uk_bin_collection 0.86.1__tar.gz → 0.87.0__tar.gz

{uk_bin_collection-0.86.1 → uk_bin_collection-0.87.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.86.1
+Version: 0.87.0
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.86.1 → uk_bin_collection-0.87.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.86.1"
+version = "0.87.0"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.86.1 → uk_bin_collection-0.87.0}/uk_bin_collection/tests/input.json

@@ -427,6 +427,15 @@
         "wiki_name": "Glasgow City Council",
         "wiki_note": "Replace XXXXXXXX with UPRN."
     },
+    "GloucesterCityCouncil": {
+        "house_number": "111",
+        "postcode": "GL2 0RR",
+        "uprn": "100120479507",
+        "skip_get_url": true,
+        "web_driver": "http://selenium:4444",
+        "url": "https://gloucester-self.achieveservice.com/service/Bins___Check_your_bin_day",
+        "wiki_name": "Gloucester City Council"
+    },
     "GuildfordCouncil": {
         "house_number": "THE LODGE, PUTTENHAM HILL HOUSE, PUTTENHAM HILL, PUTTENHAM, GUILDFORD, GU3 1AH",
         "postcode": "GU3 1AH",
@@ -490,6 +499,13 @@
         "wiki_name": "Huntingdon District Council",
         "wiki_note": "Replace XXXXXXXX with UPRN."
     },
+    "IslingtonCouncil": {
+        "uprn": "5300094897",
+        "url": "https://www.islington.gov.uk/your-area?Postcode=unused&Uprn=5300094897",
+        "wiki_command_url_override": "https://www.islington.gov.uk/your-area?Postcode=unused&Uprn=XXXXXXXX",
+        "wiki_name": "Islington Council",
+        "wiki_note": "Replace XXXXXXXX with UPRN."
+    },
     "KingstonUponThamesCouncil": {
         "url": "https://waste-services.kingston.gov.uk/waste/2701097",
         "wiki_command_url_override": "https://waste-services.kingston.gov.uk/waste/XXXXXXX",
@@ -1225,4 +1241,4 @@
         "url": "https://waste-api.york.gov.uk/api/Collections/GetBinCollectionDataForUprn/",
         "wiki_name": "York Council"
     }
-}
+}

uk_bin_collection-0.87.0/uk_bin_collection/uk_bin_collection/councils/GloucesterCityCouncil.py

@@ -0,0 +1,128 @@
+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://gloucester-self.achieveservice.com/service/Bins___Check_your_bin_day"
+
+            bin_data = {"bins": []}
+
+            user_uprn = kwargs.get("uprn")
+            user_postcode = kwargs.get("postcode")
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+            check_uprn(user_uprn)
+            check_postcode(user_postcode)
+            # Create Selenium webdriver
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            driver.get(page)
+
+            cookies_button = WebDriverWait(driver, timeout=15).until(
+                EC.presence_of_element_located((By.ID, "close-cookie-message"))
+            )
+            cookies_button.click()
+
+            without_login_button = WebDriverWait(driver, timeout=15).until(
+                EC.presence_of_element_located(
+                    (By.LINK_TEXT, "or, Continue with no account")
+                )
+            )
+            without_login_button.click()
+
+            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)
+            inputElement_postcodesearch = wait.until(
+                EC.element_to_be_clickable((By.NAME, "find_postcode"))
+            )
+
+            inputElement_postcodesearch.send_keys(user_postcode)
+
+            # Wait for the 'Select address' dropdown to be updated
+            time.sleep(2)
+
+            dropdown = wait.until(
+                EC.element_to_be_clickable((By.NAME, "chooseAddress"))
+            )
+            # Create a 'Select' for it, then select the first address in the list
+            # (Index 0 is "Select...")
+            dropdownSelect = Select(dropdown)
+            dropdownSelect.select_by_value(str(user_uprn))
+
+            # 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"), "%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 bin_data

uk_bin_collection-0.87.0/uk_bin_collection/uk_bin_collection/councils/IslingtonCouncil.py

@@ -0,0 +1,37 @@
+from bs4 import BeautifulSoup
+from dateutil.parser import parse
+
+from uk_bin_collection.uk_bin_collection.common import *
+from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
+
+
+class CouncilClass(AbstractGetBinDataClass):
+    def parse_data(self, page: str, **kwargs) -> dict:
+        uprn = kwargs.get("uprn")
+        check_uprn(uprn)
+
+        api_url = f"https://www.islington.gov.uk/your-area?Postcode=unused&Uprn={uprn}"
+        response = requests.get(api_url)
+
+        soup = BeautifulSoup(response.text, features="html.parser")
+
+        data = {"bins": []}
+
+        waste_table = (
+            soup.find(string="Waste and recycling collections")
+            .find_next("div", class_="m-toggle-content")
+            .find("table")
+        )
+
+        if waste_table:
+            rows = waste_table.find_all("tr")
+            for row in rows:
+                waste_type = row.find("th").text.strip()
+                next_collection = parse(row.find("td").text.strip()).date()
+
+                data['bins'].append({
+                    "type": waste_type,
+                    "collectionDate": next_collection.strftime(date_format),
+                })
+
+        return data