Merge pull request #9 from AdrianoKF/8-new-vaccination-report-format

Support new vaccination report format

.github/workflows/python-app.yml

@@ -0,0 +1,62 @@
+# This workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: Python application
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python 3.9
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.9
+    - name: Cache
+      uses: actions/cache@v2.1.6
+      with:
+        # A list of files, directories, and wildcard patterns to cache and restore
+        path: .venv
+        # An explicit key for restoring and saving the cache
+        key: venv-cache-${{hashFiles('**/poetry.lock')}}
+        restore-keys: |
+          venv-cache-${{hashFiles('**/poetry.lock')}}
+          venv-cache-
+    - name: Python Poetry Action
+      # You may pin to the exact commit or the version.
+      # uses: abatilo/actions-poetry@8284d202bc272a8d0597e26e1c0b4a0d0c73db93
+      uses: abatilo/actions-poetry@v2.1.0
+      with:
+        # The version of poetry to install
+        poetry-version: 1.1.7
+    - name: Install dependencies
+      run: |
+        poetry config virtualenvs.in-project true
+        poetry install
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        poetry run flake8 . --count --exclude .git,.venv --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        poetry run flake8 . --count --exclude .git,.venv  --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Test with pytest
+      run: |
+        poetry run pytest
+
+  validate:
+    runs-on: "ubuntu-latest"
+    steps:
+      - uses: "actions/checkout@v2"
+      - name: HACS validation
+        uses: "hacs/action@main"
+        with:
+          category: "integration"
+          ignore: brands wheels

README.md

@@ -2,7 +2,8 @@
 
 ## Adding to your dashboard
 
-You can add an overview of the current infection numbers to your dashboard using the [multiple-entity-row](https://github.com/benct/lovelace-multiple-entity-row) card:
+You can add an overview of the current infection and vaccination numbers to your dashboard
+using the [multiple-entity-row](https://github.com/benct/lovelace-multiple-entity-row) card:
 
 ```yaml
 type: entities
@@ -24,4 +25,25 @@ entities:
     secondary_info:
       attribute: incidence
       unit: cases/100k
+  - type: custom:multiple-entity-row
+    entity: sensor.covid_19_vaccinations_augsburg
+    entities:
+      - attribute: ratio_vaccinated_once
+        name: Once
+        format: precision1
+        unit: '%'
+      - attribute: ratio_vaccinated_full
+        name: Fully
+        format: precision1
+        unit: '%'
+      - attribute: ratio_vaccinated_total
+        name: Total
+        format: precision1
+        unit: '%'
+    show_state: false
+    icon: mdi:needle
+    name: COVID-19 Vaccinations
+    secondary_info:
+      attribute: date
+      format: date
 ```

custom_components/home_assistant_covid19_augsburg/__init__.py

@@ -12,7 +12,7 @@ if TYPE_CHECKING:
     from homeassistant.core import HomeAssistant
 
 from .const import DOMAIN
-from .crawler import CovidCrawler, IncidenceData
+from .crawler import CovidCrawler
 
 _LOGGER = logging.getLogger(__name__)
 
@@ -67,9 +67,12 @@ async def get_coordinator(hass: HomeAssistant):
     if DOMAIN in hass.data:
         return hass.data[DOMAIN]
 
-    async def async_get_data() -> IncidenceData:
+    async def async_get_data() -> dict:
         crawler = CovidCrawler(hass)
-        return await crawler.crawl()
+        return {
+            "incidence": await crawler.crawl_incidence(),
+            "vaccination": await crawler.crawl_vaccination(),
+        }
 
     hass.data[DOMAIN] = DataUpdateCoordinator(
         hass,

custom_components/home_assistant_covid19_augsburg/crawler.py

@@ -15,6 +15,32 @@ def parse_num(s, t=int):
     return 0
 
 
+def parse_date(
+    day: int, month: str, year=datetime.datetime.now().year
+) -> datetime.date:
+    """Parse a German medium-form date, e.g. 17. August into a datetime.date"""
+    months = [
+        "Januar",
+        "Februar",
+        "März",
+        "April",
+        "Mai",
+        "Juni",
+        "Juli",
+        "August",
+        "September",
+        "Oktober",
+        "November",
+        "Dezember",
+    ]
+    date = datetime.date(
+        year=int(year),
+        month=1 + months.index(month),
+        day=parse_num(day),
+    )
+    return date
+
+
 @dataclass
 class IncidenceData:
     location: str
@@ -26,46 +52,68 @@ class IncidenceData:
     num_dead: int = 0
 
 
+@dataclass
+class VaccinationData:
+    date: str
+
+    total_vaccinations: int = 0
+    num_vaccinated_once: int = 0
+    num_vaccinated_full: int = 0
+    num_vaccinated_booster: int = 0
+
+    ratio_vaccinated_once: float = 0.0
+    ratio_vaccinated_full: float = 0.0
+    ratio_vaccinated_total: float = 0.0
+    ratio_vaccinated_booster: float = 0.0
+
+
 class CovidCrawlerBase(ABC):
     @abstractmethod
-    def crawl(self) -> IncidenceData:
+    def crawl_incidence(self) -> IncidenceData:
+        pass
+
+    @abstractmethod
+    def crawl_vaccination(self) -> VaccinationData:
         pass
 
 
 class CovidCrawler(CovidCrawlerBase):
     def __init__(self, hass=None) -> None:
-        self.url = (
-            "https://www.augsburg.de/umwelt-soziales/gesundheit/coronavirus/fallzahlen"
-        )
         self.hass = hass
 
-    async def crawl(self) -> IncidenceData:
+    async def _fetch(self, url: str) -> str:
+        """Fetch a URL, using either the current Home Assistant instance or requests"""
+
+        if self.hass:
+            from homeassistant.helpers import aiohttp_client
+
+            result = await aiohttp_client.async_get_clientsession(self.hass).get(url)
+            soup = BeautifulSoup(await result.text(), "html.parser")
+        else:
+            import requests
+
+            result = requests.get(url)
+            result.raise_for_status()
+            soup = BeautifulSoup(result.text, "html.parser")
+        return soup
+
+    async def crawl_incidence(self) -> IncidenceData:
         """
         Fetch COVID-19 infection data from the target website.
         """
 
         _log.info("Fetching COVID-19 data update")
 
-        if self.hass:
-            from homeassistant.helpers import aiohttp_client
+        url = (
+            "https://www.augsburg.de/umwelt-soziales/gesundheit/coronavirus/fallzahlen"
+        )
+        soup = await self._fetch(url)
 
-            result = await aiohttp_client.async_get_clientsession(self.hass).get(
-                self.url
-            )
-            soup = BeautifulSoup(await result.text(), "html.parser")
-        else:
-            import requests
-
-            result = requests.get(self.url)
-            if not result.ok:
-                result.raise_for_status()
-            soup = BeautifulSoup(result.text, "html.parser")
-
-        match = soup.find(class_="frame--type-textpic")
-        text = match.p.text
+        match = soup.find(id="c1067628")
+        text = match.text.strip()
         _log.debug(f"Infection data text: {text}")
 
-        matches = re.search(r"(\d+,\d+)\sNeuinfektion", text)
+        matches = re.search(r"(\d+(,\d+)?)\sNeuinfektion", text)
         if not matches:
             raise ValueError(
                 f"Could not extract incidence from scraped web page, {text=}"
@@ -74,38 +122,15 @@ class CovidCrawler(CovidCrawlerBase):
         incidence = parse_num(matches.group(1), t=float)
         _log.debug(f"Parsed incidence: {incidence}")
 
-        text = match.h2.text
-        matches = re.search(r"\((\d+)\. (\w+).*\)", text)
+        match = soup.find(id="c1052517")
+        text = match.text.strip()
+        matches = re.search(r"Stand: (\d+)\. (\w+) (\d{4})", text)
         if not matches:
             raise ValueError(f"Could not extract date from scraped web page, {text=}")
 
-        months = [
-            "Januar",
-            "Februar",
-            "März",
-            "April",
-            "Mai",
-            "Juni",
-            "Juli",
-            "August",
-            "September",
-            "Oktober",
-            "November",
-            "Dezember",
-        ]
-        day = parse_num(matches.group(1))
-        month_name = matches.group(2)
-        date = datetime.date(
-            year=datetime.datetime.now().year,
-            month=1 + months.index(month_name),
-            day=day,
-        )
+        date = parse_date(matches.group(1), matches.group(2), matches.group(3))
         _log.debug(f"Parsed date: {date}")
 
-        match = match.find_next_sibling(class_="frame--type-textpic")
-        text = match.text
-        _log.debug(f"Infection counts text: {text}")
-
         regexes = [
             r"Insgesamt: (?P<total_cases>[0-9.]+)",
             r"genesen: (?P<num_recovered>[0-9.]+)",
@@ -130,3 +155,56 @@ class CovidCrawler(CovidCrawlerBase):
         _log.debug(f"Result data: {result}")
 
         return result
+
+    async def crawl_vaccination(self) -> VaccinationData:
+        _log.info("Fetching COVID-19 vaccination data update")
+        url = (
+            "https://www.augsburg.de/umwelt-soziales/gesundheit/coronavirus/impfzentrum"
+        )
+        soup = await self._fetch(url)
+
+        container_id = "c1088140"
+        result = soup.find(id=container_id)
+        text = re.sub(r"\s+", " ", result.text)
+        regexes = [
+            r"(?P<total_vaccinations>\d+([.]\d+)?) Personen in Augsburg mindestens",
+            r"(?P<num_vaccinated_full>\d+([.]\d+)?) Personen sind mindestens zweimal geimpft",
+            r"(?P<num_vaccinated_booster>\d+([.]\d+)?) Personen haben eine Auffrischungsimpfung",
+        ]
+        values = {}
+        for r in regexes:
+            matches = re.search(r, text)
+            if not matches:
+                continue
+            values.update(
+                {
+                    k: parse_num(v.replace(".", ""))
+                    for k, v in matches.groupdict().items()
+                }
+            )
+
+        matches = re.search(r"Stand (?P<day>\d+)\. (?P<month>\w+) (?P<year>\d+)", text)
+        if not matches:
+            raise ValueError(f"Could not extract date from scraped web page, {text=}")
+
+        values["num_vaccinated_once"] = values["total_vaccinations"] - (
+            values["num_vaccinated_full"] + values["num_vaccinated_booster"]
+        )
+
+        values["date"] = parse_date(**matches.groupdict()).strftime("%Y-%m-%d")
+        result = VaccinationData(**values)
+
+        # Total population in Augsburg as listed on the crawled page
+        population = 298014
+
+        result.ratio_vaccinated_full = result.num_vaccinated_full / population * 100
+        result.ratio_vaccinated_once = result.num_vaccinated_once / population * 100
+        result.ratio_vaccinated_total = (
+            result.ratio_vaccinated_once + result.ratio_vaccinated_full
+        )
+        result.ratio_vaccinated_booster = (
+            result.num_vaccinated_booster / population * 100
+        )
+        _log.debug(f"Result data: {result}")
+
+        return result

custom_components/home_assistant_covid19_augsburg/main.py

@@ -3,7 +3,10 @@ from .crawler import CovidCrawler
 
 async def main():
     crawler = CovidCrawler()
-    result = await crawler.crawl()
+    result = await crawler.crawl_incidence()
+    print(result)
+
+    result = await crawler.crawl_vaccination()
     print(result)
 
 

custom_components/home_assistant_covid19_augsburg/manifest.json

@@ -1,9 +1,10 @@
 {
     "domain": "covid19_augsburg",
     "name": "COVID-19 Augsburg",
-    "version": "0.1.0",
+    "version": "1.2.0",
     "config_flow": true,
     "documentation": "https://github.com/AdrianoKF/home-assistant-covid19-augsburg",
+    "issue_tracker": "https://github.com/AdrianoKF/home-assistant-covid19-augsburg/issues",
     "requirements": ["beautifulsoup4==4.8.2"],
     "dependencies": [],
     "codeowners": ["@AdrianoKF"]

custom_components/home_assistant_covid19_augsburg/sensor.py

@@ -1,3 +1,5 @@
+from dataclasses import asdict
+
 from homeassistant.helpers.entity import Entity
 
 from . import get_coordinator
@@ -7,7 +9,12 @@ async def async_setup_entry(hass, _, async_add_entities):
     """Defer sensor setup to the shared sensor module."""
     coordinator = await get_coordinator(hass)
 
-    async_add_entities([CoronaAugsburgSensor(coordinator)])
+    async_add_entities(
+        [
+            CoronaAugsburgSensor(coordinator),
+            CoronaAugsburgVaccinationSensor(coordinator),
+        ]
+    )
 
 
 class CoronaAugsburgSensor(Entity):
@@ -41,18 +48,59 @@ class CoronaAugsburgSensor(Entity):
 
     @property
     def state(self):
-        return self.coordinator.data.incidence
+        return self.coordinator.data["incidence"].incidence
 
     @property
     def device_state_attributes(self):
-        return {
-            "date": self.coordinator.data.date,
-            "incidence": self.coordinator.data.incidence,
-            "total_cases": self.coordinator.data.total_cases,
-            "num_dead": self.coordinator.data.num_dead,
-            "num_recovered": self.coordinator.data.num_recovered,
-            "num_infected": self.coordinator.data.num_infected,
-        }
+        data = self.coordinator.data["incidence"]
+        return asdict(data)
+
+    async def async_added_to_hass(self):
+        """When entity is added to hass."""
+        self.coordinator.async_add_listener(self.async_write_ha_state)
+
+    async def async_will_remove_from_hass(self):
+        """When entity will be removed from hass."""
+        self.coordinator.async_remove_listener(self.async_write_ha_state)
+
+
+class CoronaAugsburgVaccinationSensor(Entity):
+    """Representation of vaccination data for the city of Augsburg"""
+
+    def __init__(self, coordinator):
+        """Initialize sensor."""
+        self.coordinator = coordinator
+        self._name = "COVID-19 Vaccinations Augsburg"
+        self._state = None
+
+    @property
+    def available(self):
+        return self.coordinator.last_update_success and self.coordinator.data
+
+    @property
+    def name(self):
+        return self._name
+
+    @property
+    def unique_id(self):
+        return self._name
+
+    @property
+    def icon(self):
+        return "mdi:needle"
+
+    @property
+    def unit_of_measurement(self):
+        return ""
+
+    @property
+    def state(self):
+        return self.coordinator.data["vaccination"].total_vaccinations
+
+    @property
+    def device_state_attributes(self):
+        data = self.coordinator.data["vaccination"]
+        return asdict(data)
 
     async def async_added_to_hass(self):
         """When entity is added to hass."""

pyproject.toml

@@ -1,5 +1,5 @@
 [tool.poetry]
-name = "git add re"
+name = "home_assistant_covid19_augsburg"
 version = "0.1.0"
 description = ""
 authors = ["Adrian Rumpold <a.rumpold@gmail.com>"]

tests/test_example.py

@@ -0,0 +1,8 @@
+"""Placeholder test suite to Pytest doesn't exit with error code
+
+TODO: Remove once other tests have been added.
+"""
+
+
+def test_example():
+    assert True