrapper']/select[@class='dropdown']",
+                    )
+                )
+            )
+
+            options_present = wait.until(
+                EC.presence_of_all_elements_located(
+                    (By.CSS_SELECTOR, "select.dropdown option")
+                )
+            )
+            drop = Select(dropdown)
+            drop.select_by_visible_text(str(user_paon))
+
+            results_present = wait.until(
+                EC.presence_of_element_located(
+                    (
+                        By.CLASS_NAME,
+                        "results",
+                    )
+                )
+            )
+
+            data = {"bins": []}  # dictionary for data
+            soup = BeautifulSoup(driver.page_source, "html.parser")
+
+            bin_types = {}  # Dictionary to store bin types
+
+            # Extract bin types from header elements
+            header_elements = soup.find_all(
+                "li", class_=lambda x: x and x.startswith("header")
+            )
+            for header_element in header_elements:
+                bin_type = header_element.get_text(strip=True)
+                bin_class = [
+                    cls for cls in header_element.get("class") if cls != "header"
+                ]
+                if bin_class:
+                    bin_types[bin_class[0]] = bin_type
+
+            # Extract collection dates and associate them with respective bin types
+            date_elements = soup.find_all(
+                "li", class_=lambda x: x and x.startswith("date")
+            )
+            for date_element in date_elements:
+                bin_class = [cls for cls in date_element.get("class") if cls != "date"]
+                if bin_class:
+                    bin_type = bin_types.get(bin_class[0])
+                    span_text = date_element.find("span").get_text(strip=True)
+                    collection_date = datetime.strptime(span_text, "%a, %d %b %Y")
+                    data["bins"].append(
+                        {
+                            "type": bin_type,
+                            "collectionDate": collection_date.strftime(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 data

uk_bin_collection/uk_bin_collection/councils/EastSuffolkCouncil.py

@@ -0,0 +1,112 @@
+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 WebDriverWait, Select
+
+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_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)
+            driver.get(
+                "https://my.eastsuffolk.gov.uk/service/Bin_collection_dates_finder"
+            )
+
+            # Wait for iframe to load and switch to it
+            WebDriverWait(driver, 30).until(
+                EC.frame_to_be_available_and_switch_to_it((By.ID, "fillform-frame-1"))
+            )
+
+            # Wait for postcode entry box
+            postcode = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located((By.ID, "alt_postcode_search"))
+            )
+            # Enter postcode
+            postcode.send_keys(user_postcode.replace(" ", ""))
+
+            # Wait for address selection dropdown to appear
+            address = Select(
+                WebDriverWait(driver, 10).until(
+                    EC.visibility_of_element_located((By.ID, "alt_choose_address"))
+                )
+            )
+
+            # Wait for spinner to disappear (signifies options are loaded for select)
+            WebDriverWait(driver, 10).until(
+                EC.invisibility_of_element_located((By.CLASS_NAME, "spinner-outer"))
+            )
+
+            # Sometimes the options aren't fully there despite the spinner being gone, wait another 2 seconds.
+            sleep(2)
+
+            # Select address by UPRN
+            address.select_by_value(user_uprn)
+
+            # Wait for spinner to disappear (signifies data is loaded)
+            WebDriverWait(driver, 10).until(
+                EC.invisibility_of_element_located((By.CLASS_NAME, "spinner-outer"))
+            )
+
+            sleep(2)
+
+            # Find data table
+            data_table = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (
+                        By.XPATH,
+                        '//div[@data-field-name="collection_details"]/div[contains(@class, "fieldContent")]/div[contains(@class, "repeatable-table-wrapper")]',
+                    )
+                )
+            )
+
+            # Make a BS4 object
+            soup = BeautifulSoup(
+                data_table.get_attribute("innerHTML"), features="html.parser"
+            )
+
+            data = {"bins": []}
+
+            rows = soup.find("table").find("tbody").find_all("tr")
+            for row in rows:
+                cols = row.find_all("td")
+                bin_type = cols[2].find_all("span")[1].text.title()
+                collection_date = cols[3].find_all("span")[1].text
+                collection_date = datetime.strptime(
+                    collection_date, "%d/%m/%Y"
+                ).strftime(date_format)
+                dict_data = {"type": bin_type, "collectionDate": collection_date}
+                data["bins"].append(dict_data)
+
+            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 data

uk_bin_collection/uk_bin_collection/councils/EastleighBoroughCouncil.py

@@ -0,0 +1,70 @@
+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:
+        uprn = kwargs.get("uprn")
+        # Check the UPRN is valid
+        check_uprn(uprn)
+
+        # Request URL
+        url = f"https://www.eastleigh.gov.uk/waste-bins-and-recycling/collection-dates/your-waste-bin-and-recycling-collections?uprn={uprn}"
+
+        # Make Request
+        requests.packages.urllib3.disable_warnings()
+        page = requests.get(url)
+
+        # Make a BS4 object
+        soup = BeautifulSoup(page.text, features="html.parser")
+        soup.prettify()
+
+        # Data to return
+        data = {"bins": []}
+
+        # Valid bin types
+        binTypes = [
+            "Household Waste Bin",
+            "Recycling Bin",
+            "Food Waste Bin",
+            "Glass Box and Batteries",
+            "Garden Waste Bin",
+        ]
+
+        # Value to create dict for DL values
+        keys, values = [], []
+
+        # Loop though DT and DD for DL containing bins
+        dl = soup.find("dl", {"class": "dl-horizontal"})
+        for dt in dl.find_all("dt"):
+            keys.append(dt.text.strip())
+        for dd in dl.find_all("dd"):
+            values.append(dd.text.strip())
+
+        # Create dict for bin name and string dates
+        binDict = dict(zip(keys, values))
+
+        # Process dict for valid bin types
+        for bin in list(binDict):
+            if bin in binTypes:
+                if not binDict[bin].startswith("You haven't yet signed up for"):
+                    # Convert date
+                    date = datetime.strptime(binDict[bin], "%a, %d %b %Y")
+
+                    # Set bin data
+                    dict_data = {
+                        "type": bin,
+                        "collectionDate": date.strftime(date_format),
+                    }
+                    data["bins"].append(dict_data)
+
+        # Return bin data
+        return data

uk_bin_collection/uk_bin_collection/councils/EnvironmentFirst.py

@@ -0,0 +1,48 @@
+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:
+        # Make a BS4 object
+        soup = BeautifulSoup(page.text, features="html.parser")
+        soup.prettify()
+
+        # Get the paragraph lines from the page
+        data = {"bins": []}
+        page_text = soup.find("div", {"class": "collect"}).find_all("p")
+
+        # Parse the correct lines (find them, remove the ordinal indicator and make them the correct format date) and
+        # then add them to the dictionary
+        rubbish_day = datetime.strptime(
+            remove_ordinal_indicator_from_date_string(
+                page_text[2].find_next("strong").text
+            ),
+            "%d %B %Y",
+        ).strftime(date_format)
+        dict_data = {
+            "type": "Rubbish",
+            "collectionDate": rubbish_day,
+        }
+        data["bins"].append(dict_data)
+        recycling_day = datetime.strptime(
+            remove_ordinal_indicator_from_date_string(
+                page_text[4].find_next("strong").text
+            ),
+            "%d %B %Y",
+        ).strftime(date_format)
+        dict_data = {
+            "type": "Recycling",
+            "collectionDate": recycling_day,
+        }
+        data["bins"].append(dict_data)
+
+        return data

uk_bin_collection/uk_bin_collection/councils/ErewashBoroughCouncil.py

@@ -0,0 +1,61 @@
+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": []}
+        uprn = kwargs.get("uprn")
+        check_uprn(uprn)
+
+        requests.packages.urllib3.disable_warnings()
+        response = requests.get(
+            f"https://map.erewash.gov.uk/isharelive.web/myerewash.aspx?action=SetAddress&UniqueId={uprn}",
+            headers={"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64)"},
+        )
+
+        soup = BeautifulSoup(response.text, features="html.parser")
+        collections = soup.find("div", {"aria-label": "Waste Collection"}).find_all(
+            "div", {"class": "atPanelContent"}
+        )
+        for c in collections:
+            bin_type = c.find("h4").get_text(strip=True)
+            if "my next" in bin_type.lower():
+                collection_info = c.find("div", {"class": "atPanelData"}).get_text(
+                    strip=True
+                )
+                results = re.search(
+                    "([A-Za-z]+ \\d+[A-Za-z]+ [A-Za-z]+ \\d*)", collection_info
+                )
+                if results:
+                    collection_date = datetime.strptime(
+                        remove_ordinal_indicator_from_date_string(results[1]).strip(),
+                        "%A %d %B %Y",
+                    ).strftime(date_format)
+                    dict_data = {
+                        "type": bin_type.replace("My Next ", "").replace(
+                            " Collection", ""
+                        ),
+                        "collectionDate": collection_date,
+                    }
+                    data["bins"].append(dict_data)
+                    if "garden waste" in collection_info.lower():
+                        dict_data = {
+                            "type": "Garden Waste",
+                            "collectionDate": collection_date,
+                        }
+                        data["bins"].append(dict_data)
+
+        data["bins"].sort(
+            key=lambda x: datetime.strptime(x.get("collectionDate"), date_format)
+        )
+
+        return data

uk_bin_collection/uk_bin_collection/councils/FenlandDistrictCouncil.py

@@ -0,0 +1,65 @@
+import json
+
+import requests
+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)
+
+        headers = {
+            "Accept": "application/json, text/javascript, */*; q=0.01",
+            "Accept-Language": "en-GB,en;q=0.7",
+            "Connection": "keep-alive",
+            "Content-Type": "application/json; charset=utf-8",
+            "Referer": "https://www.fenland.gov.uk/article/13114/?uprn=200002981143&lat=52.665569590474&lng=0.177905443639&postcode=PE13+3SL&line1=20+Felsted+Avenue&rad=5m&layers=2%2C3%2C1",
+            "Sec-Fetch-Dest": "empty",
+            "Sec-Fetch-Mode": "cors",
+            "Sec-Fetch-Site": "same-origin",
+            "Sec-GPC": "1",
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36",
+            "X-Requested-With": "XMLHttpRequest",
+        }
+
+        # It needs lat and lng for point data, but we don't need it >:)
+        params = {
+            "type": "loadlayer",
+            "layerId": "2",
+            "uprn": user_uprn,
+            "lat": "0.000000000001",
+            "lng": "0.000000000001",
+        }
+
+        requests.packages.urllib3.disable_warnings()
+        response = requests.get(
+            "https://www.fenland.gov.uk/article/13114/", params=params, headers=headers
+        )
+
+        # Returned data is just json, so we can get what we need
+        json_data = json.loads(response.text)["features"][0]["properties"]["upcoming"]
+        data = {"bins": []}
+
+        for item in json_data:
+            collections_list = item["collections"]
+            for bin in collections_list:
+                bin_type = bin["desc"]
+                bin_date = datetime.strptime(
+                    bin["collectionDate"], "%Y-%m-%dT%H:%M:%SZ"
+                ).strftime(date_format)
+                dict_data = {
+                    "type": bin_type,
+                    "collectionDate": bin_date,
+                }
+                data["bins"].append(dict_data)
+
+        return data

uk_bin_collection/uk_bin_collection/councils/ForestOfDeanDistrictCouncil.py

@@ -0,0 +1,113 @@
+from bs4 import BeautifulSoup
+from datetime import datetime
+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
+import time
+
+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://community.fdean.gov.uk/s/waste-collection-enquiry"
+
+            data = {"bins": []}
+
+            house_number = kwargs.get("paon")
+            postcode = kwargs.get("postcode")
+            full_address = f"{house_number}, {postcode}"
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+
+            # Create Selenium webdriver
+            driver = create_webdriver(web_driver, headless)
+            driver.get(page)
+
+            # If you bang in the house number (or property name) and postcode in the box it should find your property
+            wait = WebDriverWait(driver, 60)
+            address_entry_field = wait.until(
+                EC.presence_of_element_located(
+                    (By.XPATH, '//*[@id="combobox-input-19"]')
+                )
+            )
+
+            address_entry_field.send_keys(str(full_address))
+
+            address_entry_field = wait.until(
+                EC.element_to_be_clickable((By.XPATH, '//*[@id="combobox-input-19"]'))
+            )
+            address_entry_field.click()
+            address_entry_field.send_keys(Keys.BACKSPACE)
+            address_entry_field.send_keys(str(full_address[len(full_address) - 1]))
+
+            first_found_address = wait.until(
+                EC.element_to_be_clickable(
+                    (By.XPATH, '//*[@id="dropdown-element-19"]/ul')
+                )
+            )
+
+            first_found_address.click()
+            # Wait for the 'Select your property' dropdown to appear and select the first result
+            next_btn = wait.until(
+                EC.element_to_be_clickable((By.XPATH, "//lightning-button/button"))
+            )
+            next_btn.click()
+            bin_data = wait.until(
+                EC.presence_of_element_located(
+                    (By.XPATH, "//span[contains(text(), 'Container')]")
+                )
+            )
+
+            soup = BeautifulSoup(driver.page_source, features="html.parser")
+
+            rows = soup.find_all("tr", class_="slds-hint-parent")
+            current_year = datetime.now().year
+
+            for row in rows:
+                columns = row.find_all("td")
+                if columns:
+                    container_type = row.find("th").text.strip()
+                    collection_day = re.sub(
+                        r"[^a-zA-Z0-9,\s]", "", columns[0].get_text()
+                    ).strip()
+
+                    # Parse the date from the string
+                    parsed_date = datetime.strptime(collection_day, "%a, %d %B")
+                    if parsed_date < datetime(
+                        parsed_date.year, parsed_date.month, parsed_date.day
+                    ):
+                        parsed_date = parsed_date.replace(year=current_year + 1)
+                    else:
+                        parsed_date = parsed_date.replace(year=current_year)
+                    # Format the date as %d/%m/%Y
+                    formatted_date = parsed_date.strftime("%d/%m/%Y")
+
+                    # Add the bin type and collection date to the 'data' dictionary
+                    data["bins"].append(
+                        {"type": container_type, "collectionDate": formatted_date}
+                    )
+        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