uk_bin_collection 0.98.3__tar.gz → 0.98.4__tar.gz

{uk_bin_collection-0.98.3 → uk_bin_collection-0.98.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.98.3
+Version: 0.98.4
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.98.3 → uk_bin_collection-0.98.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.98.3"
+version = "0.98.4"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.98.3 → uk_bin_collection-0.98.4}/uk_bin_collection/tests/input.json

@@ -132,7 +132,7 @@
     "BradfordMDC": {
         "custom_component_show_url_field": false,
         "skip_get_url": true,
-        "uprn": "100052235823",
+        "uprn": "100051146921",
         "url": "https://onlineforms.bradford.gov.uk/ufs/collectiondates.eb",
         "wiki_name": "Bradford MDC",
         "wiki_note": "To get the UPRN, you will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search). Post code isn't parsed by this script, but you can pass it in double quotes."
@@ -680,7 +680,7 @@
     },
     "ManchesterCityCouncil": {
         "skip_get_url": true,
-        "uprn": "000077048077",
+        "uprn": "77127089",
         "url": "https://www.manchester.gov.uk/bincollections",
         "wiki_name": "Manchester City Council"
     },
@@ -691,7 +691,7 @@
         "wiki_name": "Mansfield District Council"
     },
     "MertonCouncil": {
-        "url": "https://myneighbourhood.merton.gov.uk/Wasteservices/WasteServices.aspx?ID=28298025",
+        "url": "https://myneighbourhood.merton.gov.uk/wasteservices/WasteServices.aspx?ID=25851371",
         "wiki_command_url_override": "https://myneighbourhood.merton.gov.uk/Wasteservices/WasteServices.aspx?ID=XXXXXXXX",
         "wiki_name": "Merton Council",
         "wiki_note": "Follow the instructions [here](https://myneighbourhood.merton.gov.uk/Wasteservices/WasteServicesSearch.aspx) until you get the \"Your recycling and rubbish collection days\" page then copy the URL and replace the URL in the command (the Address parameter is optional)."

{uk_bin_collection-0.98.3 → uk_bin_collection-0.98.4}/uk_bin_collection/uk_bin_collection/councils/BradfordMDC.py

@@ -1,5 +1,6 @@
 import requests
 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
 
@@ -92,7 +93,6 @@ class CouncilClass(AbstractGetBinDataClass):
         dict_data = {
             "type": bin_type,
             "collectionDate": bin_date,
-            "colour": bin_colour,
         }
         data["bins"].append(dict_data)
 

{uk_bin_collection-0.98.3 → uk_bin_collection-0.98.4}/uk_bin_collection/uk_bin_collection/councils/GlasgowCityCouncil.py

@@ -1,4 +1,5 @@
 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
 
@@ -18,36 +19,34 @@ class CouncilClass(AbstractGetBinDataClass):
         # Declare an empty dict for data, and pair icon source URLs with their respective bin type
         data = {"bins": []}
         bin_types = {
-            "../images/bins/cal_blue.png": "Mixed recycling",
-            "../images/bins/cal_green.png": "General waste",
-            "../images/bins/cal_grey.png": "Food waste",
-            "../images/bins/cal_brown.png": "Organic waste",
-            "../images/bins/cal_purple.png": "Glass",
-            "../images/bins/cal_ash.png": "Ash bin",
+            "../Images/Bins/blueBin.gif": "Mixed recycling",
+            "../Images/Bins/greenBin.gif": "General waste",
+            "../Images/Bins/greyBin.gif": "Food waste",
+            "../Images/Bins/brownBin.gif": "Organic waste",
+            "../Images/Bins/purpleBin.gif": "Glass",
+            "../Images/Bins/ashBin.gif": "Ash bin",
         }
 
         # Find the page body with all the calendars
-        body = soup.find("div", {"id": "printArticle"})
-        cal_year = datetime.strptime(soup.select("#Year")[0].text.strip(), "%Y").year
+        body = soup.find("div", {"id": "Application_ctl00"})
         calendars = body.find_all_next("table", {"title": "Calendar"})
-
         # For each calendar grid, get the month and all icons within it. We only take icons with alt text, as this
         # includes the bin type while excluding spacers
         for item in calendars:
-            cal_month = datetime.strptime(item.find_next("td").text.strip(), "%B").month
-            icons = item.find_all("img", alt=True)
-
+            icons = item.find_all("img")
             # For each icon, get the day box, so we can parse the correct day number and make a datetime
             for icon in icons:
-                cal_item = icon.find_parent().find_parent().find_parent().contents
-                cal_day = datetime.strptime(cal_item[1].text.strip(), "%d").day
-                bin_date = datetime(cal_year, cal_month, cal_day)
+                cal_item = icon.find_parent().find_parent()
+                bin_date = datetime.strptime(
+                    cal_item["title"],
+                    "%A, %d %B %Y",
+                )
 
                 # If the collection date is in the future, we want the date. Select the correct type, add the new
                 # datetime, then add to the list
                 if datetime.now() <= bin_date:
                     dict_data = {
-                        "type": bin_types.get(icon["src"].lower()),
+                        "type": bin_types.get(icon["src"]),
                         "collectionDate": bin_date.strftime(date_format),
                     }
                     data["bins"].append(dict_data)

uk_bin_collection-0.98.4/uk_bin_collection/uk_bin_collection/councils/ManchesterCityCouncil.py

@@ -0,0 +1,90 @@
+from datetime import datetime
+
+import requests
+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
+
+
+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:
+        # Get and check UPRN
+        user_uprn = kwargs.get("uprn")
+        check_uprn(user_uprn)
+        bindata = {"bins": []}
+
+        COLLECTION_MAP = {
+            "ahtm_dates_black_bin": "Black bin",
+            "ahtm_dates_brown_commingled_bin": "Brown bin",
+            "ahtm_dates_blue_pulpable_bin": "Blue bin",
+            "ahtm_dates_green_organic_bin": "Green Bin",
+        }
+
+        API_URL = "https://manchester.form.uk.empro.verintcloudservices.com/api/custom?action=bin_checker-get_bin_col_info&actionedby=_KDF_custom&loadform=true&access=citizen&locale=en"
+        AUTH_URL = "https://manchester.form.uk.empro.verintcloudservices.com/api/citizen?archived=Y&preview=false&locale=en"
+        AUTH_KEY = "Authorization"
+
+        r = requests.get(AUTH_URL)
+        r.raise_for_status()
+        auth_token = r.headers[AUTH_KEY]
+
+        post_data = {
+            "name": "sr_bin_coll_day_checker",
+            "data": {
+                "uprn": user_uprn,
+                "nextCollectionFromDate": (datetime.now() - timedelta(days=1)).strftime(
+                    "%Y-%m-%d"
+                ),
+                "nextCollectionToDate": (datetime.now() + timedelta(days=30)).strftime(
+                    "%Y-%m-%d"
+                ),
+            },
+            "email": "",
+            "caseid": "",
+            "xref": "",
+            "xref1": "",
+            "xref2": "",
+        }
+
+        headers = {
+            "referer": "https://manchester.portal.uk.empro.verintcloudservices.com/",
+            "accept": "application/json",
+            "content-type": "application/json",
+            AUTH_KEY: auth_token,
+        }
+
+        r = requests.post(API_URL, data=json.dumps(post_data), headers=headers)
+        r.raise_for_status()
+
+        result = r.json()
+        print(result["data"])
+
+        for key, value in result["data"].items():
+            if key.startswith("ahtm_dates_"):
+                print(key)
+                print(value)
+
+                dates_list = [
+                    datetime.strptime(date.strip(), "%d/%m/%Y %H:%M:%S").date()
+                    for date in value.split(";")
+                    if date.strip()
+                ]
+
+                for current_date in dates_list:
+                    dict_data = {
+                        "type": COLLECTION_MAP.get(key),
+                        "collectionDate": current_date.strftime(date_format),
+                    }
+                    bindata["bins"].append(dict_data)
+
+        bindata["bins"].sort(
+            key=lambda x: datetime.strptime(x.get("collectionDate"), "%d/%m/%Y")
+        )
+        return bindata

{uk_bin_collection-0.98.3 → uk_bin_collection-0.98.4}/uk_bin_collection/uk_bin_collection/councils/NeathPortTalbotCouncil.py

@@ -106,6 +106,7 @@ class CouncilClass(AbstractGetBinDataClass):
                     bin_date = datetime.strptime(
                         date.get_text(strip=True)
                         .removesuffix("(Today)")
+                        .removesuffix("(Tomorrow)")
                         .replace("&nbsp", " ")
                         + " "
                         + datetime.now().strftime("%Y"),

{uk_bin_collection-0.98.3 → uk_bin_collection-0.98.4}/uk_bin_collection/uk_bin_collection/councils/UttlesfordDistrictCouncil.py

@@ -10,7 +10,6 @@ from selenium.webdriver.common.keys import Keys
 from selenium.webdriver.support import expected_conditions as EC
 from selenium.webdriver.support.ui import Select
 from selenium.webdriver.support.wait import WebDriverWait
-from uk_bin_collection.uk_bin_collection.common import *
 
 from uk_bin_collection.uk_bin_collection.common import *
 from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
@@ -91,9 +90,10 @@ class CouncilClass(AbstractGetBinDataClass):
                 if len(cols) == 2:
                     bin_types = [img["alt"] for img in cols[0].find_all("img")]
                     collection_date_str = cols[1].text
-                    collection_date = datetime.strptime(
-                        collection_date_str, "%A %dth %B"
+                    collection_date_str = remove_ordinal_indicator_from_date_string(
+                        collection_date_str
                     )
+                    collection_date = datetime.strptime(collection_date_str, "%A %d %B")
                     collection_date = collection_date.replace(
                         year=2024
                     )  # Assuming the year is 2024

{uk_bin_collection-0.98.3 → uk_bin_collection-0.98.4}/uk_bin_collection/uk_bin_collection/councils/ValeofWhiteHorseCouncil.py

@@ -1,5 +1,6 @@
 import requests
 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
 
@@ -89,11 +90,7 @@ class CouncilClass(AbstractGetBinDataClass):
                 raise ValueError(f"Error parsing bin data: {ex}")
 
             # Build data dict for each entry
-            dict_data = {
-                "type": bin_type,
-                "collectionDate": bin_date,
-                "colour": bin_colour,
-            }
+            dict_data = {"type": bin_type, "collectionDate": bin_date}
             data["bins"].append(dict_data)
 
         data["bins"].sort(

{uk_bin_collection-0.98.3 → uk_bin_collection-0.98.4}/uk_bin_collection/uk_bin_collection/councils/WestSuffolkCouncil.py

@@ -65,7 +65,6 @@ class CouncilClass(AbstractGetBinDataClass):
 
                     dict_data = {
                         "type": bin_name_clean,
-                        "colour": bin_colour,
                         "collectionDate": next_collection.strftime(date_format),
                     }
 

uk_bin_collection-0.98.3/uk_bin_collection/uk_bin_collection/councils/ManchesterCityCouncil.py

@@ -1,107 +0,0 @@
-from datetime import datetime
-
-import requests
-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
-
-
-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:
-        # Get and check UPRN
-        user_uprn = kwargs.get("uprn")
-        check_uprn(user_uprn)
-
-        # Start a new session to walk through the form
-        requests.packages.urllib3.disable_warnings()
-        s = requests.Session()
-
-        # There's a cookie that makes the whole thing valid when you search for a postcode,
-        # but postcode and UPRN is a hassle imo, so this makes a request for the session to get a cookie
-        # using a Manchester City Council postcode I hardcoded in the data payload
-        postcode_request_header = {
-            "authority": "www.manchester.gov.uk",
-            "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,"
-            "image/webp,image/apng,*/*;q=0.8",
-            "accept-language": "en-GB,en;q=0.6",
-            "cache-control": "max-age=0",
-            # Requests sorts cookies= alphabetically
-            "origin": "https://www.manchester.gov.uk",
-            "referer": "https://www.manchester.gov.uk/bincollections",
-            "sec-fetch-dest": "document",
-            "sec-fetch-mode": "navigate",
-            "sec-fetch-site": "same-origin",
-            "sec-fetch-user": "?1",
-            "sec-gpc": "1",
-            "upgrade-insecure-requests": "1",
-            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, "
-            "like Gecko) Chrome/104.0.5112.102 Safari/537.36",
-        }
-        postcode_request_data = {
-            "mcc_bin_dates_search_term": "M2 5DB",
-            "mcc_bin_dates_submit": "Go",
-        }
-        response = s.post(
-            "https://www.manchester.gov.uk/bincollections",
-            headers=postcode_request_header,
-            data=postcode_request_data,
-        )
-
-        # Make a POST with the same cookie-fied session using the user's UPRN data
-        uprn_request_headers = {
-            "authority": "www.manchester.gov.uk",
-            "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8",
-            "accept-language": "en-GB,en;q=0.6",
-            "cache-control": "max-age=0",
-            # Requests sorts cookies= alphabetically
-            # 'cookie': 'TestCookie=Test; CookieConsent={stamp:%27D8rypjMDBJhpfMWybSMdGXP1hCZWGJYtGETiMTu1UuXTdRIKl8SU5g==%27%2Cnecessary:true%2Cpreferences:true%2Cstatistics:true%2Cmarketing:true%2Cver:6%2Cutc:1661783732090%2Cregion:%27gb%27}; PHPSESSID=kElJxYAt%2Cf-4ZWoskt0s5tn32BUQRXDYUVp3G-NsqOAOaeIcKlm2T4r7ATSgqfz6',
-            "origin": "https://www.manchester.gov.uk",
-            "referer": "https://www.manchester.gov.uk/bincollections",
-            "sec-fetch-dest": "document",
-            "sec-fetch-mode": "navigate",
-            "sec-fetch-site": "same-origin",
-            "sec-fetch-user": "?1",
-            "sec-gpc": "1",
-            "upgrade-insecure-requests": "1",
-            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.102 Safari/537.36",
-        }
-        uprn_request_data = {
-            "mcc_bin_dates_uprn": user_uprn,
-            "mcc_bin_dates_submit": "Go",
-        }
-        response = s.post(
-            "https://www.manchester.gov.uk/bincollections",
-            headers=uprn_request_headers,
-            data=uprn_request_data,
-        )
-
-        # Make that BS4 object and use it to prettify the response
-        soup = BeautifulSoup(response.content, features="html.parser")
-        soup.prettify()
-
-        # Get the collection items on the page and strip the bits of text that we don't care for
-        collections = []
-        for bin in soup.find_all("div", {"class": "collection"}):
-            bin_type = bin.find_next("h3").text.replace("  DUE TODAY", "").strip()
-            next_collection = bin.find_next("p").text.replace("Next collection ", "")
-            next_collection = datetime.strptime(next_collection, "%A %d %b %Y")
-            collections.append((bin_type, next_collection))
-
-        # Sort the collections by date order rather than bin type, then return as a dictionary (with str date)
-        ordered_data = sorted(collections, key=lambda x: x[1])
-        data = {"bins": []}
-        for item in ordered_data:
-            dict_data = {
-                "type": item[0],
-                "collectionDate": item[1].strftime(date_format),
-            }
-            data["bins"].append(dict_data)
-
-        return data