Merge pull request #350 from OliverCullimore/157-reigate-banstead

uk_bin_collection/tests/council_schemas/ReigateAndBansteadBoroughCouncil.schema

@@ -0,0 +1,39 @@
+{
+    "$schema": "http://json-schema.org/draft-06/schema#",
+    "$ref": "#/definitions/Welcome5",
+    "definitions": {
+        "Welcome5": {
+            "type": "object",
+            "additionalProperties": false,
+            "properties": {
+                "bins": {
+                    "type": "array",
+                    "items": {
+                        "$ref": "#/definitions/Bin"
+                    }
+                }
+            },
+            "required": [
+                "bins"
+            ],
+            "title": "Welcome5"
+        },
+        "Bin": {
+            "type": "object",
+            "additionalProperties": false,
+            "properties": {
+                "type": {
+                    "type": "string"
+                },
+                "collectionDate": {
+                    "type": "string"
+                }
+            },
+            "required": [
+                "collectionDate",
+                "type"
+            ],
+            "title": "Bin"
+        }
+    }
+}

uk_bin_collection/tests/features/validate_council_outputs.feature

@@ -63,6 +63,7 @@ Feature: Test each council output matches expected results in /outputs
             | NorthTynesideCouncil |
             | NorthumberlandCouncil |
             | PrestonCityCouncil |
+            | ReigateAndBansteadBoroughCouncil |
             | RochdaleCouncil |
             | RushcliffeBoroughCouncil |
             | RushmoorCouncil |

uk_bin_collection/tests/input.json

@@ -358,6 +358,13 @@
     "url": "https://selfservice.preston.gov.uk/service/Forms/FindMyNearest.aspx?Service=bins",
     "wiki_name": "Preston City Council"
   },
+  "ReigateAndBansteadBoroughCouncil": {
+    "SKIP_GET_URL": "SKIP_GET_URL",
+    "uprn": "68134867",
+    "url": "https://www.reigate-banstead.gov.uk/",
+    "wiki_name": "Reigate and Banstead Borough Council",
+    "wiki_note": "To get the UPRN, you can use [FindMyAddress](https://www.findmyaddress.co.uk/search)"
+  },
   "RochdaleCouncil": {
     "SKIP_GET_URL": "SKIP_GET_URL",
     "postcode": "OL11 5BE",

uk_bin_collection/tests/outputs/ReigateAndBansteadBoroughCouncil.json

@@ -0,0 +1,52 @@
+{
+    "bins": [
+        {
+            "type": "Food waste",
+            "collectionDate": "03/10/2023"
+        },
+        {
+            "type": "Paper and cardboard",
+            "collectionDate": "03/10/2023"
+        },
+        {
+            "type": "Food waste",
+            "collectionDate": "10/10/2023"
+        },
+        {
+            "type": "Paper and cardboard",
+            "collectionDate": "10/10/2023"
+        },
+        {
+            "type": "Mixed recycling",
+            "collectionDate": "10/10/2023"
+        },
+        {
+            "type": "Refuse",
+            "collectionDate": "10/10/2023"
+        },
+        {
+            "type": "Food waste",
+            "collectionDate": "17/10/2023"
+        },
+        {
+            "type": "Paper and cardboard",
+            "collectionDate": "17/10/2023"
+        },
+        {
+            "type": "Food waste",
+            "collectionDate": "24/10/2023"
+        },
+        {
+            "type": "Paper and cardboard",
+            "collectionDate": "24/10/2023"
+        },
+        {
+            "type": "Mixed recycling",
+            "collectionDate": "24/10/2023"
+        },
+        {
+            "type": "Refuse",
+            "collectionDate": "24/10/2023"
+        }
+    ]
+}

uk_bin_collection/uk_bin_collection/councils/ReigateAndBansteadBoroughCouncil.py

@@ -0,0 +1,69 @@
+import time
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support import expected_conditions as EC
+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:
+        # Set up Selenium to run 'headless'
+        options = webdriver.ChromeOptions()
+        options.add_argument("--headless")
+        options.add_argument("--no-sandbox")
+        options.add_argument("--disable-gpu")
+        options.add_argument("--disable-dev-shm-usage")
+        options.add_experimental_option("excludeSwitches", ["enable-logging"])
+
+        user_uprn = kwargs.get("uprn")
+        check_uprn(user_uprn)
+        # Pad UPRN with 0's at the start for any that aren't 12 chars
+        user_uprn = user_uprn.zfill(12)
+
+        # Create Selenium webdriver
+        driver = webdriver.Chrome(options=options)
+        driver.get(f"https://my.reigate-banstead.gov.uk/en/service/Bins_and_recycling___collections_calendar?uprn={user_uprn}")
+
+        # Wait for iframe to load and switch to it
+        WebDriverWait(driver, 30).until(EC.frame_to_be_available_and_switch_to_it((By.ID, 'fillform-frame-1')))
+
+        # Wait for form
+        WebDriverWait(driver, 30).until(EC.presence_of_element_located((By.CSS_SELECTOR, 'span[data-name="html2"] > div')))
+
+        # Make a BS4 object
+        soup = BeautifulSoup(driver.page_source, features="html.parser")
+        soup.prettify()
+
+        data = {"bins": []}
+        section = soup.find("span", {"data-name": "html2"})
+        dates = section.find_all("div")
+        for d in dates:
+            date = d.find("h3")
+            collections = d.find_all("li")
+            if date and collections:
+                collection_date = datetime.strptime(date.get_text(strip=True), "%A %d %B %Y").strftime(date_format)
+                for c in collections:
+                    collection_type = c.get_text(strip=True)
+                    if c.get_text(strip=True):
+                        dict_data = {
+                            "type": collection_type,
+                            "collectionDate": collection_date,
+                        }
+                        data["bins"].append(dict_data)
+
+        data["bins"].sort(
+            key=lambda x: datetime.strptime(x.get("collectionDate"), date_format)
+        )
+
+        return data