uk_bin_collection 0.159.0__py3-none-any.whl → 0.159.1__py3-none-any.whl

uk_bin_collection/uk_bin_collection/councils/SouthwarkCouncil.py

@@ -1,10 +1,40 @@
-import requests
+from datetime import datetime
+
 from bs4 import BeautifulSoup
 
-from uk_bin_collection.uk_bin_collection.common import *
+from uk_bin_collection.uk_bin_collection.common import check_uprn
 from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
 
 
+def extract_collection_date(section, section_id):
+    """
+    Helper function to safely extract title and collection date from a section.
+    Returns tuple (title, collection_date) or (None, None) if not found.
+    """
+    if not section:
+        return None, None
+
+    title_element = section.find("p", {"id": section_id})
+    if not title_element:
+        return None, None
+
+    title = title_element.get_text(strip=True)
+
+    next_collection_text = section.find(
+        string=lambda t: isinstance(t, str) and "next collection" in t.lower()
+    )
+
+    if not next_collection_text:
+        return title, None
+
+    text = str(next_collection_text).strip()
+    _, sep, rhs = text.partition(":")
+    if not sep:
+        return title, None
+    collection_date = rhs.strip()
+    return title, collection_date
+
+
 # import the wonderful Beautiful Soup and the URL grabber
 class CouncilClass(AbstractGetBinDataClass):
     """
@@ -22,141 +52,39 @@ class CouncilClass(AbstractGetBinDataClass):
         baseurl = "https://services.southwark.gov.uk/bins/lookup/"
         url = baseurl + user_uprn
 
-        headers = {
-            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36"
-        }
-
-        # Make the web request
-        response = requests.get(url, headers=headers).text
+        # Make the web request using the common helper (standard UA, timeout, logging)
+        response = self.get_data(url).text
 
         soup = BeautifulSoup(response, "html.parser")
-
-        # Extract recycling collection information
-        recycling_section = soup.find(
-            "div", {"aria-labelledby": "recyclingCollectionTitle"}
-        )
-        if recycling_section:
-            recycling_title = recycling_section.find(
-                "p", {"id": "recyclingCollectionTitle"}
-            ).text
-            recycling_next_collection = (
-                recycling_section.find(text=lambda text: "Next collection" in text)
-                .strip()
-                .split(": ")[1]
-            )
-
-            dict_data = {
-                "type": recycling_title,
-                "collectionDate": datetime.strptime(
-                    recycling_next_collection, "%a, %d %B %Y"
-                ).strftime("%d/%m/%Y"),
-            }
-            data["bins"].append(dict_data)
-
-        # Extract refuse collection information
-        refuse_section = soup.find("div", {"aria-labelledby": "refuseCollectionTitle"})
-        if refuse_section:
-            refuse_title = refuse_section.find(
-                "p", {"id": "refuseCollectionTitle"}
-            ).text
-            refuse_next_collection = (
-                refuse_section.find(text=lambda text: "Next collection" in text)
-                .strip()
-                .split(": ")[1]
-            )
-
-            dict_data = {
-                "type": refuse_title,
-                "collectionDate": datetime.strptime(
-                    refuse_next_collection, "%a, %d %B %Y"
-                ).strftime("%d/%m/%Y"),
-            }
-            data["bins"].append(dict_data)
-
-        # Extract food waste collection information
-        food_section = soup.find(
-            "div", {"aria-labelledby": "domesticFoodCollectionTitle"}
-        )
-        if food_section:
-            food_title = food_section.find(
-                "p", {"id": "domesticFoodCollectionTitle"}
-            ).text
-            food_next_collection = (
-                food_section.find(text=lambda text: "Next collection" in text)
-                .strip()
-                .split(": ")[1]
-            )
-
-            dict_data = {
-                "type": food_title,
-                "collectionDate": datetime.strptime(
-                    food_next_collection, "%a, %d %B %Y"
-                ).strftime("%d/%m/%Y"),
-            }
-            data["bins"].append(dict_data)
-
-        # Extract communal food waste collection information
-        comfood_section = soup.find(
-            "div", {"aria-labelledby": "communalFoodCollectionTitle"}
-        )
-        if comfood_section:
-            comfood_title = comfood_section.find(
-                "p", {"id": "communalFoodCollectionTitle"}
-            ).text
-            comfood_next_collection = (
-                comfood_section.find(text=lambda text: "Next collection" in text)
-                .strip()
-                .split(": ")[1]
-            )
-
-            dict_data = {
-                "type": comfood_title,
-                "collectionDate": datetime.strptime(
-                    comfood_next_collection, "%a, %d %B %Y"
-                ).strftime("%d/%m/%Y"),
-            }
-            data["bins"].append(dict_data)
-
-        comrec_section = soup.find(
-            "div", {"aria-labelledby": "recyclingCommunalCollectionTitle"}
+        # Extract collection information for all bin types
+        section_ids = (
+            "recyclingCollectionTitle",
+            "refuseCollectionTitle",
+            "domesticFoodCollectionTitle",
+            "communalFoodCollectionTitle",
+            "recyclingCommunalCollectionTitle",
+            "refuseCommunalCollectionTitle",
         )
-        if comrec_section:
-            comrec_title = comrec_section.find(
-                "p", {"id": "recyclingCommunalCollectionTitle"}
-            ).text
-            comrec_next_collection = (
-                comrec_section.find(text=lambda text: "Next collection" in text)
-                .strip()
-                .split(": ")[1]
-            )
 
-            dict_data = {
-                "type": comrec_title,
-                "collectionDate": datetime.strptime(
-                    comrec_next_collection, "%a, %d %B %Y"
-                ).strftime("%d/%m/%Y"),
-            }
-            data["bins"].append(dict_data)
-
-        comref_section = soup.find(
-            "div", {"aria-labelledby": "refuseCommunalCollectionTitle"}
-        )
-        if comref_section:
-            comref_title = comref_section.find(
-                "p", {"id": "refuseCommunalCollectionTitle"}
-            ).text
-            comref_next_collection = (
-                comref_section.find(text=lambda text: "Next collection" in text)
-                .strip()
-                .split(": ")[1]
+        for section_id in section_ids:
+            section = soup.find("div", {"aria-labelledby": section_id})
+            if not section:
+                continue
+
+            title, next_collection = extract_collection_date(section, section_id)
+            if not (title and next_collection):
+                continue
+
+            try:
+                parsed = datetime.strptime(next_collection, "%a, %d %B %Y")
+            except ValueError:
+                continue
+
+            data["bins"].append(
+                {
+                    "type": title,
+                    "collectionDate": parsed.strftime("%d/%m/%Y"),
+                }
             )
 
-            dict_data = {
-                "type": comref_title,
-                "collectionDate": datetime.strptime(
-                    comref_next_collection, "%a, %d %B %Y"
-                ).strftime("%d/%m/%Y"),
-            }
-            data["bins"].append(dict_data)
-
-        return data
+        return data

{uk_bin_collection-0.159.0.dist-info → uk_bin_collection-0.159.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.159.0
+Version: 0.159.1
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.159.0.dist-info → uk_bin_collection-0.159.1.dist-info}/RECORD

@@ -276,7 +276,7 @@ uk_bin_collection/uk_bin_collection/councils/SouthRibbleCouncil.py,sha256=juX7pg
 uk_bin_collection/uk_bin_collection/councils/SouthStaffordshireDistrictCouncil.py,sha256=ACQMHWyamnj1ag3gNF-8Jhp-DKUok1GhFdnzH4nCzwU,3201
 uk_bin_collection/uk_bin_collection/councils/SouthTynesideCouncil.py,sha256=dxXGrJfg_fn2IPTBgq6Duwy0WY8GYLafMuisaCjOnbs,3426
 uk_bin_collection/uk_bin_collection/councils/SouthamptonCityCouncil.py,sha256=exNoI-Vun_C5FowCYhZ_600MBUe_OPR7MdGZEMNLL0I,1542
-uk_bin_collection/uk_bin_collection/councils/SouthwarkCouncil.py,sha256=xgxOKyy-jFKOl_5zYaJovr0ijEMN20ssOSB7I7Jtfhw,5685
+uk_bin_collection/uk_bin_collection/councils/SouthwarkCouncil.py,sha256=AR4qv12oHkMRmNb62pk0IByeOQ7ePh-FnxrK4TWqM0E,2772
 uk_bin_collection/uk_bin_collection/councils/SpelthorneBoroughCouncil.py,sha256=iamG0wxIyYprttJPVc0jdbOoHavc1AmRpMhyc02MUrE,5703
 uk_bin_collection/uk_bin_collection/councils/StAlbansCityAndDistrictCouncil.py,sha256=mPZz6Za6kTSkrfHnj0OfwtnpRYR1dKvxbuFEKnWsiL8,1451
 uk_bin_collection/uk_bin_collection/councils/StHelensBC.py,sha256=X9dvnQTNn7QUO8gv1A587e1aDI92TWN4iNLATTn3H3w,4777
@@ -350,8 +350,8 @@ uk_bin_collection/uk_bin_collection/councils/tests/test_south_kesteven_district_
 uk_bin_collection/uk_bin_collection/councils/tests/test_south_kesteven_integration.py,sha256=ax_kevIIB1BpDTVjEnoiZnDk0srkc1Vw7B2i5XLLqiE,6647
 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=Qb76X46V0UMZJwO8zMNPvnVY7jNa-bmTlrirDi1tuJA,4553
-uk_bin_collection-0.159.0.dist-info/LICENSE,sha256=vABBUOzcrgfaTKpzeo-si9YVEun6juDkndqA8RKdKGs,1071
-uk_bin_collection-0.159.0.dist-info/METADATA,sha256=P0cd-TTHh50QbuBkadrZ-QSykQIQLQnVTCknm-vJu0k,26769
-uk_bin_collection-0.159.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-uk_bin_collection-0.159.0.dist-info/entry_points.txt,sha256=36WCSGMWSc916S3Hi1ZkazzDKHaJ6CD-4fCEFm5MIao,90
-uk_bin_collection-0.159.0.dist-info/RECORD,,
+uk_bin_collection-0.159.1.dist-info/LICENSE,sha256=vABBUOzcrgfaTKpzeo-si9YVEun6juDkndqA8RKdKGs,1071
+uk_bin_collection-0.159.1.dist-info/METADATA,sha256=ea00NlOlSDzueVpUIYwsoIOyerpqMHlcr8fz2MQIvkw,26769
+uk_bin_collection-0.159.1.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+uk_bin_collection-0.159.1.dist-info/entry_points.txt,sha256=36WCSGMWSc916S3Hi1ZkazzDKHaJ6CD-4fCEFm5MIao,90
+uk_bin_collection-0.159.1.dist-info/RECORD,,