Merge pull request #5 from AdrianoKF/4-infection-data-parsing-error

Update infection data parser for new web page layout
AdrianoKF · Sep 17, 2021 · 2b453f4 · 2b453f4
2 parents 35d5232 + 62904f4
commit 2b453f4
Showing 1 changed file with 6 additions and 9 deletions.
diff --git a/custom_components/home_assistant_covid19_augsburg/crawler.py b/custom_components/home_assistant_covid19_augsburg/crawler.py
@@ -107,8 +107,8 @@ async def crawl_incidence(self) -> IncidenceData:
         )
         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)
@@ -120,18 +120,15 @@ async def crawl_incidence(self) -> IncidenceData:
         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.]+)",