Add scraper

Signed-off-by: AKP <tom@tdpain.net>

circuit-laundry-notifier/circuit_scraper.py

@@ -0,0 +1,89 @@
+from typing import *
+from enum import Enum
+from dataclasses import dataclass
+import requests
+from bs4 import BeautifulSoup
+
+
+class MachineState(Enum):
+    Available = "AVAIL"
+    InUse = "IN_USE"
+    Completed = "COMPLETED"
+    Unknown = "UNKNOWN"
+
+
+class MachineType(Enum):
+    Washer = "WASHER"
+    Dryer = "DRYER"
+
+
+@dataclass(init=False, repr=True)
+class Machine:
+    number: str
+    type: MachineType
+    state: MachineState
+    minutes_remaining: Optional[int]
+
+
+class CircuitScraper:
+    _base_url: str = "https://www.circuit.co.uk/circuit-view/laundry-site"
+
+    _class_washer = "accordion__title"
+    _class_dryer = "accordion__title--dryer"
+    _class_in_use = "accordion__title--in-use"
+    _class_completed = "accordion__title--idle"
+    _class_state_unknown = "accordion__title--unknown"
+
+    @staticmethod
+    def _get_site_url(site_id: str) -> str:
+        return CircuitScraper._base_url + f"/?site={site_id}"
+
+    @staticmethod
+    def get_site_machine_states(site_id: str) -> List[Machine]:
+        site_url = CircuitScraper._get_site_url(site_id)
+
+        r = requests.get(site_url)
+        r.raise_for_status()
+
+        soup = BeautifulSoup(r.content, "html.parser")
+
+        machines = []
+        for item in soup.select("section.accordions--circuit-view.js-machine-type"):
+            machines += list(item.select("div.accordion"))
+
+        for item in machines:
+            states = item.select("div.accordion__slug div.accordion__title")
+            if len(states) == 0:
+                continue
+
+            attr_classes = states[0].attrs.get("class", [])
+            machine = Machine()
+
+            descriptor_text = states[0].get_text().lower()
+
+            machine.type = MachineType.Dryer if "dryer" in descriptor_text else MachineType.Washer
+            machine.number = descriptor_text.replace("washer", "").replace("dryer", "").strip()
+
+            # Note that CircuitScraper._class_washer is included on every item, hence if it's none of the other ones are
+            # present, we fall back to that one.
+            if CircuitScraper._class_in_use in attr_classes:
+                machine.state = MachineState.InUse
+            elif CircuitScraper._class_completed in attr_classes:
+                machine.state = MachineState.Completed
+            elif CircuitScraper._class_state_unknown in attr_classes:
+                machine.state = MachineState.Unknown
+            elif CircuitScraper._class_dryer in attr_classes:
+                # Technically we could just pretend this one doesn't exist, but we'll keep it in for posterity's sake.
+                machine.state = MachineState.Available
+            else:
+                machine.state = MachineState.Available
+
+            if machine.state == MachineState.InUse:
+                minutes_remaining_text = item.select("p span")[0].get_text(strip=True)
+                machine.minutes_remaining = int(minutes_remaining_text.replace("mins", "").strip())
+            else:
+                machine.minutes_remaining = None
+
+            machines.append(machine)
+
+        return machines

poetry.lock

@@ -0,0 +1,94 @@
+[[package]]
+name = "beautifulsoup4"
+version = "4.11.1"
+description = "Screen-scraping library"
+category = "main"
+optional = false
+python-versions = ">=3.6.0"
+
+[package.dependencies]
+soupsieve = ">1.2"
+
+[package.extras]
+html5lib = ["html5lib"]
+lxml = ["lxml"]
+
+[[package]]
+name = "certifi"
+version = "2022.9.24"
+description = "Python package for providing Mozilla's CA Bundle."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "charset-normalizer"
+version = "2.1.1"
+description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
+category = "main"
+optional = false
+python-versions = ">=3.6.0"
+
+[package.extras]
+unicode_backport = ["unicodedata2"]
+
+[[package]]
+name = "idna"
+version = "3.4"
+description = "Internationalized Domain Names in Applications (IDNA)"
+category = "main"
+optional = false
+python-versions = ">=3.5"
+
+[[package]]
+name = "requests"
+version = "2.28.1"
+description = "Python HTTP for Humans."
+category = "main"
+optional = false
+python-versions = ">=3.7, <4"
+
+[package.dependencies]
+certifi = ">=2017.4.17"
+charset-normalizer = ">=2,<3"
+idna = ">=2.5,<4"
+urllib3 = ">=1.21.1,<1.27"
+
+[package.extras]
+socks = ["PySocks (>=1.5.6,!=1.5.7)"]
+use_chardet_on_py3 = ["chardet (>=3.0.2,<6)"]
+
+[[package]]
+name = "soupsieve"
+version = "2.3.2.post1"
+description = "A modern CSS selector implementation for Beautiful Soup."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "urllib3"
+version = "1.26.12"
+description = "HTTP library with thread-safe connection pooling, file post, and more."
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, <4"
+
+[package.extras]
+brotli = ["brotlicffi (>=0.8.0)", "brotli (>=1.0.9)", "brotlipy (>=0.6.0)"]
+secure = ["pyOpenSSL (>=0.14)", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "certifi", "urllib3-secure-extra", "ipaddress"]
+socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
+
+[metadata]
+lock-version = "1.1"
+python-versions = "^3.8"
+content-hash = "f387c917af52c11962400d12327a47dde4e322812f89078f6592ed4809432d7a"
+
+[metadata.files]
+beautifulsoup4 = []
+certifi = []
+charset-normalizer = []
+idna = []
+requests = []
+soupsieve = []
+urllib3 = []