uk_bin_collection 0.82.1__tar.gz → 0.84.0__tar.gz

{uk_bin_collection-0.82.1 → uk_bin_collection-0.84.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.82.1
+Version: 0.84.0
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.82.1 → uk_bin_collection-0.84.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.82.1"
+version = "0.84.0"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.82.1 → uk_bin_collection-0.84.0}/uk_bin_collection/tests/input.json

@@ -247,6 +247,13 @@
         "wiki_name": "Conwy County Borough Council",
         "wiki_note": "Conwy County Borough Council is a straight up uprn in the url eg &uprn=XXXXXXXXXXXXX ."
     },
+    "CornwallCouncil": {
+        "skip_get_url": true,
+        "uprn": "100040128734",
+        "url": "https://www.cornwall.gov.uk/my-area/",
+        "wiki_name": "Cornwall Council",
+        "wiki_note": "Use https://uprn.uk/ to find your UPRN."
+    },
     "CrawleyBoroughCouncil": {
         "house_number": "9701076",
         "skip_get_url": true,
@@ -393,11 +400,11 @@
         "wiki_note": "Pass the house name/number in the house number parameter, wrapped in double quotes"
     },
     "GedlingBoroughCouncil": {
-        "house_number": "Valeside Gardens",
+        "house_number": "Friday G4, Friday J",
         "skip_get_url": true,
         "url": "https://www.gedling.gov.uk/",
         "wiki_name": "Gedling Borough Council",
-        "wiki_note": "Pass the street name into the -n parameter. Use [this](https://apps.gedling.gov.uk/refuse/search.aspx) to help work out a street search that is unique. Known issues: 1) If multiple streets returned, it will pick the first and these may have different bin schedules. 2) This data is hand entered as council only provide non-parseable non-accessible PDFs - Please double check for any issues. 2b) Data is only included until end of Nov 2024 (refuse) and March 2024 (Garden). Data will need to be updated by hand after these dates."
+        "wiki_note": "Use [this site](https://www.gbcbincalendars.co.uk/) to find the collections for your address. Use the -n parameter to add them in a comma-separated list inside quotes, such as: 'Friday G4, Friday J'."
     },
     "GlasgowCityCouncil": {
         "url": "https://www.glasgow.gov.uk/forms/refuseandrecyclingcalendar/PrintCalendar.aspx?UPRN=906700034497",

{uk_bin_collection-0.82.1 → uk_bin_collection-0.84.0}/uk_bin_collection/uk_bin_collection/common.py

@@ -106,6 +106,15 @@ def get_date_with_ordinal(date_number: int) -> str:
         else {1: "st", 2: "nd", 3: "rd"}.get(date_number % 10, "th")
     )
 
+def has_numbers(inputString: str) -> bool:
+    """
+
+    :rtype: bool
+    :param inputString: String to check for numbers
+    :return: True if any numbers are found in input string
+    """
+    return any(char.isdigit() for char in inputString)
+
 
 def remove_ordinal_indicator_from_date_string(date_string: str) -> str:
     """

uk_bin_collection-0.84.0/uk_bin_collection/uk_bin_collection/councils/CornwallCouncil.py

@@ -0,0 +1,70 @@
+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
+from dateutil.relativedelta import relativedelta
+
+
+
+# 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": []}
+        collections = []
+
+        curr_date = datetime.today()
+
+        user_uprn = kwargs.get("uprn")
+        check_uprn(user_uprn)
+
+        headers = {
+            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
+            'Accept-Language': 'en-GB,en;q=0.9',
+            'Cache-Control': 'no-cache',
+            'Connection': 'keep-alive',
+            'Pragma': 'no-cache',
+            'Sec-Fetch-Dest': 'document',
+            'Sec-Fetch-Mode': 'navigate',
+            'Sec-Fetch-Site': 'none',
+            'Sec-Fetch-User': '?1',
+            'Upgrade-Insecure-Requests': '1',
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.6422.143 Safari/537.36',
+            'sec-ch-ua': '"Opera GX";v="111", "Chromium";v="125", "Not.A/Brand";v="24"',
+            'sec-ch-ua-mobile': '?0',
+            'sec-ch-ua-platform': '"Windows"',
+        }
+        params = {
+            'uprn': f'{user_uprn}',
+            # 'uprn': f'100040128734',
+        }
+        response = requests.get(
+            'https://www.cornwall.gov.uk/umbraco/surface/waste/MyCollectionDays',
+            params=params,
+            headers=headers
+        )
+
+        soup = BeautifulSoup(response.text, features="html.parser")
+        soup.prettify()
+
+        for item in soup.find_all('div', class_='collection text-center service'):
+            bin_type = item.contents[1].text + " bin"
+            collection_date = datetime.strptime(item.contents[5].text, "%d %b").replace(year=curr_date.year)
+            if curr_date.month == 12 and collection_date.month == 1:
+                collection_date = collection_date + relativedelta(years=1)
+            collections.append((bin_type, collection_date))
+
+            ordered_data = sorted(collections, key=lambda x: x[1])
+            data = {"bins": []}
+            for bin in ordered_data:
+                dict_data = {
+                    "type": bin[0].capitalize().strip(),
+                    "collectionDate": bin[1].strftime(date_format),
+                }
+                data["bins"].append(dict_data)
+
+        return data

uk_bin_collection-0.84.0/uk_bin_collection/uk_bin_collection/councils/GedlingBoroughCouncil.py

@@ -0,0 +1,54 @@
+from bs4 import BeautifulSoup
+import urllib.parse
+
+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": []}
+        collections = []
+        selected_collections = kwargs.get("paon").split(',')
+        calendar_urls = []
+        run_date = datetime.now().date()
+
+        # For each collection, check if there's a number. Garden bins have no numbers, so we can generate the needed
+        # URLs this way
+        for item in selected_collections:
+            item = item.strip().lower().replace(" ", "_")
+            if has_numbers(item):
+                calendar_urls.append(f"https://www.gbcbincalendars.co.uk/json/gedling_borough_council_{item}_bin_schedule.json")
+            else:
+                calendar_urls.append(f"https://www.gbcbincalendars.co.uk/json/gedling_borough_council_{item}_garden_bin_schedule.json")
+
+        # Parse each URL and load future data
+        for url in calendar_urls:
+            response = requests.get(url)
+            if response.status_code != 200:
+                raise ConnectionError(f"Could not get response from: {url}")
+            json_data = response.json()["collectionDates"]
+            for col in json_data:
+                bin_date = datetime.strptime(col.get("collectionDate"), "%Y-%m-%d").date()
+                if bin_date >= run_date:
+                    collections.append((col.get("alternativeName"), bin_date))
+
+        # Sort the data
+        ordered_data = sorted(collections, key=lambda x: x[1])
+        data = {"bins": []}
+        for bin in ordered_data:
+            dict_data = {
+                "type": bin[0],
+                "collectionDate": bin[1].strftime(date_format),
+            }
+            data["bins"].append(dict_data)
+        print()
+
+        return data