uk_bin_collection 0.148.6__py3-none-any.whl → 0.150.0__py3-none-any.whl

uk_bin_collection/tests/input.json

@@ -1436,6 +1436,13 @@
         "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 +1490,7 @@
     "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 +1539,7 @@
         "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)",
@@ -1772,6 +1779,13 @@
         "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN.",
         "LAD24CD": "E07000178"
     },
+    "PembrokeshireCountyCouncil": {
+        "url": "https://nearest.pembrokeshire.gov.uk/property/100100278790",
+        "wiki_command_url_override": "https://nearest.pembrokeshire.gov.uk/property/XXXXXXXXXX",
+        "wiki_name": "Pembrokeshire",
+        "wiki_note": "Replace XXXXXXXX with your UPRN. You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find it.",
+        "LAD24CD": "W06000009"
+    },
     "PeterboroughCityCouncil": {
         "house_number": "7 Arundel Road, Peterborough, PE4 6JJ",
         "postcode": "PE4 6JJ",

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/uk_bin_collection/councils/MorayCouncil.py

@@ -14,52 +14,70 @@ class CouncilClass(AbstractGetBinDataClass):
     """
 
     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)
 
-        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},
-            )
+        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")
 
-        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:
+        # 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_types.get(i),
-                            "collectionDate": datetime.strptime(
-                                f"{dom} {month} {year}",
-                                "%d %B %Y",
-                            ).strftime("%d/%m/%Y"),
+                            "type": bin_type,
+                            "collectionDate": collection_date,
                         }
                         bindata["bins"].append(dict_data)
+                    except ValueError as e:
+                        print(f"Error parsing date: {e}")  # Debug
+                        continue
 
-        bindata["bins"].sort(
-            key=lambda x: datetime.strptime(x.get("collectionDate"), "%d/%m/%Y")
-        )
-
+        print(f"Final bindata: {bindata}")  # Debug
         return bindata

uk_bin_collection/uk_bin_collection/councils/PembrokeshireCountyCouncil.py

@@ -0,0 +1,96 @@
+from datetime import datetime
+
+import bs4.element
+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
+
+
+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 BeautifulSoup object
+        soup = BeautifulSoup(page.text, features="html.parser")
+
+        data = {"bins": []}
+
+        # Locate the section containing bin collection data
+        bin_collection_divs = soup.find_all(
+            "div", class_="col-6 col-md-4 text-center mb-3"
+        )
+
+        if not bin_collection_divs:
+            raise ValueError("No bin collection data found in the provided HTML.")
+
+        for bin_div in bin_collection_divs:
+            # Get the image tag first to check if this is a bin collection div
+            img_tag = bin_div.find("img")
+            if (
+                not img_tag
+                or not img_tag.get("src")
+                or "pembrokeshire.gov.uk/images" not in img_tag["src"]
+            ):
+                continue
+
+            # Extract bin type - first try the image title
+            bin_type = None
+            if img_tag.get("title"):
+                bin_type = img_tag["title"].strip()
+
+            # If no title, get all text nodes and join them
+            if not bin_type:
+                # Get all text nodes that are not within a <strong> tag (to exclude the date)
+                text_nodes = [
+                    text.strip()
+                    for text in bin_div.find_all(text=True, recursive=True)
+                    if text.strip()
+                    and not isinstance(text.parent, bs4.element.Tag)
+                    or text.parent.name != "strong"
+                ]
+                if text_nodes:
+                    bin_type = " ".join(text_nodes).strip()
+
+            if not bin_type:
+                continue  # Skip if we couldn't find a bin type
+
+            # Extract collection date
+            bin_date_tag = bin_div.find("strong")
+            if not bin_date_tag:
+                continue  # Skip if no date found
+
+            bin_date = bin_date_tag.text.strip()
+
+            try:
+                # Parse the date into a datetime object
+                collection_date = datetime.strptime(bin_date, "%d/%m/%Y")
+                # Format date back to DD/MM/YYYY format as required by schema
+                formatted_date = collection_date.strftime("%d/%m/%Y")
+            except ValueError:
+                continue  # Skip if date parsing fails
+
+            # Append the bin data to the list
+            dict_data = {
+                "type": bin_type,
+                "collectionDate": formatted_date,
+            }
+            data["bins"].append(dict_data)
+
+        if not data["bins"]:
+            raise ValueError(
+                "No valid bin collection data could be parsed from the HTML."
+            )
+
+        # Sort the bins by collection date
+        data["bins"].sort(
+            key=lambda x: datetime.strptime(x["collectionDate"], "%d/%m/%Y")
+        )
+
+        print(data)
+
+        return data

{uk_bin_collection-0.148.6.dist-info → uk_bin_collection-0.150.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.148.6
+Version: 0.150.0
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.148.6.dist-info → uk_bin_collection-0.150.0.dist-info}/RECORD

@@ -7,7 +7,7 @@ uk_bin_collection/tests/council_feature_input_parity.py,sha256=DO6Mk4ImYgM5ZCZ-c
 uk_bin_collection/tests/features/environment.py,sha256=VQZjJdJI_kZn08M0j5cUgvKT4k3iTw8icJge1DGOkoA,127
 uk_bin_collection/tests/features/validate_council_outputs.feature,sha256=SJK-Vc737hrf03tssxxbeg_JIvAH-ddB8f6gU1LTbuQ,251
 uk_bin_collection/tests/generate_map_test_results.py,sha256=CKnGK2ZgiSXomRGkomX90DitgMP-X7wkHhyKORDcL2E,1144
-uk_bin_collection/tests/input.json,sha256=WD2BCIhsrpbU_53tvTPnHW7MQXiOYowTzkKN4UtuI9E,131240
+uk_bin_collection/tests/input.json,sha256=A-3wFKuCCIS11YpMknZHsGtz3cv-cojKuu6lFqfPkIY,131984
 uk_bin_collection/tests/output.schema,sha256=ZwKQBwYyTDEM4G2hJwfLUVM-5v1vKRvRK9W9SS1sd18,1086
 uk_bin_collection/tests/step_defs/step_helpers/file_handler.py,sha256=Ygzi4V0S1MIHqbdstUlIqtRIwnynvhu4UtpweJ6-5N8,1474
 uk_bin_collection/tests/step_defs/test_validate_council.py,sha256=VZ0a81sioJULD7syAYHjvK_-nT_Rd36tUyzPetSA0gk,3475
@@ -184,6 +184,7 @@ uk_bin_collection/uk_bin_collection/councils/MalvernHillsDC.py,sha256=iQG0EkX2np
 uk_bin_collection/uk_bin_collection/councils/ManchesterCityCouncil.py,sha256=RY301_82z3-xInGai5ocT7rzoV75ATbf0N7uxn8Z9LE,3110
 uk_bin_collection/uk_bin_collection/councils/MansfieldDistrictCouncil.py,sha256=F5AiTxImrnjE1k3ry96bfstOf5XSNBJS_4qqmymmh3w,1386
 uk_bin_collection/uk_bin_collection/councils/MedwayCouncil.py,sha256=nBJSv09OUOascrfNu1ek1wNzE9ONu5ZkrBU-1qwDHJ0,1278
+uk_bin_collection/uk_bin_collection/councils/MeltonBoroughCouncil.py,sha256=Xql_ydrk59nx3dPok6YSVZ7mk8GJT2-IKOGqILgE0xU,2802
 uk_bin_collection/uk_bin_collection/councils/MertonCouncil.py,sha256=xsOSX4KCcUHHo4BHB5JhFC9r5Q-h586Vk-5-X2VAJl0,2809
 uk_bin_collection/uk_bin_collection/councils/MidAndEastAntrimBoroughCouncil.py,sha256=oOWwU5FSgGej2Mv7FQ66N-EzS5nZgmGsd0WnfLWUc1I,5238
 uk_bin_collection/uk_bin_collection/councils/MidDevonCouncil.py,sha256=8MxqGgOJVseMkrTmEMT0EyDW7UMbXMoa5ZcJ2nD55Ew,3367
@@ -195,7 +196,7 @@ uk_bin_collection/uk_bin_collection/councils/MidlothianCouncil.py,sha256=-VKvdIh
 uk_bin_collection/uk_bin_collection/councils/MiltonKeynesCityCouncil.py,sha256=7e2pGBLCw24pNItHeI9jkxQ3rEOZ4WC4zVlbvKYGdXE,2600
 uk_bin_collection/uk_bin_collection/councils/MoleValleyDistrictCouncil.py,sha256=xWR5S0gwQu9gXxjl788Wux1KaC0CT7ZFw0iXuRLZCEM,5599
 uk_bin_collection/uk_bin_collection/councils/MonmouthshireCountyCouncil.py,sha256=PC2tui10S-DXmiKUqXZun5MInIgqqQjtT5wII1K_9a0,2532
-uk_bin_collection/uk_bin_collection/councils/MorayCouncil.py,sha256=jsHCQ_aV_bG0GPfF7h6g5TP84sroplYC5k2M6iEKiTw,2265
+uk_bin_collection/uk_bin_collection/councils/MorayCouncil.py,sha256=B8unofp2x1HF72QT_3E0Iew78PWMywjzkNDJdWof2Tc,3309
 uk_bin_collection/uk_bin_collection/councils/NeathPortTalbotCouncil.py,sha256=p95UYogx3_WJ_1kgfeH5kGQdrZ3YyEJjVuZ7WOOPAvs,5710
 uk_bin_collection/uk_bin_collection/councils/NewForestCouncil.py,sha256=Vdmv_p75OJwSeltWE5wZhE8wy5XW0CIKIn1cKNvI0pQ,5336
 uk_bin_collection/uk_bin_collection/councils/NewarkAndSherwoodDC.py,sha256=lAleYfCGUWCKOi7Ye_cjgfpI3pWwTcFctlYmh0hjebM,2140
@@ -224,6 +225,7 @@ uk_bin_collection/uk_bin_collection/councils/NuneatonBedworthBoroughCouncil.py,s
 uk_bin_collection/uk_bin_collection/councils/OadbyAndWigstonBoroughCouncil.py,sha256=Kgy5HA0xZ9hR4_cAydPfOfskhGUB4j93AQF2-9Fj-Cg,2179
 uk_bin_collection/uk_bin_collection/councils/OldhamCouncil.py,sha256=9dlesCxNoVXlmQaqZj7QFh00smnJbm1Gnjkr_Uvzurs,1771
 uk_bin_collection/uk_bin_collection/councils/OxfordCityCouncil.py,sha256=d_bY0cXRDH4kSoWGGCTNN61MNErapSOf2WSTYDJr2r8,2318
+uk_bin_collection/uk_bin_collection/councils/PembrokeshireCountyCouncil.py,sha256=GRAxjf_DuO5uZ660kEbZt_yCjP3n2maMxsYTPCTz3GQ,3324
 uk_bin_collection/uk_bin_collection/councils/PerthAndKinrossCouncil.py,sha256=Kos5GzN2co3Ij3tSHOXB9S71Yt78RROCfVRtnh7M1VU,3657
 uk_bin_collection/uk_bin_collection/councils/PeterboroughCityCouncil.py,sha256=lOrDD4jfJ-_C5UwCGqRcQ1G-U1F5X6rf255ypzYEBcg,6300
 uk_bin_collection/uk_bin_collection/councils/PlymouthCouncil.py,sha256=FJqpJ0GJhpjYeyZ9ioZPkKGl-zrqMD3y5iKa07e_i30,3202
@@ -337,8 +339,8 @@ uk_bin_collection/uk_bin_collection/councils/YorkCouncil.py,sha256=I2kBYMlsD4bId
 uk_bin_collection/uk_bin_collection/councils/council_class_template/councilclasstemplate.py,sha256=QD4v4xpsEE0QheR_fGaNOIRMc2FatcUfKkkhAhseyVU,1159
 uk_bin_collection/uk_bin_collection/create_new_council.py,sha256=m-IhmWmeWQlFsTZC4OxuFvtw5ZtB8EAJHxJTH4O59lQ,1536
 uk_bin_collection/uk_bin_collection/get_bin_data.py,sha256=YvmHfZqanwrJ8ToGch34x-L-7yPe31nB_x77_Mgl_vo,4545
-uk_bin_collection-0.148.6.dist-info/LICENSE,sha256=vABBUOzcrgfaTKpzeo-si9YVEun6juDkndqA8RKdKGs,1071
-uk_bin_collection-0.148.6.dist-info/METADATA,sha256=w-ll8-C6yznvAJKkIyof53UFTDki9OGprblylgnCglc,20914
-uk_bin_collection-0.148.6.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-uk_bin_collection-0.148.6.dist-info/entry_points.txt,sha256=36WCSGMWSc916S3Hi1ZkazzDKHaJ6CD-4fCEFm5MIao,90
-uk_bin_collection-0.148.6.dist-info/RECORD,,
+uk_bin_collection-0.150.0.dist-info/LICENSE,sha256=vABBUOzcrgfaTKpzeo-si9YVEun6juDkndqA8RKdKGs,1071
+uk_bin_collection-0.150.0.dist-info/METADATA,sha256=HiNbfbMdwcpyKKz8YaAvrwvc_L1pQS4CeppVTKlYycA,20914
+uk_bin_collection-0.150.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+uk_bin_collection-0.150.0.dist-info/entry_points.txt,sha256=36WCSGMWSc916S3Hi1ZkazzDKHaJ6CD-4fCEFm5MIao,90
+uk_bin_collection-0.150.0.dist-info/RECORD,,