Merge pull request #11 from AdrianoKF/10-negative-first-vaccination-doses

Fix for negative number of first vaccination doses

custom_components/home_assistant_covid19_augsburg/crawler.py

@@ -59,10 +59,12 @@ class VaccinationData:
     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):
@@ -107,11 +109,11 @@ class CovidCrawler(CovidCrawlerBase):
         )
         soup = await self._fetch(url)
 
-        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=}"
@@ -120,18 +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=}")
 
-        date = parse_date(matches.group(1), matches.group(2))
+        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.]+)",
@@ -168,9 +167,9 @@ class CovidCrawler(CovidCrawlerBase):
         result = soup.find(id=container_id)
         text = re.sub(r"\s+", " ", result.text)
         regexes = [
-            r"(?P<total_vaccinations>\d+[.]\d+) Impfdosen",
-            r"Weitere (?P<num_vaccinated_once>\d+[.]\d+) Personen haben die Erstimpfung erhalten",
-            r"(?P<num_vaccinated_full>\d+[.]\d+) Personen sind bereits vollständig geimpft",
+            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:
@@ -188,18 +187,24 @@ class CovidCrawler(CovidCrawlerBase):
         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["date"] = parse_date(**matches.groupdict()).strftime("%Y-%m-%d")
         result = VaccinationData(**values)
 
-        # Total population in Augsburg as of 2020
-        # https://www.augsburg.de/fileadmin/user_upload/buergerservice_rathaus/rathaus/statisiken_und_geodaten/statistiken/Monitoring/Demografiemonitoring_der_Stadt_Augsburg_2021.pdf
-        population = 299021
+        # 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/manifest.json

@@ -1,11 +1,15 @@
 {
-    "domain": "covid19_augsburg",
-    "name": "COVID-19 Augsburg",
-    "version": "1.1.1",
-    "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"]
-  }
+  "domain": "covid19_augsburg",
+  "name": "COVID-19 Augsburg",
+  "version": "1.2.1",
+  "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"
+  ]
+}

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
-name = "git add re"
-version = "0.1.0"
+name = "home_assistant_covid19_augsburg"
+version = "1.2.1"
 description = ""
 authors = ["Adrian Rumpold <a.rumpold@gmail.com>"]
 packages = [