uk_bin_collection 0.152.10__tar.gz → 0.152.11__tar.gz

{uk_bin_collection-0.152.10 → uk_bin_collection-0.152.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.152.10
+Version: 0.152.11
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.152.10 → uk_bin_collection-0.152.11}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.152.10"
+version = "0.152.11"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.152.10 → uk_bin_collection-0.152.11}/uk_bin_collection/tests/input.json

@@ -641,6 +641,13 @@
         "wiki_note": "Pass the house number and postcode in their respective parameters. This parser requires a Selenium webdriver.",
         "LAD24CD": "E07000096"
     },
+    "DarlingtonBoroughCouncil": {
+        "uprn": "10003076924",
+        "url": "https://www.darlington.gov.uk/bins-waste-and-recycling/collection-day-lookup/",
+        "wiki_name": "Darlington Borough Council",
+        "wiki_note": "Use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find your UPRN.",
+        "LAD24CD": "E06000005"
+    },
     "DartfordBoroughCouncil": {
         "uprn": "100060861698",
         "url": "https://www.dartford.gov.uk/waste-recycling/collection-day",

{uk_bin_collection-0.152.10 → uk_bin_collection-0.152.11}/uk_bin_collection/uk_bin_collection/councils/CheltenhamBoroughCouncil.py

@@ -245,25 +245,39 @@ class CouncilClass(AbstractGetBinDataClass):
             # extract table body
             for row in table.find_all("tr")[1:]:
                 if row.find_all("td")[1].text.strip() == "Normal collection day":
-                    bh_dict[
-                        parse(
-                            row.find_all("td")[0].text.strip(),
-                            dayfirst=True,
-                            fuzzy=True,
-                        ).date()
-                    ] = parse(
-                        row.find_all("td")[0].text.strip(), dayfirst=True, fuzzy=True
-                    ).date()
+                    try:
+                        # Check for normal collection day (no change)
+                        if row.find_all("td")[0].text.strip() == "Normal collection":
+                            continue
+                        else:
+                            bh_dict[
+                                parse(
+                                    row.find_all("td")[0].text.strip(),
+                                    dayfirst=True,
+                                    fuzzy=True,
+                                ).date()
+                            ] = parse(
+                                row.find_all("td")[0].text.strip(), dayfirst=True, fuzzy=True
+                            ).date()
+                    except:
+                        continue
                 else:
-                    bh_dict[
-                        parse(
-                            row.find_all("td")[0].text.strip(),
-                            dayfirst=True,
-                            fuzzy=True,
-                        ).date()
-                    ] = parse(
-                        row.find_all("td")[1].text.strip(), dayfirst=True, fuzzy=True
-                    ).date()
+                    try:
+                        # Check for normal collection day (no change)
+                        if row.find_all("td")[1].text.strip() == "Normal collection":
+                            continue
+                        else:
+                            bh_dict[
+                                parse(
+                                    row.find_all("td")[0].text.strip(),
+                                    dayfirst=True,
+                                    fuzzy=True,
+                                ).date()
+                            ] = parse(
+                                row.find_all("td")[1].text.strip(), dayfirst=True, fuzzy=True
+                            ).date()
+                    except:
+                        continue
 
         for refuse_date in refuse_dates:
             collection_date = (datetime.strptime(refuse_date, "%d/%m/%Y") + timedelta(

uk_bin_collection-0.152.11/uk_bin_collection/uk_bin_collection/councils/DarlingtonBoroughCouncil.py

@@ -0,0 +1,68 @@
+import re
+
+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:
+
+        data = {"bins": []}
+
+        user_uprn = kwargs.get("uprn")
+        check_uprn(user_uprn)
+
+        url = f"https://www.darlington.gov.uk/bins-waste-and-recycling/collection-day-lookup/?uprn={user_uprn}"
+
+        # Referrer: https://www.darlington.gov.uk/bins-waste-and-recycling/collection-day-lookup/
+        # X-Requested-With: XMLHttpRequest
+        headers = {
+            "Accept": "*/*",
+            "Accept-Encoding": "gzip, deflate, br, zstd",
+            "Accept-Language": "en-GB,en;q=0.5",
+            "Referer": "https://www.darlington.gov.uk/bins-waste-and-recycling/collection-day-lookup/",
+            "Sec-Detch-Dest": "empty",
+            "Sec-Fetch-Mode": "cors",
+            "Sec-Fetch-Site": "same-origin",
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.6167.186 Safari/537.36",
+            "X-Requested-With": "XMLHttpRequest",
+        }
+
+        # Make a BS4 object
+        page = requests.get(url, headers=headers)
+        soup = BeautifulSoup(page.text, features="html.parser")
+        soup.prettify()
+
+        # Loop over each date card
+        card_blocks = soup.select("#detailsDisplay .refuse-results")
+
+        for card in card_blocks:
+            bin_date_tag = card.select_one(".card-footer h3")
+            if not bin_date_tag:
+                continue
+
+            bin_type = card.select_one(".card-header h2").text.strip()
+            bin_date = bin_date_tag.text.strip()
+
+            # Remove any extra text from the date "(Today)", "(Tomorrow)"
+            cleaned_bin_date = re.sub(r"\s*\(.*?\)", "", bin_date).strip()
+
+            next_binfo = {
+                "type": bin_type,
+                "collectionDate": datetime.strptime(
+                    cleaned_bin_date, "%A %d %B %Y"
+                ).strftime(date_format),
+            }
+
+            data["bins"].append(next_binfo)
+
+        return data

{uk_bin_collection-0.152.10 → uk_bin_collection-0.152.11}/uk_bin_collection/uk_bin_collection/councils/RochfordCouncil.py

@@ -33,10 +33,9 @@ class CouncilClass(AbstractGetBinDataClass):
                     "tr", {"class": "govuk-table__row"}
                 ):
                     week_text = week.get_text().strip().split("\n")
+                    date_str = week_text[0].split(" - ")[0].split("–")[0].strip()
                     collection_date = datetime.strptime(
-                        remove_ordinal_indicator_from_date_string(
-                            week_text[0].split(" - ")[0]
-                        ).strip(),
+                        remove_ordinal_indicator_from_date_string(date_str),
                         "%A %d %B",
                     )
                     next_collection = collection_date.replace(year=datetime.now().year)