def get_vs_weekly_general_data(pdf):
content = sc.pdftotext(pdf, page=1)
week = sc.find(r'Epidemiologische Situation Woche (\d+)', content)
end_date = sc.find(r'(\d+\.\d+\.\d{4})', content)
end_date = sc.date_from_text(end_date)
start_date = end_date - datetime.timedelta(days=7)
year = start_date.year
return week, year
from io import StringIO
import scrape_common as sc
import scrape_gl_common as sgc
def split_whitespace(text):
if not text:
return []
text = re.sub(r'\s\s+', ' ', text)
return text.split(' ')
# weekly pdf
pdf_url = sgc.get_gl_pdf_url()
pdf = sc.download_content(pdf_url, silent=True)
content = sc.pdftotext(pdf, page=1)
pdf_date = sc.find(r'Stand: (\d{2}\.\d{2}.\d{4})', content)
pdf_date = sc.date_from_text(pdf_date)
number_of_tests = sc.find(r'PCR-Tests\sKanton Glarus\s(\d+\'?\d+)\s',
content).replace('\'', '')
is_first = True
if number_of_tests:
dd = sc.DayData(canton='GL', url=pdf_url)
dd.datetime = pdf_date
dd.tested = number_of_tests
is_first = False
print(dd)
content = sc.pdftotext(pdf, page=2, raw=True)
dates = split_whitespace(
base_url = 'https://www.jura.ch'
url = f'{base_url}/fr/Autorites/Coronavirus/Chiffres-H-JU/Evolution-des-cas-COVID-19-dans-le-Jura.html'
d = sc.download(url, silent=True)
d = d.replace(' ', ' ')
soup = BeautifulSoup(d, 'html.parser')
pdf_url = soup.find('a', title=re.compile(r'.*PDF.*')).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_content(pdf_url, silent=True)
td = sc.TestData(canton='JU', url=pdf_url)
content = sc.pdftotext(pdf, page=1)
td.week = sc.find(r'Situation semaine épidémiologique (\d+)', content)
td.year = sc.find(r'Du \d+.* (\d{4})', content)
content = sc.pdftotext(pdf, page=2)
td.total_tests = sc.find(r'Nombre de tests\d?\s+(\d+)', content)
res = re.match(
r'.*Nombre de tests positifs .*\s+(\d+)\s+\((\d+\.?\d?)%\s?\d?\)', content,
re.DOTALL | re.MULTILINE)
assert res, 'failed to find number of positive tests and positivity rate'
td.positive_tests = res[1]
td.positivity_rate = res[2]
print(td)
def get_vs_weekly_general_data(pdf):
content = sc.pdftotext(pdf, page=1)
week = sc.find(r'Epidemiologische Situation Woche (\d+)', content)
year = sc.find(r'\d+\.\d+\.(\d{4})', content)
return week, year
from io import StringIO
import scrape_common as sc
import scrape_gl_common as sgc
def split_whitespace(text):
if not text:
return []
text = re.sub(r'\s\s+', ' ', text)
return text.split(' ')
# weekly pdf
pdf_url = sgc.get_gl_pdf_url()
pdf = sc.download_content(pdf_url, silent=True)
content = sc.pdftotext(pdf, page=1)
pdf_date = sc.find(r'Stand: (\d{2}\.\d{2}.\d{4})', content)
pdf_date = sc.date_from_text(pdf_date)
number_of_tests = sc.find(r'PCR-Tests\sKanton Glarus\s(\d+\'?\d+)\s',
content).replace('\'', '')
is_first = True
if number_of_tests:
dd = sc.DayData(canton='GL', url=pdf_url)
dd.datetime = pdf_date
dd.tested = number_of_tests
is_first = False
print(dd)
content = sc.pdftotext(pdf, page=2, layout=True)
dates = split_whitespace(
import re
import scrape_common as sc
import scrape_vs_common as svc
# get the latest weekly PDF
url = svc.get_vs_latest_weekly_pdf_url()
# fetch the PDF
pdf = sc.download_content(url, silent=True)
week, year = svc.get_vs_weekly_general_data(pdf)
# second last page contains the district data
page = int(sc.pdfinfo(pdf)) - 2
content = sc.pdftotext(pdf, page=page, layout=True, rect=[0, 403, 420, 50], fixed=2)
# strip everything including the "Anzahl Faelle" column + values
def strip_left_number(content):
lines = content.split('\n')
pos = None
for line in lines:
res = re.search(r'\s+(\d+) ', line)
if res is not None:
if pos is None:
pos = res.end()
else:
pos = min(pos, res.end())
new_content = []
for line in lines:
new_content.append(line[pos:])
import re
import scrape_common as sc
import scrape_vs_common as svc
# get all PDFs
for url in svc.get_vs_weekly_pdf_urls():
td = sc.TestData(canton='VS', url=url)
pdf = sc.download_content(url, silent=True)
td.week, td.year = svc.get_vs_weekly_general_data(pdf)
for page in range(4, 6):
content = sc.pdftotext(pdf, page=page, raw=True)
content = re.sub(r'(\d)\‘(\d)', r'\1\2', content)
content = re.sub(r'(\d)\’(\d)', r'\1\2', content)
td.total_tests = sc.find(r'Alle\s+Arten\s+von\s+Tests\s+(\d+)', content)
td.positivity_rate = sc.find(r'Alle\s+Arten\s+von\s+Tests\s+\d+\s+(\d+\.\d+)%', content)
td.pcr_total_tests = sc.find(r'PCR\s+(\d+)', content)
td.pcr_positivity_rate = sc.find(r'PCR\s+\d+\s+(\d+\.\d+)%', content)
td.ag_total_tests = sc.find(r'Antigentests\s+(\d+)', content)
td.ag_positivity_rate = sc.find(r'Antigentests\s+\d+\s+(\d+\.\d+)%', content)
if not td.total_tests:
continue
print(td)
