uk_bin_collection 0.149.0__tar.gz → 0.150.1__tar.gz

{uk_bin_collection-0.149.0 → uk_bin_collection-0.150.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.149.0
+Version: 0.150.1
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.149.0 → uk_bin_collection-0.150.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.149.0"
+version = "0.150.1"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.149.0 → uk_bin_collection-0.150.1}/uk_bin_collection/tests/input.json

@@ -222,12 +222,10 @@
         "LAD24CD": "E07000129"
     },
     "BlackburnCouncil": {
+        "url": "https://www.blaby.gov.uk",
         "LAD24CD": "E06000008",
         "skip_get_url": true,
         "uprn": "100010733027",
-        "url": "https://mybins.blackburn.gov.uk/api/mybins/getbincollectiondays?uprn=100010733027&month=8&year=2022",
-        "web_driver": "http://selenium:4444",
-        "wiki_command_url_override": "https://www.blackburn.gov.uk",
         "wiki_name": "Blackburn with Darwen",
         "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN."
     },
@@ -1436,6 +1434,13 @@
         "wiki_note": "Pass the UPRN. You can find it using [FindMyAddress](https://www.findmyaddress.co.uk/search).",
         "LAD24CD": "E06000035"
     },
+    "MeltonBoroughCouncil": {
+        "uprn": "100030540956",
+        "url": "https://my.melton.gov.uk/collections",
+        "wiki_name": "Melton",
+        "wiki_note": "To get the UPRN, you can use [FindMyAddress](https://www.findmyaddress.co.uk/search).",
+        "LAD24CD": "E07000133"
+    },
     "MertonCouncil": {
         "url": "https://myneighbourhood.merton.gov.uk/wasteservices/WasteServices.aspx?ID=25936129",
         "wiki_command_url_override": "https://myneighbourhood.merton.gov.uk/Wasteservices/WasteServices.aspx?ID=XXXXXXXX",
@@ -1483,7 +1488,7 @@
     "MiddlesbroughCouncil": {
         "house_number": "12 Constantine Court Park Road North, Middlesbrough",
         "skip_get_url": true,
-        "url": "https://www.midsussex.gov.uk/waste-recycling/bin-collection/",
+        "url": "https://www.middlesbrough.gov.uk/recycling-and-rubbish/bin-collection-dates/",
         "web_driver": "http://selenium:4444",
         "wiki_name": "Middlesbrough",
         "wiki_note": "Pass the entire address without postcode as it appears when you type it on the website. This parser requires a Selenium webdriver.",
@@ -1532,7 +1537,7 @@
         "LAD24CD": "W06000021"
     },
     "MorayCouncil": {
-        "uprn": "28841",
+        "uprn": "45438",
         "url": "https://bindayfinder.moray.gov.uk/",
         "wiki_name": "Moray",
         "wiki_note": "Find your property ID by going to (https://bindayfinder.moray.gov.uk), search for your property and extracting the ID from the URL. i.e. (https://bindayfinder.moray.gov.uk/disp_bins.php?id=00028841)",

uk_bin_collection-0.150.1/uk_bin_collection/uk_bin_collection/councils/MeltonBoroughCouncil.py

@@ -0,0 +1,82 @@
+import json
+from datetime import datetime, timedelta
+
+import requests
+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 extract_dates(self, date_string: str) -> list:
+        """
+        Extract dates from strings like "01/05/2025, and then 15/05/2025"
+        Returns list of datetime objects
+        """
+        date_string = date_string.replace("and then", ",")
+        date_parts = [part.strip() for part in date_string.split(",") if part.strip()]
+
+        dates = []
+        for part in date_parts:
+            try:
+                date_obj = datetime.strptime(part, "%d/%m/%Y")
+                dates.append(date_obj)
+            except ValueError:
+                continue
+
+        return dates
+
+    def parse_data(self, page: str, **kwargs) -> dict:
+        user_uprn = kwargs.get("uprn")
+        check_uprn(user_uprn)
+
+        url = f"https://my.melton.gov.uk/set-location?id={user_uprn}&redirect=collections&rememberloc="
+        response = requests.get(url)
+        soup = BeautifulSoup(response.text, "html.parser")
+
+        collections = []
+
+        # Find all box items
+        box_items = soup.find_all("li", class_=lambda x: x and x.startswith("box-item"))
+
+        for box in box_items:
+            bin_type = box.find("h2")
+            if (
+                bin_type and "Missed bin" not in bin_type.text
+            ):  # Skip the "Missed bin" section
+                bin_name = bin_type.text.strip()
+
+                # Find the strong tag containing dates
+                dates_element = box.find("strong")
+                if dates_element:
+                    dates_text = dates_element.text.strip()
+                    # Use self.extract_dates instead of extract_dates
+                    collection_dates = self.extract_dates(dates_text)
+
+                    # Add each date for this bin type to collections
+                    for date in collection_dates:
+                        collections.append((bin_name, date))
+
+        # Sort the collections by date
+        ordered_data = sorted(collections, key=lambda x: x[1])
+
+        # Format the data as required
+        data = {"bins": []}
+        for item in ordered_data:
+            dict_data = {
+                "type": item[0],
+                "collectionDate": item[1].strftime(date_format),
+            }
+            data["bins"].append(dict_data)
+
+        print(json.dumps(data, indent=2))
+
+        return data

uk_bin_collection-0.150.1/uk_bin_collection/uk_bin_collection/councils/MorayCouncil.py

@@ -0,0 +1,83 @@
+import requests
+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:
+        user_uprn = kwargs.get("uprn")
+        print(f"Using UPRN: {user_uprn}")  # Debug
+        bindata = {"bins": []}
+
+        user_uprn = user_uprn.zfill(8)
+
+        url = f"https://bindayfinder.moray.gov.uk/disp_bins.php?id={user_uprn}"
+
+        # year = datetime.today().year
+        # url = f"https://bindayfinder.moray.gov.uk/cal_{year}_view.php"
+        print(f"Trying URL: {url}")  # Debug
+
+        response = requests.get(url)
+        print(f"Response status code: {response.status_code}")  # Debug
+
+        # if response.status_code != 200:
+        #     fallback_url = "https://bindayfinder.moray.gov.uk/cal_2024_view.php"
+        #     print(f"Falling back to: {fallback_url}")  # Debug
+        #     response = requests.get(
+        #         fallback_url,
+        #         params={"id": user_uprn},
+        #     )
+        #     print(f"Fallback response status: {response.status_code}")  # Debug
+
+        soup = BeautifulSoup(response.text, "html.parser")
+
+        # Find all container_images divs
+        container_images = soup.find_all("div", class_="container_images")
+        print(f"Found {len(container_images)} container images")  # Debug
+
+        for container in container_images:
+            # Get bin type from image alt text
+            img = container.find("img")
+            if img and img.get("alt"):
+                # Use the full alt text as one bin type instead of splitting
+                bin_type = img["alt"]
+                print(f"Found bin type: {bin_type}")  # Debug
+
+            # Get collection date from binz_txt
+            date_text = container.find("div", class_="binz_txt")
+            if date_text:
+                date_str = date_text.text
+                print(f"Found date text: {date_str}")  # Debug
+
+                # Extract just the date portion
+                import re
+
+                date_match = re.search(r"(\d{1,2}\s+[A-Za-z]+\s+\d{4})", date_str)
+                if date_match:
+                    date_portion = date_match.group(1)
+                    try:
+                        # Convert the date string to the required format
+                        parsed_date = datetime.strptime(date_portion, "%d %B %Y")
+                        collection_date = parsed_date.strftime("%d/%m/%Y")
+                        print(f"Parsed date: {collection_date}")  # Debug
+
+                        dict_data = {
+                            "type": bin_type,
+                            "collectionDate": collection_date,
+                        }
+                        bindata["bins"].append(dict_data)
+                    except ValueError as e:
+                        print(f"Error parsing date: {e}")  # Debug
+                        continue
+
+        print(f"Final bindata: {bindata}")  # Debug
+        return bindata

uk_bin_collection-0.149.0/uk_bin_collection/uk_bin_collection/councils/MorayCouncil.py

@@ -1,65 +0,0 @@
-import requests
-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:
-
-        user_uprn = kwargs.get("uprn")
-        bindata = {"bins": []}
-
-        user_uprn = user_uprn.zfill(8)
-
-        year = datetime.today().year
-        response = requests.get(
-            f"https://bindayfinder.moray.gov.uk/cal_{year}_view.php",
-            params={"id": user_uprn},
-        )
-        if response.status_code != 200:
-            # fall back to known good calendar URL
-            response = requests.get(
-                "https://bindayfinder.moray.gov.uk/cal_2024_view.php",
-                params={"id": user_uprn},
-            )
-        soup = BeautifulSoup(response.text, "html.parser")
-
-        bin_types = {
-            "G": "Green",
-            "B": "Brown",
-            "P": "Purple",
-            "C": "Blue",
-            "O": "Orange",
-        }
-
-        for month_container in soup.findAll("div", class_="month-container"):
-            for div in month_container.findAll("div"):
-                if "month-header" in div["class"]:
-                    month = div.text
-                elif div["class"] and div["class"][0] in ["B", "GPOC", "GBPOC"]:
-                    bins = div["class"][0]
-                    dom = int(div.text)
-                    for i in bins:
-                        dict_data = {
-                            "type": bin_types.get(i),
-                            "collectionDate": datetime.strptime(
-                                f"{dom} {month} {year}",
-                                "%d %B %Y",
-                            ).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