uk_bin_collection 0.159.0__tar.gz → 0.159.2__tar.gz

{uk_bin_collection-0.159.0 → uk_bin_collection-0.159.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.159.0
+Version: 0.159.2
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com
@@ -14,7 +14,7 @@ Requires-Dist: holidays
 Requires-Dist: icalevents (>=0.2.1,<0.3.0)
 Requires-Dist: lxml
 Requires-Dist: pandas
-Requires-Dist: pillow (>=10.0.0,<11.0.0)
+Requires-Dist: pillow (>=10.0.0)
 Requires-Dist: python-dateutil
 Requires-Dist: requests
 Requires-Dist: selenium

{uk_bin_collection-0.159.0 → uk_bin_collection-0.159.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.159.0"
+version = "0.159.2"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]
@@ -64,7 +64,7 @@ webdriver-manager = "^4.0.1"
 tabulate = "^0.9.0"
 icalevents = "^0.2.1"
 easyocr = "^1.7.0"
-pillow = "^10.0.0"
+pillow = ">=10.0.0"
 
 [tool.commitizen]
 name = "cz_conventional_commits"

uk_bin_collection-0.159.2/uk_bin_collection/uk_bin_collection/councils/SouthwarkCouncil.py

@@ -0,0 +1,90 @@
+from datetime import datetime
+
+from bs4 import BeautifulSoup
+
+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):
+    """
+    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")
+        check_uprn(user_uprn)
+        data = {"bins": []}
+
+        baseurl = "https://services.southwark.gov.uk/bins/lookup/"
+        url = baseurl + user_uprn
+
+        # Make the web request using the common helper (standard UA, timeout, logging)
+        response = self.get_data(url).text
+
+        soup = BeautifulSoup(response, "html.parser")
+        # Extract collection information for all bin types
+        section_ids = (
+            "recyclingCollectionTitle",
+            "refuseCollectionTitle",
+            "domesticFoodCollectionTitle",
+            "communalFoodCollectionTitle",
+            "recyclingCommunalCollectionTitle",
+            "refuseCommunalCollectionTitle",
+        )
+
+        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"),
+                }
+            )
+
+        return data

uk_bin_collection-0.159.0/uk_bin_collection/uk_bin_collection/councils/SouthwarkCouncil.py

@@ -1,162 +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")
-        check_uprn(user_uprn)
-        data = {"bins": []}
-
-        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
-
-        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"}
-        )
-        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]
-            )
-
-            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