uk_bin_collection 0.83.0__tar.gz → 0.84.1__tar.gz

{uk_bin_collection-0.83.0 → uk_bin_collection-0.84.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.83.0
+Version: 0.84.1
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.83.0 → uk_bin_collection-0.84.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.83.0"
+version = "0.84.1"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.83.0 → uk_bin_collection-0.84.1}/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,

{uk_bin_collection-0.83.0 → uk_bin_collection-0.84.1}/uk_bin_collection/uk_bin_collection/councils/BoltonCouncil.py

@@ -1,4 +1,6 @@
 import time
+import re
+
 from datetime import datetime
 
 from bs4 import BeautifulSoup
@@ -80,7 +82,8 @@ class CouncilClass(AbstractGetBinDataClass):
                 bin_type = " ".join(words).capitalize()
                 date_list = item.find_all("p")
                 for d in date_list:
-                    next_collection = datetime.strptime(d.text.strip(), "%A %d %B %Y")
+                    clean_date_str = re.sub(r'[^A-Za-z0-9 ]+', '', d.text.strip())
+                    next_collection = datetime.strptime(clean_date_str, "%A %d %B %Y")
                     collections.append((bin_type, next_collection))
 
             # Sort the text and list elements by date

uk_bin_collection-0.84.1/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