adriano/home-assistant-covid19-augsburg
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

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

Browse Source 
Update infection data parser for new web page layout
This commit is contained in:
Adrian Rumpold
2021-09-17 08:34:55 +02:00
committed by GitHub
parent 35d5232d8e 62904f4c09
commit 2b453f4b5e
1 changed files with 6 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
custom_components/home_assistant_covid19_augsburg/crawler.py
View File

@@ -107,8 +107,8 @@ 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)
@@ -120,18 +120,15 @@ 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.]+)",