uk_bin_collection 0.143.0__tar.gz → 0.143.2__tar.gz

{uk_bin_collection-0.143.0 → uk_bin_collection-0.143.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.143.0
+Version: 0.143.2
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.143.0 → uk_bin_collection-0.143.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.143.0"
+version = "0.143.2"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.143.0 → uk_bin_collection-0.143.2}/uk_bin_collection/uk_bin_collection/councils/AshfordBoroughCouncil.py

@@ -21,7 +21,7 @@ class CouncilClass(AbstractGetBinDataClass):
     def parse_data(self, page: str, **kwargs) -> dict:
         driver = None
         try:
-        # Get and check UPRN
+            # Get and check UPRN
             user_uprn = kwargs.get("uprn")
             user_postcode = kwargs.get("postcode")
             check_uprn(user_uprn)
@@ -73,7 +73,10 @@ class CouncilClass(AbstractGetBinDataClass):
             # Click search button
             findAddress = WebDriverWait(driver, 10).until(
                 EC.presence_of_element_located(
-                    (By.ID, "ContentPlaceHolder1_CollectionDayLookup2_Button_SelectAddress")
+                    (
+                        By.ID,
+                        "ContentPlaceHolder1_CollectionDayLookup2_Button_SelectAddress",
+                    )
                 )
             )
             findAddress.click()
@@ -89,7 +92,9 @@ class CouncilClass(AbstractGetBinDataClass):
             bin_tables = soup.find_all("table")
 
             for bin_table in bin_tables:
-                bin_text = bin_table.find("td", id=re.compile("CollectionDayLookup2_td_"))
+                bin_text = bin_table.find(
+                    "td", id=re.compile("CollectionDayLookup2_td_")
+                )
                 if not bin_text:
                     continue
 
@@ -112,7 +117,9 @@ class CouncilClass(AbstractGetBinDataClass):
                     if date_soup.text.strip().lower() == "today":
                         date = datetime.now().date()
                     else:
-                        date = datetime.strptime(date_str.split(" ")[1], "%d/%m/%Y").date()
+                        date = datetime.strptime(
+                            date_str.split(" ")[1], "%d/%m/%Y"
+                        ).date()
 
                 except ValueError:
                     continue
@@ -132,4 +139,4 @@ class CouncilClass(AbstractGetBinDataClass):
             # This block ensures that the driver is closed regardless of an exception
             if driver:
                 driver.quit()
-        return bindata
+        return bindata

{uk_bin_collection-0.143.0 → uk_bin_collection-0.143.2}/uk_bin_collection/uk_bin_collection/councils/EastHertsCouncil.py

@@ -89,7 +89,9 @@ class CouncilClass(AbstractGetBinDataClass):
             property.click()
 
             upcoming_scheduled_collections = WebDriverWait(driver, 10).until(
-                EC.presence_of_element_located((By.ID, "upcoming-scheduled-collections"))
+                EC.presence_of_element_located(
+                    (By.ID, "upcoming-scheduled-collections")
+                )
             )
 
             soup = BeautifulSoup(driver.page_source, features="html.parser")
@@ -125,4 +127,4 @@ class CouncilClass(AbstractGetBinDataClass):
             # This block ensures that the driver is closed regardless of an exception
             if driver:
                 driver.quit()
-        return bindata
+        return bindata

{uk_bin_collection-0.143.0 → uk_bin_collection-0.143.2}/uk_bin_collection/uk_bin_collection/councils/HertsmereBoroughCouncil.py

@@ -48,7 +48,11 @@ class CouncilClass(AbstractGetBinDataClass):
             for tag in strong:
                 parent = tag.parent
                 bin_type = (
-                    (parent.text).split("-")[1].strip().replace("\xa0", " ").split(" and ")
+                    (parent.text)
+                    .split("-")[1]
+                    .strip()
+                    .replace("\xa0", " ")
+                    .split(" and ")
                 )
                 for bin in bin_type:
                     dict_data = {
@@ -104,7 +108,9 @@ class CouncilClass(AbstractGetBinDataClass):
                 table_data = []
                 for row in table.find("tbody").find_all("tr"):
                     # Extract cell data from each <td> tag
-                    row_data = [cell.get_text(strip=True) for cell in row.find_all("td")]
+                    row_data = [
+                        cell.get_text(strip=True) for cell in row.find_all("td")
+                    ]
                     table_data.append(row_data)
 
             else:
@@ -112,7 +118,9 @@ class CouncilClass(AbstractGetBinDataClass):
 
             collection_day = (table_data[0])[1]
 
-            current_week_bins = [bin for bin in bin_weeks if bin["week"] == current_week]
+            current_week_bins = [
+                bin for bin in bin_weeks if bin["week"] == current_week
+            ]
             next_week_bins = [bin for bin in bin_weeks if bin["week"] != current_week]
 
             days_of_week = [
@@ -168,4 +176,4 @@ class CouncilClass(AbstractGetBinDataClass):
             # This block ensures that the driver is closed regardless of an exception
             if driver:
                 driver.quit()
-        return bindata
+        return bindata

{uk_bin_collection-0.143.0 → uk_bin_collection-0.143.2}/uk_bin_collection/uk_bin_collection/councils/LeedsCityCouncil.py

@@ -43,88 +43,70 @@ class CouncilClass(AbstractGetBinDataClass):
             postcode_box = wait.until(
                 EC.element_to_be_clickable(
                     (
-                        By.ID,
-                        "ctl00_ctl48_g_eea1a8ba_4306_488e_96f2_97f22038e29f_ctl00_txtPostCode",
+                        By.XPATH,
+                        "//input[@id='postcode']",
                     )
                 )
             )
             postcode_box.send_keys(user_postcode)
             postcode_btn_present = wait.until(
                 EC.presence_of_element_located(
-                    (
-                        By.ID,
-                        "ctl00_ctl48_g_eea1a8ba_4306_488e_96f2_97f22038e29f_ctl00_btnSearchAddress",
-                    )
-                )
-            )
-            postcode_btn = wait.until(
-                EC.element_to_be_clickable(
                     (
                         By.XPATH,
-                        '//*[@id="ctl00_ctl48_g_eea1a8ba_4306_488e_96f2_97f22038e29f_ctl00_btnSearchAddress"]',
+                        "//button[contains(text(),'Look up Address')]",
                     )
                 )
             )
-
-            postcode_btn.send_keys(Keys.ENTER)
+            postcode_btn_present.click()
 
             dropdown_present = wait.until(
                 EC.presence_of_element_located(
                     (
                         By.XPATH,
-                        '//*[@id="ctl00_ctl48_g_eea1a8ba_4306_488e_96f2_97f22038e29f_ctl00_ddlAddressList"]/option',
-                    )
-                )
-            )
-            address_dropdown = wait.until(
-                EC.element_to_be_clickable(
-                    (
-                        By.ID,
-                        "ctl00_ctl48_g_eea1a8ba_4306_488e_96f2_97f22038e29f_ctl00_ddlAddressList",
+                        '//option[contains(text(),"Select an address")]/parent::select',
                     )
                 )
             )
 
-            dropdown_present.click()
+            dropdown_select = Select(dropdown_present)
+
+            dropdown_select.select_by_value(user_uprn)
 
-            dropdownSelect = Select(address_dropdown)
-            dropdownSelect.select_by_value(str(user_uprn))
-            results = wait.until(
+            result = wait.until(
                 EC.presence_of_element_located(
                     (
-                        By.ID,
-                        "ctl00_ctl48_g_eea1a8ba_4306_488e_96f2_97f22038e29f_ctl00_BinResultsDetails",
+                        By.XPATH,
+                        "//div[@class='lcc-bins']",
                     )
                 )
             )
 
             data = {"bins": []}  # dictionary for data
-            soup = BeautifulSoup(driver.page_source, "html.parser")
-
-            bin_types = soup.find_all("ul", class_="binCollectionTimesList")
-
-            for bin_collection_dates in bin_types:
-
-                bin_collection_list = bin_collection_dates.find_all("li")
-
-                if bin_collection_list:
-                    collection_dates = [
-                        date.text.strip() for date in bin_collection_list
-                    ]
-
-                    # Convert the collection dates to the desired format
-                    formatted_dates = [
-                        datetime.strptime(date, "%A %d %b %Y").strftime(date_format)
-                        for date in collection_dates
-                    ]
-
-                    # Extract the type of bin from the header
-                    bin_type = bin_collection_dates.find_previous("h3").text.split()[0]
+            soup = BeautifulSoup(
+                result.get_attribute("innerHTML"), features="html.parser"
+            )
 
-                    # Adding data to the 'bins' dictionary for each date
-                    for date in formatted_dates:
-                        dict_data = {"type": bin_type, "collectionDate": date}
-                        data["bins"].append(dict_data)
+            bin_sections = soup.select("div.lcc-bin:not(.lcc-bin--calendar)")
+
+            for section in bin_sections:
+                h3_text = section.find("h3").get_text(strip=True)
+                bin_type = h3_text.split()[0]  # e.g., 'Black', 'Brown', 'Green'
+
+                # Find all <li> elements inside the bin days list
+                date_elements = section.select("div.lcc-bin__days li")
+                for li in date_elements:
+                    raw_date = li.get_text(strip=True)
+                    if not raw_date:
+                        continue
+                    try:
+                        formatted_date = datetime.strptime(
+                            raw_date, "%A %d %b %Y"
+                        ).strftime(date_format)
+                        data["bins"].append(
+                            {"type": bin_type, "collectionDate": formatted_date}
+                        )
+                    except ValueError:
+                        print(f"Skipping unparseable date: {raw_date}")
         except Exception as e:
             # Here you can log the exception if needed
             print(f"An error occurred: {e}")

{uk_bin_collection-0.143.0 → uk_bin_collection-0.143.2}/uk_bin_collection/uk_bin_collection/councils/SouthOxfordshireCouncil.py

@@ -79,7 +79,7 @@ class CouncilClass(AbstractGetBinDataClass):
                             "%A %d %B -",
                         )
                     )
-                    str.capitalize(" ".join(bin_info[2:]))
+                    bin_type = str.capitalize(" ".join(bin_info[2:]))
             except:
                 continue
 

{uk_bin_collection-0.143.0 → uk_bin_collection-0.143.2}/uk_bin_collection/uk_bin_collection/councils/WindsorAndMaidenheadCouncil.py

@@ -59,4 +59,3 @@ class CouncilClass(AbstractGetBinDataClass):
             if driver:
                 driver.quit()
         return data
-