uk_bin_collection 0.152.5__tar.gz → 0.152.7__tar.gz

{uk_bin_collection-0.152.5 → uk_bin_collection-0.152.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.152.5
+Version: 0.152.7
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.152.5 → uk_bin_collection-0.152.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.152.5"
+version = "0.152.7"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.152.5 → uk_bin_collection-0.152.7}/uk_bin_collection/tests/input.json

@@ -614,8 +614,9 @@
         "postcode": "SE25 5DW",
         "skip_get_url": true,
         "url": "https://service.croydon.gov.uk/wasteservices/w/webpage/bin-day-enter-address",
+        "web_driver": "http://selenium:4444",
         "wiki_name": "Croydon",
-        "wiki_note": "Pass the house number and postcode in their respective parameters.",
+        "wiki_note": "Pass the house number and postcode in their respective parameters. This parser requires a Selenium webdriver.",
         "LAD24CD": "E09000008"
     },
     "CumberlandAllerdaleCouncil": {
@@ -627,8 +628,9 @@
         "LAD24CD": "E06000063"
     },
     "CumberlandCouncil": {
-        "uprn": "100110734613",
-        "url": "https://waste.cumberland.gov.uk",
+        "postcode": "CA6 5PH",
+        "uprn": "10009457328",
+        "url": "https://waste.cumberland.gov.uk/renderform?t=25&k=E43CEB1FB59F859833EF2D52B16F3F4EBE1CAB6A",
         "wiki_name": "Cumberland",
         "wiki_note": "Use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find your UPRN.",
         "LAD24CD": "E06000063"
@@ -745,7 +747,7 @@
         "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN.",
         "LAD24CD": "E07000061"
     },
-    "EastCambridgeshireCouncil": { 
+    "EastCambridgeshireCouncil": {
         "skip_get_url": true,
         "uprn": "10002597178",
         "url": "https://www.eastcambs.gov.uk/",
@@ -1443,6 +1445,7 @@
         "house_number": "71",
         "postcode": "ME16 8BT",
         "url": "https://my.maidstone.gov.uk/service/Find-your-bin-day",
+        "web_driver": "http://selenium:4444", 
         "wiki_name": "Maidstone",
         "wiki_note": "Pass the house number and postcode in their respective parameters. This parser requires a Selenium webdriver.",
         "LAD24CD": "E07000110"
@@ -1827,8 +1830,8 @@
     "OxfordCityCouncil": {
         "postcode": "OX3 7QF",
         "uprn": "100120820551",
-        "url": "https://www.oxford.gov.uk",
-        "wiki_command_url_override": "https://www.oxford.gov.uk",
+        "url": "https://www.oxford.gov.uk/xfp/form/142",
+        "wiki_command_url_override": "https://www.oxford.gov.uk/xfp/form/142",
         "wiki_name": "Oxford",
         "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN.",
         "LAD24CD": "E07000178"

{uk_bin_collection-0.152.5 → uk_bin_collection-0.152.7}/uk_bin_collection/uk_bin_collection/councils/AdurAndWorthingCouncils.py

@@ -69,8 +69,10 @@ class CouncilClass(AbstractGetBinDataClass):
                                 current_year = datetime.now().year
                                 bin_date = bin_date.replace(year=current_year)
 
-                                # If the date is in the past, it's probably for next year
-                                if bin_date < datetime.now():
+                                # Only add a year if the date is more than 30 days in the past
+                                # This handles both mid-year and year-end transitions better
+                                today = datetime.now()
+                                if (today - bin_date).days > 30:
                                     bin_date = bin_date.replace(year=current_year + 1)
 
                                 collections.append((bin_type, bin_date))

{uk_bin_collection-0.152.5 → uk_bin_collection-0.152.7}/uk_bin_collection/uk_bin_collection/councils/CroydonCouncil.py

@@ -79,12 +79,9 @@ class CouncilClass(AbstractGetBinDataClass):
             next_button.click()
 
             # Wait for the bin collection content to load
-            collection_content = WebDriverWait(driver, 10).until(
-                EC.presence_of_element_located(
-                    (
-                        By.XPATH,
-                        '//*[@id="mats_content_wrapper"]/div[2]/div[2]/div[2]/div/div[1]/div/div[3]/div/div/div/div',
-                    )
+            listing_records = WebDriverWait(driver, 10).until(
+                EC.presence_of_all_elements_located(
+                    (By.CSS_SELECTOR, "#mats_content_wrapper .listing_template_record")
                 )
             )
 

{uk_bin_collection-0.152.5 → uk_bin_collection-0.152.7}/uk_bin_collection/uk_bin_collection/councils/CumberlandCouncil.py

@@ -16,6 +16,7 @@ class CouncilClass(AbstractGetBinDataClass):
     def parse_data(self, page: str, **kwargs) -> dict:
 
         user_uprn = kwargs.get("uprn")
+        postcode = kwargs.get("postcode")
         check_uprn(user_uprn)
         bindata = {"bins": []}
 
@@ -57,6 +58,7 @@ class CouncilClass(AbstractGetBinDataClass):
             "TriggerCtl": "",
             "FF265": f"U{user_uprn}",
             "FF265lbltxt": "Please select your address",
+            "FF265-text": postcode
         }
 
         # print(payload)

{uk_bin_collection-0.152.5 → uk_bin_collection-0.152.7}/uk_bin_collection/uk_bin_collection/councils/KingstonUponThamesCouncil.py

@@ -51,7 +51,7 @@ class CouncilClass(AbstractGetBinDataClass):
                     if row.find("dt").get_text().strip().lower() == "next collection":
                         collection_date = remove_ordinal_indicator_from_date_string(
                             row.find("dd").get_text()
-                        ).strip()
+                        ).strip().replace(" (In progress)", "")
                         # strip out any text inside of the date string
                         collection_date = re.sub(
                             r"\n\s*\(this.*?\)", "", collection_date

{uk_bin_collection-0.152.5 → uk_bin_collection-0.152.7}/uk_bin_collection/uk_bin_collection/councils/NorthHertfordshireDistrictCouncil.py

@@ -151,7 +151,7 @@ class CouncilClass(AbstractGetBinDataClass):
 
             # Looking for bin types in the exact HTML structure
             bin_type_elements = soup.select(
-                "div.formatting_bold.formatting_size_bigger.formatting span.value-as-text"
+                "div.page_cell.contains_widget:first-of-type div.formatting_bold.formatting_size_bigger.formatting span.value-as-text"
             )
             # print(f"Found {len(bin_type_elements)} bin type elements")
 

{uk_bin_collection-0.152.5 → uk_bin_collection-0.152.7}/uk_bin_collection/uk_bin_collection/councils/OxfordCityCouncil.py

@@ -21,8 +21,8 @@ class CouncilClass(AbstractGetBinDataClass):
         check_postcode(user_postcode)
         bindata = {"bins": []}
 
-        session_uri = "https://www.oxford.gov.uk/mybinday"
-        URI = "https://www.oxford.gov.uk/xfp/form/142"
+        session_uri = "https://www.oxford.gov.uk/xfp/form/142"
+        URI = "https://www.oxford.gov.uk/xfp/form/142#q6ad4e3bf432c83230a0347a6eea6c805c672efeb_0"
 
         session = requests.Session()
         token_response = session.get(session_uri)
@@ -40,15 +40,18 @@ class CouncilClass(AbstractGetBinDataClass):
 
         collection_response = session.post(URI, data=form_data)
 
-        collection_soup = BeautifulSoup(collection_response.text, "html.parser")
-        for paragraph in collection_soup.find("div", class_="editor").find_all("p"):
-            matches = re.match(r"^(\w+) Next Collection: (.*)", paragraph.text)
+        soup = BeautifulSoup(collection_response.text, "html.parser")
+        #print(soup)
+
+        for paragraph in soup.find("div", class_="editor").find_all("p"):
+            matches = re.match(r"^Your next (\w+) collections: (.*)", paragraph.text)
             if matches:
                 collection_type, date_string = matches.groups()
+                parts = date_string.split(', ', 1)
                 try:
-                    date = datetime.strptime(date_string, "%A %d %B %Y").date()
+                    date = datetime.strptime(parts[0], "%A %d %B %Y").date()
                 except ValueError:
-                    date = datetime.strptime(date_string, "%A %d %b %Y").date()
+                    date = datetime.strptime(parts[0], "%A %d %b %Y").date()
 
                 dict_data = {
                     "type": collection_type,
@@ -61,3 +64,5 @@ class CouncilClass(AbstractGetBinDataClass):
         )
 
         return bindata
+
+

{uk_bin_collection-0.152.5 → uk_bin_collection-0.152.7}/uk_bin_collection/uk_bin_collection/councils/RotherhamCouncil.py

@@ -15,11 +15,15 @@ class CouncilClass(AbstractGetBinDataClass):
         user_uprn = kwargs.get("uprn")
 
         check_uprn(user_uprn)
-
+        headers = {
+            "Content-Type": "application/x-www-form-urlencoded",
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36",
+        }
         response = requests.post(
             "https://www.rotherham.gov.uk/bin-collections?address={}&submit=Submit".format(
                 user_uprn
-            )
+            ), 
+            headers=headers
         )
         # Make a BS4 object
         soup = BeautifulSoup(response.text, features="html.parser")

{uk_bin_collection-0.152.5 → uk_bin_collection-0.152.7}/uk_bin_collection/uk_bin_collection/councils/RugbyBoroughCouncil.py

@@ -113,7 +113,7 @@ class CouncilClass(AbstractGetBinDataClass):
                             try:
                                 # Convert date from "Friday 09 May 2025" format
                                 parsed_date = datetime.strptime(
-                                    collection_date, "%A %d %B %Y"
+                                    collection_date, "%A %d %b %Y"
                                 )
                                 formatted_date = parsed_date.strftime("%d/%m/%Y")
 
@@ -132,7 +132,7 @@ class CouncilClass(AbstractGetBinDataClass):
                 key=lambda x: datetime.strptime(x["collectionDate"], "%d/%m/%Y")
             )
 
-            print(bin_data)
+            #print(bin_data)
 
         except Exception as e:
             # Here you can log the exception if needed

{uk_bin_collection-0.152.5 → uk_bin_collection-0.152.7}/uk_bin_collection/uk_bin_collection/councils/WiganBoroughCouncil.py

@@ -82,7 +82,7 @@ class CouncilClass(AbstractGetBinDataClass):
         # Get the dates.
         for bins in soup.find_all("div", {"class": "BinsRecycling"}):
             bin_type = bins.find("h2").text
-            binCollection = bins.find("div", {"class": "dateWrapper-next"}).get_text(
+            binCollection = bins.find("div", {"class": "dateWrap-next"}).get_text(
                 strip=True
             )
             binData = datetime.strptime(