#!/usr/bin/env python3
import re
import arrow
from bs4 import BeautifulSoup
import scrape_common as sc
def parse_gr_date(date_str):
return arrow.get(date_str, 'DD.MM.YYYY', locale='de').datetime.date()
url = 'https://www.gr.ch/DE/institutionen/verwaltung/djsg/ga/coronavirus/info/impfen/Seiten/impfen.aspx'
hist_url = 'https://www.gr.ch/DE/institutionen/verwaltung/djsg/ga/coronavirus/_layouts/15/GenericDataFeed/feed.aspx?PageID=30&ID=g_dbea8372_ed27_48e8_b2c8_b1f7a9643675&FORMAT=JSONRAW'
d = sc.download_json(hist_url)
for data in d:
vd = sc.VaccinationData(canton='GR', url=url)
vd.date = parse_gr_date(data['Stand'])
vd.first_doses = int(data['verimpft1'])
vd.second_doses = int(data['verimpft2'])
vd.total_vaccinations = vd.first_doses + vd.second_doses
print(vd)
base_url = 'https://www.jura.ch'
url = f'{base_url}/fr/Autorites/Coronavirus/Infos-Actualite/Statistiques-COVID/Evolution-des-cas-COVID-19-dans-le-Jura.html'
d = sc.download(url)
d = d.replace(' ', ' ')
soup = BeautifulSoup(d, 'html.parser')
pdf_url = soup.find('a', title=re.compile(r'Donn.es de vaccination')).get('href')
if not pdf_url.startswith('http'):
pdf_url = f'{base_url}{pdf_url}'
pdf_url = pdf_url.replace('?download=1', '')
pdf = sc.download_data(pdf_url)
pages = sc.pdfinfo(pdf)
vd = sc.VaccinationData(canton='JU', url=pdf_url)
content = sc.pdf_to_text(pdf, page=1, raw=True)
content = re.sub(r'(\d+)\'(\d+)', r'\1\2', content)
res = re.search(r'\d+\.\d+\.\d{4}\s(\d+\.\d+\.\d{4})', content)
assert res
vd.date = parse_ju_date(res[1])
res = re.search(r'(\d+)\s+Nombre d\'injection', content)
assert res
vd.total_vaccinations = res[1]
content = sc.pdf_to_text(pdf, page=2, raw=True)
content = re.sub(r'(\d+)\'(\d+)', r'\1\2', content)
csv_url = 'https://www.zg.ch/behoerden/gesundheitsdirektion/statistikfachstelle/daten/themen/result-themen-14-03-12.csv'
d_csv = sc.download(csv_url)
"""
"Datum","Typ","Anzahl","Meta","Type","Content"
"23.12.2020","Total verimpfte Dosen","250",NA,NA,NA
"24.12.2020","Total verimpfte Dosen","250",NA,NA,NA
"""
reader = csv.DictReader(StringIO(d_csv), delimiter=',')
data = collections.defaultdict(dict)
for row in reader:
if row['Datum'] == 'NA':
continue
date = parse_zg_date(row['Datum'])
if date not in data:
vd = sc.VaccinationData(canton='ZG', url=csv_url)
vd.date = date.isoformat()
data[date] = vd
if row['Typ'] == 'Total verimpfte Dosen':
data[date].total_vaccinations = row['Anzahl']
elif row['Typ'] == 'Total 1. Impfung':
data[date].first_doses = row['Anzahl']
elif row['Typ'] == 'Total 2. Impfung':
data[date].second_doses = row['Anzahl']
dates = list(data.keys())
for date in dates:
print(data[date])
def get_value(row, key):
value = row[key]
if value != '':
return int(value)
return None
url = 'https://statistik.tg.ch/public/upload/assets/94501/COVID19_Fallzahlen_Kanton_TG.csv'
d_csv = sc.download(url)
reader = csv.DictReader(StringIO(d_csv), delimiter=';')
total_doses_delivered = 0
for row in reader:
if not row['date']:
continue
vd = sc.VaccinationData(canton='TG', url=row['source'])
date = row['date']
date = parse_tg_date(date)
vd.date = date.isoformat()
vd.total_vaccinations = get_value(row, 'total_vaccinations')
doses_delivered = get_value(row, 'doses_delivered')
if doses_delivered:
total_doses_delivered += doses_delivered
vd.doses_delivered = total_doses_delivered
vd.first_doses = get_value(row, 'first_doses')
vd.second_doses = get_value(row, 'second_doses')
if vd:
print(vd)
url = f'{base_url}{url}'
pdf_urls.append(url)
for pdf_url in pdf_urls:
pdf = sc.download_data(pdf_url)
content = sc.pdf_to_text(pdf, layout=True, page=1)
res = re.search(r'(\d{2}/\d{2}/20\d{2})', content)
assert res
date = res[1]
date = parse_vs_date_daily(date)
if date.year == 2020:
# no data available in 2020
break
vd = sc.VaccinationData(canton='VS', url=pdf_url)
vd.date = date.isoformat()
res = re.search(r'.*Anzahl\s+der\s+\w+\s+Impfdosen.*\s+(\d+.\d+)\s+',
content)
if not res:
# no data available in oder PDFs
# (latest are processed first)
break
vd.total_vaccinations = re.sub(r'[^0-9]', '', res[1])
if vd:
print(vd)
url = f'{base_url}/web/coronavirus/statistiques-hebdomadaires'
content = sc.download(url)
soup = BeautifulSoup(content, 'html.parser')
return 0
soup = BeautifulSoup(main_site, 'html.parser')
for iframe in soup.find_all('iframe'):
iframe_url = (iframe['src'])
if iframe_url.find('/dbw/264') <= 0:
continue
d = sc.download(iframe_url)
d = d.replace('\n', ' ')
res = re.search(
r'<pre id="data_1".*?> ?Datum,"Pfizer/BioNTech \(1. Dosis\)","Pfizer/BioNTech \(2. Dosis\)","Moderna \(1. Dosis\)","Moderna \(2. Dosis\)"\s*([^<]+)</pre>',
d)
assert res
data = res[1]
if data:
for row in data.split(" "):
c = row.split(',')
assert len(c) == 5, f"Number of fields changed, {len(c)} != 5"
vd = sc.VaccinationData('BL', url=main_url)
vd.date = parse_row_date(c[0])
vd.first_doses = to_int(c[1]) + to_int(c[3])
vd.second_doses = to_int(c[2]) + to_int(c[4])
vd.total_vaccinations = vd.first_doses + vd.second_doses
print(vd)
break
#!/usr/bin/env python3
import datetime
import tempfile
import openpyxl
import scrape_common as sc
url = 'https://www.llv.li/inhalt/118804/amtsstellen/sonderseite-covid-19'
xls_url = 'https://www.llv.li/files/as/impfungen.xlsx'
xls_data = sc.download_data(xls_url)
fp = tempfile.NamedTemporaryFile(suffix='.xlsx')
fp.write(xls_data)
book = openpyxl.load_workbook(fp.name)
sheet = book['Impfungen']
for i in range(2, sheet.max_column):
vd = sc.VaccinationData(canton='FL', url=xls_url)
date = sheet.cell(4, i)
if date.value is None:
continue
vd.date = date.value.date().isoformat()
vd.doses_delivered = int(sheet.cell(5, i).value)
vd.total_vaccinations = int(sheet.cell(6, i).value)
vd.second_doses = int(sheet.cell(7, i).value)
vd.first_doses = vd.total_vaccinations - vd.second_doses
assert vd
print(vd)
fp.write(xls_data)
book = openpyxl.load_workbook(fp.name)
sheet = book['Tabelle1']
start_row = 2
date_column = 1
first_dose_column = 12
second_dose_column = 13
for row in range(start_row, sheet.max_row):
value = sheet.cell(row, first_dose_column).value
if value is None or value == '':
continue
try:
vd = sc.VaccinationData(canton='SH', url=main_url)
date = sheet.cell(row, date_column)
vd.date = date.value.date().isoformat()
vd.first_doses = int(sheet.cell(row, first_dose_column).value)
vd.second_doses = int(sheet.cell(row, second_dose_column).value)
vd.total_vaccinations = vd.first_doses + vd.second_doses
assert vd
print(vd)
except:
# TODO?
pass
