def sanitize_row(row):
# sanitize data:
# 2020-12-04 contains 'Non communiqué' entries, skip them for now
if not sc.represents_int(
row.get('Nombre de cas actuellement hospitalisés')):
row['Nombre de cas actuellement hospitalisés'] = ''
if not sc.represents_int(
row.get('Nombre de cas actuellement en soins intensifs')):
row['Nombre de cas actuellement en soins intensifs'] = ''
if not sc.represents_int(row.get('Nombre de nouveaux décès')):
row['Nombre de nouveaux décès'] = ''
return row
if data:
# nothing to do here
continue
# we should never reach here unless there is an unknown iframe
raise Exception(f"issue parsing data in iframe {iframe_url}")
# order dict by key to ensure the most recent entry is last
ordered_rows = OrderedDict(sorted(rows.items()))
for row_date, row in ordered_rows.items():
if not is_first:
print('-' * 10)
is_first = False
dd = sc.DayData(canton='BL', url=main_url)
dd.datetime = row['date']
dd.cases = sc.safeint(row.get('cases'))
dd.hospitalized = sc.safeint(row.get('hospitalized'))
dd.icu = sc.safeint(row.get('icu'))
dd.vent = sc.safeint(row.get('vent'))
dd.deaths = sc.safeint(row.get('deaths'))
dd.recovered = sc.safeint(row.get('recovered'))
dd.quarantined = sc.safeint(row.get('quarantined'))
dd.quarantine_riskareatravel = sc.safeint(
row.get('quarantine_riskareatravel'))
if sc.represents_int(dd.quarantined) and sc.represents_int(
dd.quarantine_riskareatravel):
dd.quarantine_total = dd.quarantined + dd.quarantine_riskareatravel
dd.isolated = sc.safeint(row.get('isolated'))
print(dd)
r'befanden\ssich\s(\d+)\spositive\sF.lle\snoch\simmer\sin\sIsolation',
content)
dd.quarantined = sc.find(r'Isolation\sund\s(\d+)\sKontakte\sin\sQuarant.ne',
content)
dd.quarantine_riskareatravel = sc.find(r'\s(\d+)\sReisende\sin\sQuarant.ne',
content)
print(dd)
xls_url = 'https://raw.githubusercontent.com/statistikZH/covid19_drop/master/Chiffres%20%20COVID-19%20Valais.xlsx'
main_url = 'https://www.vs.ch/de/web/coronavirus'
xls = sc.xlsdownload(xls_url, silent=True)
rows = sc.parse_xls(xls, header_row=1)
for i, row in enumerate(rows):
if not isinstance(row['Date'], datetime.datetime):
continue
if not sc.represents_int(row['Cumul cas positifs']):
continue
if row['Nb nouveaux cas positifs'] is None and row[
"Nb nouvelles admissions à l'hôpital"] is None:
continue
dd = sc.DayData(canton='VS', url=main_url)
dd.datetime = row['Date'].date().isoformat()
dd.cases = row['Cumul cas positifs']
dd.hospitalized = row['Total hospitalisations COVID-19']
dd.new_hosp = row['Nb nouvelles admissions à l\'hôpital']
dd.icu = row['Patients COVID-19 aux SI total (y.c. intubés)']
dd.vent = row['Patients COVID-19 intubés']
dd.deaths = row['Cumul décès COVID-19']
if row['Nb de nouvelles sorties'] is not None:
dd.recovered = sum(r['Nb de nouvelles sorties'] for r in rows[:i + 1])
isolated_date = isolated_table.find_next(string=re.compile("Stand")).string
dd_isolated.datetime = sc.find(r'Stand:?\s*(.+[0-9]{4})', isolated_date)
rows = isolated_table.find_all('tr')
headers = rows[0].find_all('td') or rows[0].find_all('th')
assert len(
headers) == 2, f"Number of header columns changed, {len(headers)} != 2"
assert headers[1].text.strip() == "Anzahl"
for i in range(1, len(rows)):
cells = rows[i].find_all('td')
if cells[0].text.strip() == 'Positiv Getestete im Tracing / in Isolation':
value = cells[1].text.strip()
if sc.represents_int(value):
dd_isolated.isolated = int(value)
elif cells[0].text.strip() == 'Kontaktpersonen im Tracing / in Quarantäne':
value = cells[1].text.strip()
if sc.represents_int(value):
dd_isolated.quarantined = int(value)
if dd_isolated:
print(dd_isolated)
print('-' * 10)
# historized cases
csv_url = 'https://www.sg.ch/ueber-den-kanton-st-gallen/statistik/covid-19/_jcr_content/Par/sgch_downloadlist/DownloadListPar/sgch_download.ocFile/KantonSG_C19-Faelle_download.csv'
d = sc.download(csv_url, silent=True)
# strip the "header" / description lines
'https://www.jura.ch/fr/Autorites/Coronavirus/Chiffres-H-JU/Evolution-des-cas-COVID-19-dans-le-Jura.html',
silent=True)
soup = BeautifulSoup(d, 'html.parser')
box = soup.find('li', class_="ico-xlsx")
xls_url = box.find('a').get('href')
assert xls_url, "URL is empty"
if not xls_url.startswith('http'):
xls_url = f'https://www.jura.ch{xls_url}'
xls = sc.xlsdownload(xls_url, silent=True)
rows = sc.parse_xls(xls, header_row=0)
is_first = True
for i, row in enumerate(rows):
if not isinstance(row['Date'], datetime.datetime):
continue
if not is_first:
print('-' * 10)
is_first = False
dd = sc.DayData(canton='JU', url=xls_url)
dd.datetime = row['Date'].date().isoformat()
dd.cases = row['Cumul des cas confimés']
dd.hospitalized = row.get('Nb cas actuellement hospitalisés')
dd.icu = row.get('Nb cas actuellement en SI')
if sc.represents_int(row.get('Nombre de nouveaux décès')):
dd.deaths = sum(r['Nombre de nouveaux décès'] for r in rows[:i + 1])
print(dd)
if dd:
if not is_first:
print('-' * 10)
is_first = False
print(dd)
# get cases xls
elem = driver.find_element_by_link_text('Indicateurs principaux')
elem.click()
case_xls_url = sgc.get_link_from_element(driver, 'download_table_indicateurs')
assert case_xls_url, "Couldn't find cases XLS url"
xls = sc.xlsdownload(case_xls_url, silent=True)
rows = sc.parse_xls(xls, header_row=0)
for row in rows:
dd = sc.DayData(canton='GE', url=url)
dd.datetime = row['Date']
dd.cases = row['Cumul cas COVID-19']
current_hosp = row[
'Total hospitalisations COVID-19 actifs (en cours) canton (HUG-cliniques)']
if sc.represents_int(current_hosp) and int(current_hosp) >= 0:
dd.hospitalized = current_hosp
dd.icu = row['Patients COVID-19 actifs aux soins intensifs HUG']
dd.icf = row['Patients COVID-19 actifs aux soins intermédiaires HUG']
dd.deaths = row['Cumul décès COVID-19 ']
if dd:
if not is_first:
print('-' * 10)
is_first = False
print(dd)
print('-' * 10)
is_first = False
print(dd)
# cases + hospitalization
rows = sc.parse_xls(xls, sheet_name='1. Covid-19-Daten', header_row=2)
for row in rows:
if not isinstance(row['A'], datetime.datetime):
continue
dd = sc.DayData(canton='AG', url=xls_url)
dd.datetime = f"{row['A'].date().isoformat()} {row['A'].time().isoformat()}"
dd.cases = row['Gesamtzahl']
non_icu = row['Bestätigte Fälle auf Abteilung (ohne IPS/IMC)']
icu = row['Bestätigte Fälle Intensivpflegestation (IPS)']
icf = row['Bestätigte Fälle Intermediate Care (IMC)']
if sc.represents_int(non_icu) and sc.represents_int(
icu) and sc.represents_int(icf):
dd.hospitalized = int(non_icu) + int(icu) + int(icf)
dd.icu = icu
dd.icf = icf
dd.deaths = row['Gesamtzahl16']
dd.recovered = row['Gesamtzahl20']
if dd:
if not is_first:
print('-' * 10)
is_first = False
print(dd)
t = sc.find(r'Contact\s+tracing\s+\(.*?Stand\:?\s+(.+?Uhr).*?\)', d) or \
sc.find(r'Contact\s+tracing.*Stand\:? (.+? Uhr).*?\)', d) or \
sc.find(r'Contact\s+tracing.*Stand ([0-9]+\.[0-9]+\.? \/ [0-9]+h)', d)
dd_ct.datetime = t
dd_ct.isolated = sc.find(
r'Aktuell\s+COVID-19-Erkrankte\s+in\s+Isolation:\s+<strong>\s?(\d+)\s?</strong>',
d)
quarantined_total = sc.find(
r'Aktuell\s+im\s+Kanton\s+wohnhafte\s+(?:Kontaktpersonen|Personen)\s+in\s+Quarantäne:\s?<strong>\s?(\d+)\s?</strong>',
d)
quarantined_travel = sc.find(
r'davon\s+Anzahl\s+Personen.*die\s+aus\s+einem\s+<strong>Risikogebiet</strong>\s+in\s+die\s+Schweiz\s+eingereist\s+sind\s+und\s+aufgrund\s+dessen\s+aktuell\s+im\s+Kanton\s+in\s+Quarantäne\s+sind:\s+<strong>\s*(\d+)</strong>',
d)
assert sc.represents_int(
quarantined_travel
), f"quarantined_travel is not an integer: {quarantined_travel}"
if sc.represents_int(quarantined_total):
dd_ct.quarantine_total = quarantined_total
quarantined = int(quarantined_total) - int(quarantined_travel)
assert quarantined >= 0, f"Quarantined is negative: {quarantined}"
dd_ct.quarantined = quarantined
dd_ct.quarantine_riskareatravel = quarantined_travel
if dd_ct:
print(dd_ct)
print('-' * 10)
# cases
if not is_first:
print('-' * 10)
is_first = False
print('SH')
sc.timestamp()
print('Downloading:', xls_url)
if isinstance(row['Uhrzeit'], datetime.datetime):
print('Date and time:', row['Datum'].date().isoformat(), row['Uhrzeit'].time().isoformat())
elif row['Uhrzeit']:
print('Date and time:', row['Datum'].strftime('%d.%m.%Y'), row['Uhrzeit'])
else:
print('Date and time:', row['Datum'].date().isoformat())
print('Confirmed cases:', row['Positiv'])
if sc.represents_int(row['Hospitalisation isoliert\nbestätigt']) and sc.represents_int(row['Hospitalisiert_Intensiv']):
print('Hospitalized:', (row.search(r'Hospitalisation isoliert\s+bestätigt.*$') + row['Hospitalisiert_Intensiv']))
print('ICU:', row['Hospitalisiert_Intensiv'])
if row['Verstorben'] is not None:
print('Deaths:', row['Verstorben'])
isolated = row.search(r'Anzahl Personen\s+in Isolation.*')
if isolated is not None:
print('Isolated:', isolated)
quarantined = row.search(r'Anzahl Personen\s+in Quarantäne\s+.*Kontaktpersonen.*')
if quarantined is not None:
print('Quarantined:', quarantined)
quarantined_risk = row.search(r'Anzahl Personen\s+in Quarantäne\s+.*Rückkehr.*Risikoländer.*')
if quarantined_risk is not None:
print('Quarantined risk area travel:', quarantined_risk)
is_first = False
print('SH')
sc.timestamp()
print('Downloading:', main_url)
if isinstance(row['Uhrzeit'], datetime.datetime):
print('Date and time:', row['Datum'].date().isoformat(),
row['Uhrzeit'].time().isoformat())
elif row['Uhrzeit']:
print('Date and time:', row['Datum'].strftime('%d.%m.%Y'),
row['Uhrzeit'])
else:
print('Date and time:', row['Datum'].date().isoformat())
print('Confirmed cases:', row['Positiv'])
if sc.represents_int(row.search(
r'Hospitalisation isoliert\s+bestätigt.*$')) and sc.represents_int(
row.search(r'Hospitalisiert.*Intensiv.*$')):
print('Hospitalized:',
(row.search(r'Hospitalisation isoliert\s+bestätigt.*$') +
row.search(r'Hospitalisiert.*Intensiv.*$')))
print('ICU:', row.search(r'Hospitalisiert.*Intensiv.*$'))
if row['Verstorben'] is not None:
print('Deaths:', row['Verstorben'])
isolated = row.search(r'Anzahl Personen\s+in Isolation.*')
if isolated is not None:
print('Isolated:', isolated)
quarantined = row.search(
r'Anzahl Personen\s+in Quarantäne\s+.*Kontaktpersonen.*')
if quarantined is not None:
print('Quarantined:', quarantined)
xls_url = f"https://sh.ch{meta['url']}"
xls = sc.xlsdownload(xls_url, silent=True)
rows = sc.parse_xls(xls, header_row=0)
is_first = True
for row in rows:
if not isinstance(row['Datum'], datetime.datetime):
continue
if not (row['Positiv'] or row['Hospitalisiert_Iso'] or row['Hospitalisiert_Intensiv'] or row['Verstorben']):
continue
if not is_first:
print('-' * 10)
is_first = False
print('SH')
sc.timestamp()
print('Downloading:', xls_url)
if isinstance(row['Uhrzeit'], datetime.datetime):
print('Date and time:', row['Datum'].date().isoformat(), row['Uhrzeit'].time().isoformat())
elif row['Uhrzeit']:
print('Date and time:', row['Datum'].strftime('%d.%m.%Y'), row['Uhrzeit'])
else:
print('Date and time:', row['Datum'].date().isoformat())
print('Confirmed cases:', row['Positiv'])
if sc.represents_int(row['Hospitalisiert_Iso']) and sc.represents_int(row['Hospitalisiert_Intensiv']):
print('Hospitalized:', (row['Hospitalisiert_Iso'] + row['Hospitalisiert_Intensiv']))
print('ICU:', row['Hospitalisiert_Intensiv'])
print('Deaths:', row['Verstorben'])