uk_bin_collection 0.157.0__tar.gz → 0.158.0__tar.gz

{uk_bin_collection-0.157.0 → uk_bin_collection-0.158.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.157.0
+Version: 0.158.0
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.157.0 → uk_bin_collection-0.158.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.157.0"
+version = "0.158.0"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

uk_bin_collection-0.158.0/uk_bin_collection/uk_bin_collection/councils/LondonBoroughSutton.py

@@ -0,0 +1,90 @@
+import requests
+from bs4 import BeautifulSoup
+from datetime import datetime
+import re
+from time import sleep
+
+from uk_bin_collection.uk_bin_collection.common import *
+from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
+
+def remove_ordinal_indicator_from_date_string(date_str):
+    return re.sub(r'(\d+)(st|nd|rd|th)', r'\1', date_str)
+
+class CouncilClass(AbstractGetBinDataClass):
+
+    def parse_data(self, page: str, **kwargs) -> dict:
+        user_uprn = kwargs.get("uprn")
+        bindata = {"bins": []}
+
+        URI = f"https://waste-services.sutton.gov.uk/waste/{user_uprn}"
+
+        s = requests.Session()
+        r = s.get(URI)
+        while "Loading your bin days..." in r.text:
+            sleep(2)
+            r = s.get(URI)
+        r.raise_for_status()
+
+        soup = BeautifulSoup(r.content, "html.parser")
+        current_year = datetime.now().year
+        next_year = current_year + 1
+
+        # Find all h3 headers (bin types)
+        services = soup.find_all("h3")
+        for service in services:
+            bin_type = service.get_text(strip=True)
+            if "Bulky Waste" in bin_type:
+                continue
+
+            # Find the next element (next sibling) which is likely a paragraph with date info
+            next_sib = service.find_next_sibling()
+            while next_sib and getattr(next_sib, 'name', None) not in [None, 'p']:
+                next_sib = next_sib.find_next_sibling()
+
+            next_coll = None
+            if next_sib:
+                text = next_sib.get_text() if hasattr(next_sib, 'get_text') else str(next_sib)
+                match = re.search(r"Next collection\s*([A-Za-z]+,? \d{1,2}(?:st|nd|rd|th)? [A-Za-z]+)", text)
+                if match:
+                    next_coll = match.group(1)
+                else:
+                    # Sometimes the text may be attached without a space after 'Next collection'
+                    match = re.search(r"Next collection([A-Za-z]+,? \d{1,2}(?:st|nd|rd|th)? [A-Za-z]+)", text)
+                    if match:
+                        next_coll = match.group(1)
+
+            # Try several siblings forward if not found
+            if not next_coll:
+                sib_try = service
+                for _ in range(3):
+                    if sib_try:
+                        sib_try = sib_try.find_next_sibling()
+                    else:
+                        break
+                    if sib_try:
+                        text = sib_try.get_text() if hasattr(sib_try, 'get_text') else str(sib_try)
+                        match = re.search(r"Next collection\s*([A-Za-z]+,? \d{1,2}(?:st|nd|rd|th)? [A-Za-z]+)", text)
+                        if match:
+                            next_coll = match.group(1)
+                            break
+
+            if next_coll:
+                next_coll = remove_ordinal_indicator_from_date_string(next_coll)
+                try:
+                    next_collection = datetime.strptime(next_coll, "%A, %d %B")
+                except ValueError:
+                    continue
+
+                if (datetime.now().month == 12 and next_collection.month == 1):
+                    next_collection = next_collection.replace(year=next_year)
+                else:
+                    next_collection = next_collection.replace(year=current_year)
+
+                dict_data = {
+                    "type": bin_type,
+                    "collectionDate": next_collection.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

uk_bin_collection-0.157.0/uk_bin_collection/uk_bin_collection/councils/LondonBoroughSutton.py

@@ -1,79 +0,0 @@
-from time import sleep
-
-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)
-        bindata = {"bins": []}
-
-        URI = f"https://waste-services.sutton.gov.uk/waste/{user_uprn}"
-
-        s = requests.Session()
-
-        r = s.get(URI)
-        while "Loading your bin days..." in r.text:
-            sleep(2)
-            r = s.get(URI)
-        r.raise_for_status()
-
-        soup = BeautifulSoup(r.content, "html.parser")
-
-        current_year = datetime.now().year
-        next_year = current_year + 1
-
-        services = soup.find_all("h3", class_="govuk-heading-m waste-service-name")
-
-        for service in services:
-            bin_type = service.get_text(
-                strip=True
-            )  # Bin type name (e.g., 'Food waste', 'Mixed recycling')
-            if bin_type == "Bulky Waste":
-                continue
-            service_details = service.find_next("div", class_="govuk-grid-row")
-
-            next_collection = (
-                (
-                    service_details.find("dt", string="Next collection")
-                    .find_next_sibling("dd")
-                    .get_text(strip=True)
-                )
-                .replace("(this collection has been adjusted from its usual time)", "")
-                .strip()
-            )
-
-            next_collection = datetime.strptime(
-                remove_ordinal_indicator_from_date_string(next_collection),
-                "%A, %d %B",
-            )
-
-            if (datetime.now().month == 12) and (next_collection.month == 1):
-                next_collection = next_collection.replace(year=next_year)
-            else:
-                next_collection = next_collection.replace(year=current_year)
-
-            dict_data = {
-                "type": bin_type,
-                "collectionDate": next_collection.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