uk_bin_collection 0.152.4__tar.gz → 0.152.5__tar.gz

{uk_bin_collection-0.152.4 → uk_bin_collection-0.152.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.152.4
+Version: 0.152.5
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.152.4 → uk_bin_collection-0.152.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.152.4"
+version = "0.152.5"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]
@@ -71,6 +71,6 @@ version_scheme = "semver"
 version_files = [
     "custom_components/uk_bin_collection/manifest.json:version",
     "custom_components/uk_bin_collection/manifest.json:requirements",
-    "custom_components/uk_bin_collection/config_flow.py:githubusercontent"
+    "custom_components/uk_bin_collection/const.py:INPUT_JSON_URL"
 ]
 

{uk_bin_collection-0.152.4 → uk_bin_collection-0.152.5}/uk_bin_collection/tests/input.json

@@ -2181,7 +2181,7 @@
     },
     "SouthRibbleCouncil": {
         "uprn": "10013243496",
-        "postcode": "PR26 7RZ",
+        "postcode": "PR266QW",
         "url": "https://forms.chorleysouthribble.gov.uk/xfp/form/70",
         "wiki_command_url_override": "https://forms.chorleysouthribble.gov.uk/xfp/form/70",
         "wiki_name": "South Ribble",

uk_bin_collection-0.152.5/uk_bin_collection/uk_bin_collection/councils/SouthRibbleCouncil.py

@@ -0,0 +1,130 @@
+from typing import Dict, List, Any, Optional
+from bs4 import BeautifulSoup
+from dateutil.relativedelta import relativedelta
+import requests
+import re
+from datetime import datetime
+from uk_bin_collection.uk_bin_collection.common import check_uprn, check_postcode, date_format
+from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
+from dateutil.parser import parse
+
+
+class CouncilClass(AbstractGetBinDataClass):
+    def get_data(self, url: str) -> str:
+        # This method is not used in the current implementation
+        return ""
+
+    def parse_data(self, page: str, **kwargs: Any) -> Dict[str, List[Dict[str, str]]]:
+        postcode: Optional[str] = kwargs.get("postcode")
+        uprn: Optional[str] = kwargs.get("uprn")
+
+        if postcode is None or uprn is None:
+            raise ValueError("Both postcode and UPRN are required.")
+
+        check_postcode(postcode)
+        check_uprn(uprn)
+
+        session = requests.Session()
+        headers = {
+            "User-Agent": (
+                "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
+                "(KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36"
+            )
+        }
+        session.headers.update(headers)
+
+        # Step 1: Load form and get token + field names
+        initial_url = "https://forms.chorleysouthribble.gov.uk/xfp/form/70"
+        get_resp = session.get(initial_url)
+        soup = BeautifulSoup(get_resp.text, "html.parser")
+
+        token = soup.find("input", {"name": "__token"})["value"]
+        page_id = soup.find("input", {"name": "page"})["value"]
+        postcode_field = soup.find("input", {"type": "text", "name": re.compile(".*_0_0")})["name"]
+
+        # Step 2: Submit postcode
+        post_resp = session.post(
+            initial_url,
+            data={
+                "__token": token,
+                "page": page_id,
+                "locale": "en_GB",
+                postcode_field: postcode,
+                "next": "Next",
+            },
+        )
+
+        soup = BeautifulSoup(post_resp.text, "html.parser")
+        token = soup.find("input", {"name": "__token"})["value"]
+        address_field_el = soup.find("select", {"name": re.compile(".*_1_0")})
+        if not address_field_el:
+            raise ValueError("Failed to find address dropdown after postcode submission.")
+
+        address_field = address_field_el["name"]
+
+        # Step 3: Submit UPRN and retrieve bin data
+        final_resp = session.post(
+            initial_url,
+            data={
+                "__token": token,
+                "page": page_id,
+                "locale": "en_GB",
+                postcode_field: postcode,
+                address_field: uprn,
+                "next": "Next",
+            },
+        )
+
+        soup = BeautifulSoup(final_resp.text, "html.parser")
+        table = soup.find("table", class_="data-table")
+        if not table:
+            raise ValueError("Could not find bin collection table.")
+
+        rows = table.find("tbody").find_all("tr")
+        data: Dict[str, List[Dict[str, str]]] = {"bins": []}
+
+        # Extract bin type mapping from JavaScript
+        bin_type_map = {}
+        scripts = soup.find_all("script", type="text/javascript")
+        for script in scripts:
+            if script.string and "const bintype = {" in script.string:
+                match = re.search(r'const bintype = \{([^}]+)\}', script.string, re.DOTALL)
+                if match:
+                    bintype_content = match.group(1)
+                    for line in bintype_content.split('\n'):
+                        line = line.strip()
+                        if '"' in line and ':' in line:
+                            parts = line.split(':', 1)
+                            if len(parts) == 2:
+                                key = parts[0].strip().strip('"').strip("'")
+                                value = parts[1].strip().rstrip(',').strip().strip('"').strip("'")
+                                bin_type_map[key] = value
+                    break
+
+        for row in rows:
+            cells = row.find_all("td")
+            if len(cells) >= 2:
+                bin_type_cell = cells[0]
+                bin_type = bin_type_cell.get_text(strip=True)
+                bin_type = bin_type_map.get(bin_type, bin_type)
+
+                date_text = cells[1].get_text(strip=True)
+                date_parts = date_text.split(", ")
+                date_str = date_parts[1] if len(date_parts) == 2 else date_text
+
+                try:
+                    day, month, year = date_str.split('/')
+                    year = int(year)
+                    if year < 100:
+                        year = 2000 + year
+
+                    date_obj = datetime(year, int(month), int(day)).date()
+
+                    data["bins"].append({
+                        "type": bin_type,
+                        "collectionDate": date_obj.strftime(date_format)
+                    })
+                except Exception:
+                    continue
+
+        return data

uk_bin_collection-0.152.4/uk_bin_collection/uk_bin_collection/councils/SouthRibbleCouncil.py

@@ -1,76 +0,0 @@
-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
-
-
-# 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_uprn = kwargs.get("uprn")
-        user_postcode = kwargs.get("postcode")
-        check_uprn(user_uprn)
-        check_postcode(user_postcode)
-        bindata = {"bins": []}
-
-        session_uri = "https://forms.chorleysouthribble.gov.uk/xfp/form/70"
-        URI = "https://forms.chorleysouthribble.gov.uk/xfp/form/70#qc576c657112a8277ba6f954ebc0490c946168363_0"
-
-        session = requests.Session()
-        token_response = session.get(session_uri)
-        soup = BeautifulSoup(token_response.text, "html.parser")
-        token = soup.find("input", {"name": "__token"}).attrs["value"]
-
-        form_data = {
-            "__token": token,
-            "page": "196",
-            "locale": "en_GB",
-            "qc576c657112a8277ba6f954ebc0490c946168363_0_0": user_postcode,
-            "qc576c657112a8277ba6f954ebc0490c946168363_1_0": user_uprn,
-            "next": "Next",
-        }
-
-        collection_response = session.post(URI, data=form_data)
-
-        #collection_soup = BeautifulSoup(collection_response.text, "html.parser")
-        
-
-        soup = BeautifulSoup(collection_response.text, "html.parser")
-        #print(soup)
-
-        rows = soup.find("table").find_all("tr")
-
-        # Form a JSON wrapper
-        data: Dict[str, List[Dict[str, str]]] = {"bins": []}
-
-        # Loops the Rows
-        for row in rows:
-            cells = row.find_all("td")
-            
-            if cells:
-                bin_type = cells[0].get_text(strip=True)
-                collection_next = cells[1].get_text(strip=True)
-
-                if len(collection_next) != 1:
-                    collection_date_obj = datetime.strptime(collection_next, "%d/%m/%y").date()
-                    # since we only have the next collection day, if the parsed date is in the past,
-                    # assume the day is instead next month
-                    if collection_date_obj < datetime.now().date():
-                        collection_date_obj += relativedelta(months=1)
-                    # Make each Bin element in the JSON
-                    dict_data = {
-                        "type": bin_type,
-                        "collectionDate": collection_date_obj.strftime("%d/%m/%Y"),
-                    }
-                    # Add data to the main JSON Wrapper
-                    data["bins"].append(dict_data)
-                    continue      
-        return data