add_southkesteven_gov_uk (#2159)

Co-authored-by: 5ila5 <5ila5@users.noreply.github.com>

README.md

@@ -1366,6 +1366,7 @@ Waste collection schedules in the following formats and countries are supported.
 - [South Gloucestershire Council](/doc/source/southglos_gov_uk.md) / southglos.gov.uk
 - [South Hams District Council](/doc/source/fccenvironment_co_uk.md) / southhams.gov.uk
 - [South Holland District Council](/doc/source/sholland_gov_uk.md) / sholland.gov.uk
+- [South Kesteven District Council](/doc/source/southkesteven_gov_uk.md) / southkesteven.gov.uk
 - [South Norfolk Council](/doc/source/south_norfolk_and_broadland_gov_uk.md) / southnorfolkandbroadland.gov.uk
 - [South Oxfordshire District Council](/doc/source/binzone_uk.md) / southoxon.gov.uk
 - [South Somerset District Council](/doc/source/iweb_itouchvision_com.md) / somerset.gov.uk

custom_components/waste_collection_schedule/waste_collection_schedule/source/southkesteven_gov_uk.py

@@ -1,5 +1,6 @@
+import logging
 import re
-from datetime import datetime
+from datetime import datetime, timedelta
 
 import bs4
 import requests
@@ -7,10 +8,13 @@ from waste_collection_schedule import Collection  # type: ignore[attr-defined]
 
 URL = "https://southkesteven.gov.uk"
 TEST_CASES = {
-    "Test_001": {"address_id": 70158},
+    "Long Bennington": {"address_id": 33399},
+    "Bourne": {"address_id": "7351"},
+    "Grantham": {"address_id": 18029},
 }
+_LOGGER = logging.getLogger(__name__)
 ICON_MAP = {
-    "Black": "mdi:trash-can",
+    "black": "mdi:trash-can",
     "gray": "mdi:recycle",
     "purple": "mdi:newspaper",
 }
@@ -38,25 +42,35 @@ class Source:
         r.raise_for_status()
 
         collections = []
-        print(r.text)
         soup = bs4.BeautifulSoup(r.content, "html.parser")
 
+        date_translate = {
+            "Tomorrow": datetime.now().date() + timedelta(days=1),
+            "Today": datetime.now().date(),
+        }
+
         # Find next collection
         # find p looks like                     <p>Your next bin collection date is <span class="alert__heading alpha">Wed 19 June 2024</span></p>
         next_collection_p = soup.find(
-            "p", text=re.compile("Your next bin collection date is")
+            lambda tag: tag.name == "p"
+            and "Your next bin collection date is" in tag.text
         )
         # above does not work so try this
 
-        if next_collection_p is not None:
+        if next_collection_p is None:
+            _LOGGER.warning(
+                "No next collection text found, continuing to look for future collections"
+            )
+        else:
             date_str = next_collection_p.find("span").text
-            date = datetime.strptime(date_str, "%A %d %B %Y").date()
+            date = (
+                date_translate.get(date_str)
+                or datetime.strptime(date_str, "%A %d %B %Y").date()
+            )
             bin_type = NEXT_BIN_TYPE_REGEX.search(
                 next_collection_p.find_next("p").text
             ).group(1)
             collections.append(Collection(date, bin_type, ICON_MAP.get(bin_type)))
-        else:
-            raise ValueError("No next collection found")
 
         # Find all Future collections
         s = soup.find_all("h3", text="Future collections")
@@ -70,13 +84,28 @@ class Source:
                 1
             )
 
-            print(collection_futher_info_link)
-
             for collection in collections_list.find_next_sibling("ul").find_all("li"):
                 # like: "Thu 29 August 2024"
                 date_str = collection.text
 
-                date = datetime.strptime(date_str, "%a %d %B %Y").date()
+                try:
+                    date = (
+                        date_translate.get(date_str)
+                        or datetime.strptime(date_str, "%a %d %B %Y").date()
+                    )
+                except ValueError:
+                    _LOGGER.warning(
+                        f"Failed to parse date {date_str}, skipping this collection"
+                    )
+                    continue
                 collections.append(Collection(date, bin_type, ICON_MAP.get(bin_type)))
 
-        return []
+        # filter out duplicate entries
+        collections = list(
+            {
+                (collection.date, collection.type): collection
+                for collection in collections
+            }.values()
+        )
+
+        return collections

doc/source/southkesteven_gov_uk.md

@@ -0,0 +1,32 @@
+# South Kesteven District Council
+
+Support for schedules provided by [South Kesteven District Council](https://southkesteven.gov.uk)
+
+## Configuration via configuration.yaml
+
+```yaml
+waste_collection_schedule:
+    sources:
+    - name: southkesteven_gov_uk
+      args:
+        address_id: ADDRESS_ID
+```
+
+### Configuration Variables
+
+**address_id**  
+*(int|string) (required)*
+
+## Example
+
+```yaml
+waste_collection_schedule:
+    sources:
+    - name: southkesteven_gov_uk
+      args:
+        address_id: "33399"
+```
+
+## How to find your `address_id`
+
+Go to the [South Kesteven bin collection](https://pre.southkesteven.gov.uk/BinSearch.aspx) website and open search for your address. Either inspect the page where you would select your address (after postcode search) where you can find the `address_id` as value of the `value` attribute of the `option` tag containing your address. Alternatively, you can switch to the network tab of your browser's developer tools and click on "View your bin days" to see the request to the server. The `address_id` is in the payload of the request.