uk_bin_collection 0.130.0__tar.gz → 0.130.1__tar.gz

{uk_bin_collection-0.130.0 → uk_bin_collection-0.130.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.130.0
+Version: 0.130.1
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.130.0 → uk_bin_collection-0.130.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.130.0"
+version = "0.130.1"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

uk_bin_collection-0.130.1/uk_bin_collection/uk_bin_collection/councils/AshfieldDistrictCouncil.py

@@ -0,0 +1,115 @@
+import time
+from datetime import datetime
+
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+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
+
+
+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:
+            # Get and check UPRN
+            user_postcode = kwargs.get("postcode")
+            user_paon = kwargs.get("paon")
+            check_paon(user_paon)
+            check_postcode(user_postcode)
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+            bindata = {"bins": []}
+
+            API_URL = "https://portal.digital.ashfield.gov.uk/w/webpage/raise-case?service=bin_calendar"
+
+            # Create Selenium webdriver
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            driver.get(API_URL)
+
+            title = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located((By.ID, "sub_page_title"))
+            )
+
+            # Wait for the postcode field to appear then populate it
+            WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (By.CSS_SELECTOR, "input.relation_path_type_ahead_search")
+                )
+            )
+
+            inputElement_postcode = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (By.CSS_SELECTOR, "input.relation_path_type_ahead_search")
+                )
+            )
+            inputElement_postcode.clear()
+            inputElement_postcode.send_keys(user_postcode)
+
+            # Wait for the 'Select your property' dropdown to appear and select the first result
+            dropdown = WebDriverWait(driver, 10).until(
+                EC.element_to_be_clickable(
+                    (
+                        By.CLASS_NAME,
+                        "result_list ",
+                    )
+                )
+            )
+
+            address_element = (
+                WebDriverWait(driver, 10)
+                .until(
+                    EC.element_to_be_clickable(
+                        (By.XPATH, f"//li[starts-with(@aria-label, '{user_paon}')]")
+                    )
+                )
+                .click()
+            )
+
+            search_button = WebDriverWait(driver, 10).until(
+                EC.element_to_be_clickable(
+                    (By.XPATH, "//input[@type='submit' and @value='Search']")
+                )
+            )
+            search_button.click()
+
+            time.sleep(10)
+
+            soup = BeautifulSoup(driver.page_source, features="html.parser")
+            soup.prettify()
+
+            # Find the table by class name
+            table = soup.find("table", {"class": "table listing table-striped"})
+
+            # Iterate over each row in the tbody of the table
+            for row in table.find("tbody").find_all("tr"):
+                # Extract the service, day, and date for each row
+                service = row.find_all("td")[0].get_text(strip=True)
+                date = row.find_all("td")[2].get_text(strip=True)
+
+                dict_data = {
+                    "type": service,
+                    "collectionDate": datetime.strptime(date, "%a, %d %b %Y").strftime(
+                        date_format
+                    ),
+                }
+                bindata["bins"].append(dict_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 bindata

uk_bin_collection-0.130.1/uk_bin_collection/uk_bin_collection/councils/PowysCouncil.py

@@ -0,0 +1,150 @@
+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": []}
+            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)
+
+            user_paon = user_paon.upper()
+
+            # Create Selenium webdriver
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            driver.get("https://en.powys.gov.uk/binday")
+
+            accept_button = WebDriverWait(driver, timeout=10).until(
+                EC.element_to_be_clickable(
+                    (
+                        By.NAME,
+                        "acceptall",
+                    )
+                )
+            )
+            accept_button.click()
+
+            # Wait for the postcode field to appear then populate it
+            inputElement_postcode = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (By.ID, "BINDAYLOOKUP_ADDRESSLOOKUP_ADDRESSLOOKUPPOSTCODE")
+                )
+            )
+            inputElement_postcode.send_keys(user_postcode)
+
+            # Click search button
+            findAddress = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (By.ID, "BINDAYLOOKUP_ADDRESSLOOKUP_ADDRESSLOOKUPSEARCH")
+                )
+            )
+            findAddress.click()
+
+            # Wait for the 'Select address' dropdown to appear and select option matching the house name/number
+            WebDriverWait(driver, 10).until(
+                EC.element_to_be_clickable(
+                    (
+                        By.XPATH,
+                        "//select[@id='BINDAYLOOKUP_ADDRESSLOOKUP_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.element_to_be_clickable(
+                    (By.ID, "BINDAYLOOKUP_ADDRESSLOOKUP_ADDRESSLOOKUPBUTTONS_NEXT")
+                )
+            ).click()
+
+            # Wait for the collections table to appear
+            WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (By.ID, "BINDAYLOOKUP_COLLECTIONDATES_COLLECTIONDATES")
+                )
+            )
+
+            soup = BeautifulSoup(driver.page_source, features="html.parser")
+
+            # General rubbish collection dates
+            general_rubbish_section = soup.find(
+                "h3", string="General Rubbish / Wheelie bin"
+            )
+            general_rubbish_dates = [
+                li.text for li in general_rubbish_section.find_next("ul").find_all("li")
+            ]
+
+            for date in general_rubbish_dates:
+                dict_data = {
+                    "type": "General Rubbish / Wheelie bin",
+                    "collectionDate": datetime.strptime(
+                        remove_ordinal_indicator_from_date_string(date), "%d %B %Y"
+                    ).strftime(date_format),
+                }
+                data["bins"].append(dict_data)
+
+            # Recycling and food waste collection dates
+            recycling_section = soup.find("h3", string="Recycling and Food Waste")
+            recycling_dates = [
+                li.text for li in recycling_section.find_next("ul").find_all("li")
+            ]
+
+            for date in recycling_dates:
+                dict_data = {
+                    "type": "Recycling and Food Waste",
+                    "collectionDate": datetime.strptime(
+                        remove_ordinal_indicator_from_date_string(date), "%d %B %Y"
+                    ).strftime(date_format),
+                }
+                data["bins"].append(dict_data)
+
+            # Garden waste collection dates
+            garden_waste_section = soup.find("h3", string="Garden Waste")
+            garden_waste_dates = [
+                li.text for li in garden_waste_section.find_next("ul").find_all("li")
+            ]
+            for date in garden_waste_dates:
+                try:
+                    dict_data = {
+                        "type": "Garden Waste",
+                        "collectionDate": datetime.strptime(
+                            remove_ordinal_indicator_from_date_string(date), "%d %B %Y"
+                        ).strftime(date_format),
+                    }
+                    data["bins"].append(dict_data)
+                except:
+                    continue
+        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-0.130.1/uk_bin_collection/uk_bin_collection/councils/TeignbridgeCouncil.py

@@ -0,0 +1,68 @@
+from bs4 import BeautifulSoup
+from selenium.webdriver.common.by import By
+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
+
+
+# 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")
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+            check_uprn(user_uprn)
+            bindata = {"bins": []}
+
+            URI = f"https://www.teignbridge.gov.uk/repositories/hidden-pages/bin-finder?uprn={user_uprn}"
+
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            driver.get(URI)
+
+            soup = BeautifulSoup(driver.page_source, features="html.parser")
+
+            collection_dates = soup.find_all(
+                "h3"
+            )  # Assuming bin types are inside <h3> tags
+            bin_type_headers = soup.find_all(
+                "div", {"class": "binInfoContainer"}
+            )  # Assuming collection dates are inside <p> tags
+
+            # Iterate over the results and extract bin type and collection dates
+            for i, date in enumerate(collection_dates):
+                collection_date = date.get_text(strip=True)
+
+                bin_types = bin_type_headers[i].find_all("div")
+                for bin_type in bin_types:
+                    dict_data = {
+                        "type": bin_type.text.strip(),
+                        "collectionDate": datetime.strptime(
+                            collection_date,
+                            "%d %B %Y%A",
+                        ).strftime("%d/%m/%Y"),
+                    }
+                    bindata["bins"].append(dict_data)
+
+            bindata["bins"].sort(
+                key=lambda x: datetime.strptime(x.get("collectionDate"), "%d/%m/%Y")
+            )
+        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 bindata

uk_bin_collection-0.130.0/uk_bin_collection/uk_bin_collection/councils/AshfieldDistrictCouncil.py

@@ -1,105 +0,0 @@
-import time
-from datetime import datetime
-
-from bs4 import BeautifulSoup
-from selenium import webdriver
-from selenium.webdriver.common.by import By
-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
-
-
-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_postcode = kwargs.get("postcode")
-        user_paon = kwargs.get("paon")
-        check_paon(user_paon)
-        check_postcode(user_postcode)
-        web_driver = kwargs.get("web_driver")
-        headless = kwargs.get("headless")
-        bindata = {"bins": []}
-
-        API_URL = "https://portal.digital.ashfield.gov.uk/w/webpage/raise-case?service=bin_calendar"
-
-        # Create Selenium webdriver
-        driver = create_webdriver(web_driver, headless, None, __name__)
-        driver.get(API_URL)
-
-        title = WebDriverWait(driver, 10).until(
-            EC.presence_of_element_located((By.ID, "sub_page_title"))
-        )
-
-        # Wait for the postcode field to appear then populate it
-        WebDriverWait(driver, 10).until(
-            EC.presence_of_element_located(
-                (By.CSS_SELECTOR, "input.relation_path_type_ahead_search")
-            )
-        )
-
-        inputElement_postcode = WebDriverWait(driver, 10).until(
-            EC.presence_of_element_located(
-                (By.CSS_SELECTOR, "input.relation_path_type_ahead_search")
-            )
-        )
-        inputElement_postcode.clear()
-        inputElement_postcode.send_keys(user_postcode)
-
-        # Wait for the 'Select your property' dropdown to appear and select the first result
-        dropdown = WebDriverWait(driver, 10).until(
-            EC.element_to_be_clickable(
-                (
-                    By.CLASS_NAME,
-                    "result_list ",
-                )
-            )
-        )
-
-        address_element = (
-            WebDriverWait(driver, 10)
-            .until(
-                EC.element_to_be_clickable(
-                    (By.XPATH, f"//li[starts-with(@aria-label, '{user_paon}')]")
-                )
-            )
-            .click()
-        )
-
-        search_button = WebDriverWait(driver, 10).until(
-            EC.element_to_be_clickable(
-                (By.XPATH, "//input[@type='submit' and @value='Search']")
-            )
-        )
-        search_button.click()
-
-        time.sleep(10)
-
-        soup = BeautifulSoup(driver.page_source, features="html.parser")
-        soup.prettify()
-
-        # Find the table by class name
-        table = soup.find("table", {"class": "table listing table-striped"})
-
-        # Iterate over each row in the tbody of the table
-        for row in table.find("tbody").find_all("tr"):
-            # Extract the service, day, and date for each row
-            service = row.find_all("td")[0].get_text(strip=True)
-            date = row.find_all("td")[2].get_text(strip=True)
-
-            dict_data = {
-                "type": service,
-                "collectionDate": datetime.strptime(date, "%a, %d %b %Y").strftime(
-                    date_format
-                ),
-            }
-            bindata["bins"].append(dict_data)
-
-        return bindata

uk_bin_collection-0.130.0/uk_bin_collection/uk_bin_collection/councils/PowysCouncil.py

@@ -1,141 +0,0 @@
-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
-        data = {"bins": []}
-        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)
-
-        user_paon = user_paon.upper()
-
-        # Create Selenium webdriver
-        driver = create_webdriver(web_driver, headless, None, __name__)
-        driver.get("https://en.powys.gov.uk/binday")
-
-        accept_button = WebDriverWait(driver, timeout=10).until(
-            EC.element_to_be_clickable(
-                (
-                    By.NAME,
-                    "acceptall",
-                )
-            )
-        )
-        accept_button.click()
-
-        # Wait for the postcode field to appear then populate it
-        inputElement_postcode = WebDriverWait(driver, 10).until(
-            EC.presence_of_element_located(
-                (By.ID, "BINDAYLOOKUP_ADDRESSLOOKUP_ADDRESSLOOKUPPOSTCODE")
-            )
-        )
-        inputElement_postcode.send_keys(user_postcode)
-
-        # Click search button
-        findAddress = WebDriverWait(driver, 10).until(
-            EC.presence_of_element_located(
-                (By.ID, "BINDAYLOOKUP_ADDRESSLOOKUP_ADDRESSLOOKUPSEARCH")
-            )
-        )
-        findAddress.click()
-
-        # Wait for the 'Select address' dropdown to appear and select option matching the house name/number
-        WebDriverWait(driver, 10).until(
-            EC.element_to_be_clickable(
-                (
-                    By.XPATH,
-                    "//select[@id='BINDAYLOOKUP_ADDRESSLOOKUP_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.element_to_be_clickable(
-                (By.ID, "BINDAYLOOKUP_ADDRESSLOOKUP_ADDRESSLOOKUPBUTTONS_NEXT")
-            )
-        ).click()
-
-        # Wait for the collections table to appear
-        WebDriverWait(driver, 10).until(
-            EC.presence_of_element_located(
-                (By.ID, "BINDAYLOOKUP_COLLECTIONDATES_COLLECTIONDATES")
-            )
-        )
-
-        soup = BeautifulSoup(driver.page_source, features="html.parser")
-
-        # General rubbish collection dates
-        general_rubbish_section = soup.find(
-            "h3", string="General Rubbish / Wheelie bin"
-        )
-        general_rubbish_dates = [
-            li.text for li in general_rubbish_section.find_next("ul").find_all("li")
-        ]
-
-        for date in general_rubbish_dates:
-            dict_data = {
-                "type": "General Rubbish / Wheelie bin",
-                "collectionDate": datetime.strptime(
-                    remove_ordinal_indicator_from_date_string(date), "%d %B %Y"
-                ).strftime(date_format),
-            }
-            data["bins"].append(dict_data)
-
-        # Recycling and food waste collection dates
-        recycling_section = soup.find("h3", string="Recycling and Food Waste")
-        recycling_dates = [
-            li.text for li in recycling_section.find_next("ul").find_all("li")
-        ]
-
-        for date in recycling_dates:
-            dict_data = {
-                "type": "Recycling and Food Waste",
-                "collectionDate": datetime.strptime(
-                    remove_ordinal_indicator_from_date_string(date), "%d %B %Y"
-                ).strftime(date_format),
-            }
-            data["bins"].append(dict_data)
-
-        # Garden waste collection dates
-        garden_waste_section = soup.find("h3", string="Garden Waste")
-        garden_waste_dates = [
-            li.text for li in garden_waste_section.find_next("ul").find_all("li")
-        ]
-        for date in garden_waste_dates:
-            try:
-                dict_data = {
-                    "type": "Garden Waste",
-                    "collectionDate": datetime.strptime(
-                        remove_ordinal_indicator_from_date_string(date), "%d %B %Y"
-                    ).strftime(date_format),
-                }
-                data["bins"].append(dict_data)
-            except:
-                continue
-
-        return data

uk_bin_collection-0.130.0/uk_bin_collection/uk_bin_collection/councils/TeignbridgeCouncil.py

@@ -1,59 +0,0 @@
-from bs4 import BeautifulSoup
-from selenium.webdriver.common.by import By
-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
-
-
-# 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")
-        web_driver = kwargs.get("web_driver")
-        headless = kwargs.get("headless")
-        check_uprn(user_uprn)
-        bindata = {"bins": []}
-
-        URI = f"https://www.teignbridge.gov.uk/repositories/hidden-pages/bin-finder?uprn={user_uprn}"
-
-        driver = create_webdriver(web_driver, headless, None, __name__)
-        driver.get(URI)
-
-        soup = BeautifulSoup(driver.page_source, features="html.parser")
-
-        collection_dates = soup.find_all(
-            "h3"
-        )  # Assuming bin types are inside <h3> tags
-        bin_type_headers = soup.find_all(
-            "div", {"class": "binInfoContainer"}
-        )  # Assuming collection dates are inside <p> tags
-
-        # Iterate over the results and extract bin type and collection dates
-        for i, date in enumerate(collection_dates):
-            collection_date = date.get_text(strip=True)
-
-            bin_types = bin_type_headers[i].find_all("div")
-            for bin_type in bin_types:
-                dict_data = {
-                    "type": bin_type.text.strip(),
-                    "collectionDate": datetime.strptime(
-                        collection_date,
-                        "%d %B %Y%A",
-                    ).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