#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import re
import scrape_common as sc
import scrape_ge_common as sgc
pdf_urls = sgc.get_ge_weekly_pdf_urls()
for pdf_url in pdf_urls:
pdf = sc.download_content(pdf_url, silent=True)
content = sc.pdftotext(pdf, page=1)
week_number = sc.find(r'Situation semaine (\d+)', content)
year = sc.find(r'au \d+(\w+)? \w+ (\d{4})', content, group=2)
pages = int(sc.pdfinfo(pdf))
for page in range(3, pages):
content = sc.pdftotext(pdf, page=page)
# remove ' separator to simplify pattern matching
content = re.sub(r'(\d)\'(\d)', r'\1\2', content)
if sc.find(r'(Dynamique et tendances épidémiologiques)', content):
weekly_tests = sc.find(
r'avec\s(\d+)\stests\s(effectués\s?)?(contre|\.)', content)
res = re.match(
r'.*taux\sde\spositivité.*\s\(?(\d+\.?\d?)%\)?\s(en|durant).*\d+\.?\d?%',
content, re.MULTILINE | re.DOTALL)
positivity_rate = None
if res:
positivity_rate = res[1]
return arrow.get(date_str, 'DD.MM.YYYY', locale='de').datetime.date()
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)
#!/usr/bin/env python
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: