uk_bin_collection 0.143.6__tar.gz → 0.144.1__tar.gz

{uk_bin_collection-0.143.6 → uk_bin_collection-0.144.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.143.6
+Version: 0.144.1
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.143.6 → uk_bin_collection-0.144.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.143.6"
+version = "0.144.1"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.143.6 → uk_bin_collection-0.144.1}/uk_bin_collection/tests/input.json

@@ -877,6 +877,15 @@
         "wiki_name": "Gravesham Borough Council",
         "wiki_note": "Pass the UPRN. You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search)."
     },
+    "GreatYarmouthBoroughCouncil": {
+        "postcode": "NR31 7EB",
+        "skip_get_url": true,
+        "uprn": "100090834792",
+        "url": "https://myaccount.great-yarmouth.gov.uk/article/6456/Find-my-waste-collection-days",
+        "web_driver": "http://selenium:4444",
+        "wiki_name": "Great Yarmouth Borough Council",
+        "wiki_note": "Pass the postcode, and UPRN in their respective parameters. This parser requires a Selenium webdriver."
+    },
     "GuildfordCouncil": {
         "house_number": "THE LODGE, PUTTENHAM HILL HOUSE, PUTTENHAM HILL, PUTTENHAM, GUILDFORD, GU3 1AH",
         "postcode": "GU3 1AH",
@@ -1668,7 +1677,7 @@
     },
     "SandwellBoroughCouncil": {
         "skip_get_url": true,
-        "uprn": "10008755549",
+        "uprn": "32101971",
         "url": "https://www.sandwell.gov.uk",
         "wiki_name": "Sandwell Borough Council",
         "wiki_note": "Pass the UPRN. You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search)."
@@ -2323,4 +2332,4 @@
         "wiki_name": "York Council",
         "wiki_note": "Provide your UPRN."
     }
-}
+}

uk_bin_collection-0.144.1/uk_bin_collection/uk_bin_collection/councils/GreatYarmouthBoroughCouncil.py

@@ -0,0 +1,140 @@
+import time
+
+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, WebDriverWait
+from selenium.webdriver.common.keys import Keys
+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
+
+# 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")
+            headless = kwargs.get("headless")
+            web_driver = kwargs.get("web_driver")
+            url = kwargs.get("url")
+
+            check_uprn(user_uprn)
+            check_postcode(user_postcode)
+
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            
+            driver.get(url)
+
+            wait = WebDriverWait(driver, 10)
+            accept_cookies_button = wait.until(
+                EC.element_to_be_clickable(
+                    (
+                        By.NAME,
+                        "acceptall",
+                    )
+                )
+            )
+            accept_cookies_button.click()
+
+            postcode_input = WebDriverWait(driver, 10).until(
+                EC.element_to_be_clickable(
+                    (By.ID, "WASTECOLLECTIONCALENDARV2_ADDRESS_ALSF")
+                )
+            )
+
+            postcode_input.send_keys(user_postcode)
+            postcode_input.send_keys(Keys.TAB + Keys.ENTER)
+
+            time.sleep(2)
+            # Wait for address box to be visible
+            select_address_input = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located(
+                    (
+                        By.ID,
+                        "WASTECOLLECTIONCALENDARV2_ADDRESS_ALML",
+                    )
+                )
+            )
+            select_address_input.click()
+
+            # Assume select_address_input is already the dropdown <select> element
+            select = Select(select_address_input)
+
+            # Select the option with the matching UPRN
+            select.select_by_value(user_uprn)
+            select_address_input.click()
+
+            select_address_input.send_keys(Keys.TAB * 2 + Keys.ENTER)
+
+            time.sleep(5)
+            # Wait for the specified div to be present
+            target_div = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located((By.ID, "WASTECOLLECTIONCALENDARV2_LOOKUP_SHOWSCHEDULE"))
+            )
+
+            soup = BeautifulSoup(driver.page_source, "html.parser")
+
+            bin_data = {"bins": []}
+            next_collections = {}  # Dictionary to store the next collection for each bin type
+
+            bin_types = {
+                "bulky": "Bulky Collection",
+                "green": "Recycling",
+                "black": "General Waste",
+                "brown": "Garden Waste"
+            }
+
+            for div in soup.select(".collection-area"):
+                img = div.select_one("img")
+                detail = div.select_one(".collection-detail")
+                date_text = detail.select_one("b").get_text(strip=True)
+
+                try:
+                    # Parse the date text
+                    date_obj = datetime.strptime(date_text + " 2025", "%A %d %B %Y")
+                    if date_obj.date() < datetime.today().date():
+                        continue  # Skip past dates
+                except ValueError:
+                    continue
+
+                # Determine bin type from alt or description
+                description = detail.get_text(separator=" ", strip=True).lower()
+                alt_text = img['alt'].lower()
+
+                for key, name in bin_types.items():
+                    if key in alt_text or key in description:
+                        # Format date as dd/mm/yyyy
+                        formatted_date = date_obj.strftime("%d/%m/%Y")
+                        bin_entry = {
+                            "type": name,
+                            "collectionDate": formatted_date
+                        }
+                        
+                        # Only keep the earliest date for each bin type
+                        if name not in next_collections or date_obj < datetime.strptime(next_collections[name]["collectionDate"], "%d/%m/%Y"):
+                            next_collections[name] = bin_entry
+                            print(f"Found next collection for {name}: {formatted_date}")  # Debug output
+                        break
+
+            # Add the next collections to the bin_data
+            bin_data["bins"] = list(next_collections.values())
+
+        except Exception as e:
+            print(f"An error occurred: {e}")
+            raise
+        finally:
+            if driver:
+                driver.quit()
+                
+        print("\nFinal bin data:")
+        print(bin_data)  # Debug output
+        return bin_data

{uk_bin_collection-0.143.6 → uk_bin_collection-0.144.1}/uk_bin_collection/uk_bin_collection/councils/SandwellBoroughCouncil.py

@@ -32,12 +32,13 @@ class CouncilClass(AbstractGetBinDataClass):
             "Referer": "https://my.sandwell.gov.uk/fillform/?iframe_id=fillform-frame-1&db_id=",
         }
         s = requests.session()
+        # Establish a session and grab the session ID
         r = s.get(SESSION_URL)
         r.raise_for_status()
         session_data = r.json()
         sid = session_data["auth-session"]
 
-        data = {
+        payload = {
             "formValues": {
                 "Property details": {
                     "Uprn": {
@@ -49,9 +50,7 @@ class CouncilClass(AbstractGetBinDataClass):
                 },
             },
         }
-
-        params = {
-            "id": "58a1a71694992",
+        base_params = {
             "repeat_against": "",
             "noRetry": "false",
             "getOnlyTokens": "undefined",
@@ -61,27 +60,36 @@ class CouncilClass(AbstractGetBinDataClass):
             "_": str(int(time.time() * 1000)),
             "sid": sid,
         }
+        # (request_id, date field to use from response, bin type labels)
+        lookups = [
+            (
+                "58a1a71694992",
+                "DWDate",
+                [
+                    "Recycling (Blue)",
+                    "Household Waste (Grey)",
+                    "Food Waste (Brown)",
+                    "Batteries",
+                ],
+            ),
+            ("56b1cdaf6bb43", "GWDate", ["Garden Waste (Green)"]),
+        ]
 
-        r = s.post(API_URL, json=data, headers=headers, params=params)
-        r.raise_for_status()
+        for request_id, date_key, bin_types in lookups:
+            params = {"id": request_id, **base_params}
 
-        data = r.json()
-        rows_data = data["integration"]["transformed"]["rows_data"]
-        if not isinstance(rows_data, dict):
-            raise ValueError("Invalid data returned from API")
-        bin_types = {
-            "Recycling (Blue)",
-            "Household Waste (Grey)",
-            "Food Waste (Brown)",
-            "Garden Waste (Green)",
-        }
-        for row in rows_data.items():
-            date = row[1]["DWDate"]
-            for bin_type in bin_types:
-                dict_data = {
-                    "type": bin_type,
-                    "collectionDate": date,
-                }
-                bindata["bins"].append(dict_data)
+            resp = s.post(API_URL, json=payload, headers=headers, params=params)
+            resp.raise_for_status()
+            result = resp.json()
+
+            rows_data = result["integration"]["transformed"]["rows_data"]
+            if not isinstance(rows_data, dict):
+                # Garden waste for some Uprns returns an empty list
+                continue
+
+            for row in rows_data.values():
+                date = row[date_key]
+                for bin_type in bin_types:
+                    bindata["bins"].append({"type": bin_type, "collectionDate": date})
 
         return bindata