def parse_weekly_data(filename):
txt = c.pdf_to_text(filename)
txt = re.sub(r'(\d)\s(\d)', r'\1\2', txt)
year = c.search(r'Stand:\s\d+\.\d+\.(\d{4})', txt)
week = int(c.search(r'Liechtenstein - Woche (\d+) ', txt))
tot_tests = ''
tot_antigen_tests = ''
pcr_pos = txt.find('Gemeldete Tests')
if pcr_pos > 0:
pcr_pos = txt.find('PCR', pcr_pos)
pcr_end_pos = txt.find('\n', pcr_pos)
assert pcr_end_pos > pcr_pos
line = txt[pcr_pos:pcr_end_pos]
#line = re.sub(r'(\d)\s(\d)', r'\1\2', line)
line = re.sub(r'\s+', r' ', line)
tot_tests = c.txt_to_int(line.split(' ')[-2])
# Antigen tests
pcr_pos = txt.find('Antigen-Schnelltests', pcr_pos)
pcr_end_pos = txt.find('\n', pcr_pos)
assert pcr_end_pos > pcr_pos
line = txt[pcr_pos:pcr_end_pos]
line = re.sub(r'\s+', r' ', line)
tot_antigen_tests = c.txt_to_int(line.split(' ')[-2])
positivity_rate = ''
antigen_positivity_rate = ''
positivity_pos = txt.find('\nPositivit')
if positivity_pos == -1:
positivity_pos = txt.find('\nAnteil positiver Tests')
if positivity_pos > 0:
positivity_pos = txt.find('PCR', positivity_pos)
positivity_end_pos = txt.find('\n', positivity_pos)
assert positivity_end_pos > positivity_pos
line = txt[positivity_pos:positivity_end_pos]
line = re.sub(r'\s+', r' ', line)
positivity_rate = line.split(' ')[-1]
positivity_rate = c.txt_to_float(positivity_rate.replace('%', ''))
# Antigen tests
positivity_pos = txt.find('Antigen-Schnelltest', positivity_pos)
positivity_end_pos = txt.find('\n', positivity_pos)
assert positivity_end_pos > positivity_pos
line = txt[positivity_pos:positivity_end_pos]
line = re.sub(r'\s+', r' ', line)
antigen_positivity_rate = line.split(' ')[-1]
try:
antigen_positivity_rate = c.txt_to_float(
positivity_rate.replace('%', ''))
except:
pass
print(
f'{year},{week},{tot_tests},{positivity_rate},{tot_antigen_tests},{antigen_positivity_rate},{filename}'
)
def parse_data(filename):
txt = c.pdf_to_text(filename)
date_time = c.search(r'Stand (\d.*) Uhr', txt)
if date_time is None:
date = c.search(r'Stand\: (\d{2}\.\d{2}\.20\d{2})', txt)
time = c.search(r'Zeit: (\d+:\d{2})', txt)
if date is not None and time is not None:
date_time = '{} {}'.format(date, time)
date = c.parse_date(date_time)
tot_tests = parse_pcr_tot_tests(txt)
positivity_rate = c.txt_to_float(
c.search(r'Bei (\d+)% dieser Tests fiel das Resultat positiv aus',
txt))
if positivity_rate is None:
positivity_rate = c.txt_to_float(
c.search(r'Positivit.tsrate( \*+| \(%\)|\*+)?\s+(\d\.?\d?)[%\s]',
txt,
index=2))
if positivity_rate is None:
positivity_rate = c.txt_to_float(
c.search(r'Anteil positive Tests \(%\)(\d)?\s+(\d\.?\d?)[%\s]',
txt,
index=2))
isolated = c.txt_to_int(
c.search(
r'(\d+)\s+(F.lle|Personen aufgrund einer laborbest.tigten COVID-19 Erkrankung)? in\sIsolation',
txt,
index=1))
quarantined = c.txt_to_int(
c.search(
r'(\d+)\s?(in|Kontaktpersonen\sin\s.rztlich\sverordneter)? Quarant.ne',
txt))
quarantined_travel = None
if isolated is None or quarantined is None:
pos = txt.find('Contact Tracing')
if pos > 0:
pcr = re.compile(
r'Total\s?(\*+|\(%\))?\s+(\d+\s?\d+|\d+)\s+(\d+\s?\d+|\d+)\s+(\d+ ?\d+|\d+)?\n'
)
#pcr = re.compile(r'Total\s?(\*+|\(%\))?\s+(\d+)\s+(\d+)\s+(\d+|\d+\s?\d+)?')
res = pcr.search(txt, pos)
if res is not None:
isolated = c.txt_to_int(res[2])
quarantined = c.txt_to_int(res[3])
quarantined_travel = c.txt_to_int(res[4].strip())
print('{},{},{},{},{},{},{}'.format(date, tot_tests or '', positivity_rate
or '', isolated or '', quarantined
or '', quarantined_travel or '',
filename))
def parse_weekly_data(filename):
txt = c.pdf_to_text(filename)
week = c.search(r'Liechtenstein - Woche (\d+) ', txt)
tot_tests = None
pcr_pos = txt.find('PCR-Tests')
if pcr_pos > 0:
pcr_pos = txt.find('\n', pcr_pos) + 1
pcr_end_pos = txt.find('\n', pcr_pos)
assert pcr_end_pos > pcr_pos
line = txt[pcr_pos:pcr_end_pos]
line = re.sub(r'(\d)\s(\d)', r'\1\2', line)
line = re.sub(r'\s+', r' ', line)
tot_tests = c.txt_to_int(line.split(' ')[-2])
positivity_rate = None
positivity_pos = txt.find('\nPositivit')
if positivity_pos == -1:
positivity_pos = txt.find('\nAnteil positive Tests')
if positivity_pos > 0:
positivity_pos += 1
positivity_end_pos = txt.find('\n', positivity_pos)
assert positivity_end_pos > positivity_pos
line = txt[positivity_pos:positivity_end_pos]
line = re.sub(r'\s+', r' ', line)
positivity_rate = line.split(' ')[-1]
positivity_rate = c.txt_to_float(positivity_rate.replace('%', ''))
print('{},{},{},{}'.format(week, tot_tests or '', positivity_rate or '',
filename))
def parse_canton_data(canton, filename):
txt = c.pdf_to_text(filename)
# pylint: disable=W0105
"""
Coronavirus-Krankheit-2019 (COVID-19)
Eidgen<C3><B6>ssisches Departement des Innern EDI
Bundesamt f<C3><BC>r Gesundheit BAG
Direktionsbereich <C3><96>ffentliche Gesundheit
Situationsbericht zur epidemiologischen Lage in der Schweiz
und im F<C3><BC>rstentum Liechtenstein - Woche 28 (06.-12.07.2020)
"""
year = c.search(r'Stand:\s\d+\.\d+\.(\d{4})', txt)
week = int(c.search(r'Liechtenstein - Woche (\d+)', txt))
"""
Canton, tests of previous-week then current-week
AG 5478 3588 808 529 1.3 1.8
AI 96 55 595 341 0.0 0.0
AR 391 249 708 451 0.5 1.2
BE 6924 4652 669 449 0.4 0.9
...
"""
start = txt.find('Anzahl PCR-Tests in der Schweiz')
if start == -1:
start = txt.find('Anzahl durchgeführte PCR-Tests in der Schweiz')
if start == -1:
start = txt.find('Anzahl durchgeführte Tests in der Schweiz')
if start == -1:
start = txt.find('Anzahl gemeldeter Tests, Anzahl Tests pro')
if start > 0:
start = txt.find(r' AG ', start)
else:
start = 0
end = txt.find('Tabelle 4. Durchgeführte Tests nach Kalenderwoche', start)
if end == -1:
end = txt.find('Die Altersverteilung der', start)
if end == -1:
end = txt.find('Die Anzahl durchgeführter Tests', start)
if end >= 0:
end -= 1
if end == -1:
end = txt.find('Gemeldete Tests nach Alter und Geschlecht', start)
if end > start > 0 and end > start:
tests_table = txt[start:end]
# the numbers are sometimes separated with spaces for >1k values
pcr = re.compile(r'(\d+)\s(\d+)')
tests_table = pcr.sub(r'\1\2', tests_table)
number_of_tests = c.txt_to_int(c.search(r'(\n\s+)?{}\s+\d+\s+(\d+)'.format(canton), tests_table, index=2))
positivity_rate = c.txt_to_float(c.search(r'(\n\s+)?{}\s+.*\s([0-9]+\.[0-9]+)\n'.format(canton), tests_table, index=2))
print(f'{year},{week},{number_of_tests},{positivity_rate},{filename}')
def parse_pcr_tot_tests(txt):
tot_tests = c.txt_to_int(
c.search(r'insgesamt auf( .ber| rund| mehr als)? ([\d\s.]+)\.',
txt,
index=2))
pcr_pos = txt.find('Tests')
if tot_tests is None and pcr_pos > 0:
# extract the line with Total / Totale Anzahl
pcr_pos = txt.find('\n', pcr_pos) + 1
pcr_end_pos = txt.find('\n', pcr_pos)
line = txt[pcr_pos:pcr_end_pos]
# replace whitespace between numbers '937 488' -> '937488'
line = re.sub(r'(\d)\s(\d)', r'\1\2', line)
# match the value
pcr = re.compile(r'(Totale Anzahl|Total)\s+\+?(\d+)\s')
res = pcr.match(line)
if res is not None:
tot_tests = c.txt_to_int(res[2])
return tot_tests
res = re.search(r'Total durchgef.hrte Tests\s+(\d+)\s+\+?\d+\s', line)
if res is not None:
tot_tests = c.txt_to_int(res[1])
return tot_tests