uk_bin_collection 0.98.1__py3-none-any.whl → 0.98.3__py3-none-any.whl

uk_bin_collection/uk_bin_collection/councils/EastRidingCouncil.py

@@ -29,7 +29,7 @@ class CouncilClass(AbstractGetBinDataClass):
             headless = kwargs.get("headless")
 
             # Create Selenium webdriver
-            page = f"https://www.eastriding.gov.uk/environment/bins-rubbish-recycling/bins-and-collections/bin-collection-dates/"
+            page = "https://www.eastriding.gov.uk/environment/bins-rubbish-recycling/bins-and-collections/bin-collection-dates/#"
 
             driver = create_webdriver(web_driver, headless, None, __name__)
             driver.get(page)
@@ -52,7 +52,7 @@ class CouncilClass(AbstractGetBinDataClass):
 
             expand_postcode_box = wait.until(
                 EC.element_to_be_clickable(
-                    (By.ID, "when-and-where-should-i-put-my-bin-out")
+                    (By.XPATH, '//a[contains(text(), "Open all")]')
                 )
             )
 

uk_bin_collection/uk_bin_collection/councils/MoleValleyDistrictCouncil.py

@@ -7,28 +7,18 @@ 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_postcode = kwargs.get("postcode")
         check_postcode(user_postcode)
 
-        root_url = "https://myproperty.molevalley.gov.uk/molevalley/api/live_addresses/{}?format=json".format(
-            user_postcode
-        )
-        requests.packages.urllib3.disable_warnings()
+        # Fetch the page content
+        root_url = "https://myproperty.molevalley.gov.uk/molevalley/api/live_addresses/{}?format=json".format(user_postcode)
         response = requests.get(root_url, verify=False)
 
         if not response.ok:
-            raise ValueError("Invalid server response code retreiving data.")
+            raise ValueError("Invalid server response code retrieving data.")
 
         jsonData = response.json()
 
@@ -37,7 +27,6 @@ class CouncilClass(AbstractGetBinDataClass):
 
         properties_found = jsonData["results"]["features"]
 
-        # If UPRN is provided, we can check a specific address.
         html_data = None
         uprn = kwargs.get("uprn")
         if uprn:
@@ -49,53 +38,81 @@ class CouncilClass(AbstractGetBinDataClass):
             if html_data is None:
                 raise ValueError("No collection data found for UPRN provided.")
         else:
-            # If UPRN not provided, just use the first result
             html_data = properties_found[0]["properties"]["three_column_layout_html"]
 
-        soup = BeautifulSoup(html_data, features="html.parser")
-        soup.prettify()
+        # Conditionally replace the commented-out sections (<!-- ... -->)
+        if "<!--" in html_data and "-->" in html_data:
+            print("Commented-out section found, replacing comments...")
+            html_data = html_data.replace("<!--", "").replace("-->", "")
+        else:
+            print("No commented-out section found, processing as is.")
+
+        # Process the updated HTML data with BeautifulSoup
+        soup = BeautifulSoup(html_data, "html.parser")
 
         data = {"bins": []}
         all_collection_dates = []
-        regex_date = re.compile(r".* ([\d]+\/[\d]+\/[\d]+)")
+        regex_date = re.compile(r"(\d{2}/\d{2}/\d{4})")  # Adjusted date regex
         regex_additional_collection = re.compile(r"We also collect (.*) on (.*) -")
 
+        # Debugging to verify the HTML content is parsed correctly
+        print("HTML content parsed successfully.")
+
         # Search for the 'Bins and Recycling' panel
-        for panel in soup.select('div[class*="panel"]'):
-            if panel.h2.text.strip() == "Bins and Recycling":
-
-                # Gather the bin types and dates
-                for collection in panel.select("div > strong"):
-                    bin_type = collection.text.strip()
-                    collection_string = collection.find_next("p").text.strip()
-                    m = regex_date.match(collection_string)
-                    if m:
-                        collection_date = datetime.strptime(
-                            m.group(1), "%d/%m/%Y"
-                        ).date()
-                        data["bins"].append(
-                            {
+        bins_panel = soup.find("h2", string="Bins and Recycling")
+        if bins_panel:
+            panel = bins_panel.find_parent("div", class_="panel")
+            print("Found 'Bins and Recycling' panel.")
+            
+            # Extract bin collection info from the un-commented HTML
+            for strong_tag in panel.find_all("strong"):
+                bin_type = strong_tag.text.strip()
+                collection_string = strong_tag.find_next("p").text.strip()
+                
+                # Debugging output
+                print(f"Processing bin type: {bin_type}")
+                print(f"Collection string: {collection_string}")
+                
+                match = regex_date.search(collection_string)
+                if match:
+                    collection_date = datetime.strptime(match.group(1), "%d/%m/%Y").date()
+                    data["bins"].append({
+                        "type": bin_type,
+                        "collectionDate": collection_date.strftime("%d/%m/%Y"),
+                    })
+                    all_collection_dates.append(collection_date)
+                else:
+                    # Add a debug line to show which collections are missing dates
+                    print(f"No valid date found for bin type: {bin_type}")
+
+            # Search for additional collections like electrical and textiles
+            for p in panel.find_all("p"):
+                additional_match = regex_additional_collection.match(p.text.strip())
+                
+                # Debugging output for additional collections
+                if additional_match:
+                    bin_type = additional_match.group(1)
+                    print(f"Found additional collection: {bin_type}")
+                    if "each collection day" in additional_match.group(2):
+                        if all_collection_dates:
+                            collection_date = min(all_collection_dates)
+                            data["bins"].append({
                                 "type": bin_type,
                                 "collectionDate": collection_date.strftime("%d/%m/%Y"),
-                            }
-                        )
-                        all_collection_dates.append(collection_date)
-
-                # Search for additional collections
-                for p in panel.select("p"):
-                    m2 = regex_additional_collection.match(p.text.strip())
-                    if m2:
-                        bin_type = m2.group(1)
-                        if "each collection day" in m2.group(2):
-                            collection_date = min(all_collection_dates)
-                            data["bins"].append(
-                                {
-                                    "type": bin_type,
-                                    "collectionDate": collection_date.strftime(
-                                        "%d/%m/%Y"
-                                    ),
-                                }
-                            )
-                break
-
-        return data
+                            })
+                        else:
+                            print("No collection dates available for additional collection.")
+                            raise ValueError("No valid bin collection dates found.")
+                else:
+                    print(f"No additional collection found in paragraph: {p.text.strip()}")
+        else:
+            raise ValueError("Unable to find 'Bins and Recycling' panel in the HTML data.")
+
+        # Debugging to check collected data
+        print(f"Collected bin data: {data}")
+        
+        # Handle the case where no collection dates were found
+        if not all_collection_dates:
+            raise ValueError("No valid collection dates were found in the data.")
+        
+        return data

{uk_bin_collection-0.98.1.dist-info → uk_bin_collection-0.98.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.98.1
+Version: 0.98.3
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.98.1.dist-info → uk_bin_collection-0.98.3.dist-info}/RECORD

@@ -64,7 +64,7 @@ uk_bin_collection/uk_bin_collection/councils/EastCambridgeshireCouncil.py,sha256
 uk_bin_collection/uk_bin_collection/councils/EastDevonDC.py,sha256=U0VwSNIldMv5nUoiXtFgjbE0m6Kb-8W2WZQGVCNF_WI,3261
 uk_bin_collection/uk_bin_collection/councils/EastLindseyDistrictCouncil.py,sha256=o_HPSFhb2ybmwv32_7T7CO1f2mGDkYCNPfaM5xz6bUI,4356
 uk_bin_collection/uk_bin_collection/councils/EastRenfrewshireCouncil.py,sha256=5giegMCKQ2JhVDR5M4mevVxIdhZtSW7kbuuoSkj3EGk,4361
-uk_bin_collection/uk_bin_collection/councils/EastRidingCouncil.py,sha256=CsYdkmL-8Ty-Kz7uNdlnJnhiDMgOPah_swYgSKbaFqA,5218
+uk_bin_collection/uk_bin_collection/councils/EastRidingCouncil.py,sha256=oL-NqriLVy_NChGASNh8qTqeakLn4iP_XzoMC6VlPGM,5216
 uk_bin_collection/uk_bin_collection/councils/EastSuffolkCouncil.py,sha256=qQ0oOfGd0sWcczse_B22YoeL9uj3og8v3UJLt_Sx29c,4353
 uk_bin_collection/uk_bin_collection/councils/EastleighBoroughCouncil.py,sha256=V4Vso4DvawFiezKlmXbTlJEK9Sjhz9nA8WeYjwtO2e4,2310
 uk_bin_collection/uk_bin_collection/councils/ElmbridgeBoroughCouncil.py,sha256=TgBOaReHWBbm0avV7HqRf0x7cxDe9cacTUcP9TFFprs,3005
@@ -111,7 +111,7 @@ uk_bin_collection/uk_bin_collection/councils/MertonCouncil.py,sha256=3Y2Un4xXo1s
 uk_bin_collection/uk_bin_collection/councils/MidAndEastAntrimBoroughCouncil.py,sha256=oOWwU5FSgGej2Mv7FQ66N-EzS5nZgmGsd0WnfLWUc1I,5238
 uk_bin_collection/uk_bin_collection/councils/MidSussexDistrictCouncil.py,sha256=AZgC9wmDLEjUOtIFvf0ehF5LHturXTH4DkE3ioPSVBA,6254
 uk_bin_collection/uk_bin_collection/councils/MiltonKeynesCityCouncil.py,sha256=3olsWa77L34vz-c7NgeGK9xmNuR4Ws_oAk5D4UpIkPw,2005
-uk_bin_collection/uk_bin_collection/councils/MoleValleyDistrictCouncil.py,sha256=54-autRRGAM4pBxlqmUE6g825rmUF-gRqrcgHL_lkIk,3994
+uk_bin_collection/uk_bin_collection/councils/MoleValleyDistrictCouncil.py,sha256=bvCrC4Qcg0Uzp9zZGcC7-7-oJcMh2cb1VaXfdkB11oc,5257
 uk_bin_collection/uk_bin_collection/councils/NeathPortTalbotCouncil.py,sha256=V9URKAv3dA_deYmStL2Nmn4GbVCM-tU2qnKobivmGew,5583
 uk_bin_collection/uk_bin_collection/councils/NewForestCouncil.py,sha256=ylTn9KmWITtaO9_Z8kJCN2w2ALfhrfGt3SeJ78lgw7M,5391
 uk_bin_collection/uk_bin_collection/councils/NewarkAndSherwoodDC.py,sha256=lAleYfCGUWCKOi7Ye_cjgfpI3pWwTcFctlYmh0hjebM,2140
@@ -210,8 +210,8 @@ uk_bin_collection/uk_bin_collection/councils/YorkCouncil.py,sha256=I2kBYMlsD4bId
 uk_bin_collection/uk_bin_collection/councils/council_class_template/councilclasstemplate.py,sha256=4s9ODGPAwPqwXc8SrTX5Wlfmizs3_58iXUtHc4Ir86o,1162
 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=YvmHfZqanwrJ8ToGch34x-L-7yPe31nB_x77_Mgl_vo,4545
-uk_bin_collection-0.98.1.dist-info/LICENSE,sha256=vABBUOzcrgfaTKpzeo-si9YVEun6juDkndqA8RKdKGs,1071
-uk_bin_collection-0.98.1.dist-info/METADATA,sha256=dmWxsxgW5nOAahaqJsFqK-bn6f5rbGSQB9uq1x0EsYk,16843
-uk_bin_collection-0.98.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-uk_bin_collection-0.98.1.dist-info/entry_points.txt,sha256=36WCSGMWSc916S3Hi1ZkazzDKHaJ6CD-4fCEFm5MIao,90
-uk_bin_collection-0.98.1.dist-info/RECORD,,
+uk_bin_collection-0.98.3.dist-info/LICENSE,sha256=vABBUOzcrgfaTKpzeo-si9YVEun6juDkndqA8RKdKGs,1071
+uk_bin_collection-0.98.3.dist-info/METADATA,sha256=tXTM95e75ygcLe_-4x6iPeWvmm7maK9V6VxrXjov5J0,16843
+uk_bin_collection-0.98.3.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+uk_bin_collection-0.98.3.dist-info/entry_points.txt,sha256=36WCSGMWSc916S3Hi1ZkazzDKHaJ6CD-4fCEFm5MIao,90
+uk_bin_collection-0.98.3.dist-info/RECORD,,