def process_data_for_myanmar(self):
try:
a = WikipediaService(url="https://en.wikipedia.org/wiki/2020_coronavirus_pandemic_in_Myanmar")
country = "Myanmar"
table_text = "Confirmed COVID-19 cases by Township"
start_row = "3"
table = a.search_table(table_text, index=1)
if start_row.isnumeric():
table = table[int(start_row) - 1:]
res = []
for row in table:
region = self.get_city_name(row[1], row[2])
if 'Total' in region:
continue
infected = row[3]
deaths = row[-1]
d = dict(
region=region,
infected=sanitize_digit(infected),
deaths=sanitize_digit(deaths),
recoveries="0",
)
res.append(d)
file_name = self.get_output_file(country)
cleanup(file_name)
self.write_output_for_country(res, country=country, file_name=file_name)
move_to_final(file_name)
except Exception as e:
print(f"Exception fetching myanmar data: {e}")
def get_active_for_row(self, row):
active = row.get("active", "")
if active:
return sanitize_digit(active)
else:
infected = int(sanitize_digit(row.get("infected", "")))
deaths = int(sanitize_digit(row.get("deaths", "")))
recoveries = int(sanitize_digit(row.get("recoveries", "")))
if deaths > infected or recoveries > infected:
print(row)
active = infected - deaths - recoveries
return str(active)
def process_country_table(self, table, country, start_row, end_row,
region_col, total_col, death_col, recovered_col,
active_col):
if start_row.isnumeric():
table = table[int(start_row) - 1:]
if end_row.lstrip('-+').isnumeric():
table = table[:int(end_row)]
result = []
for row in table:
region = row[int(region_col) - 1]
total = deceased = recovered = active = "0"
if total_col.isnumeric():
total = row[int(total_col) - 1]
total = total if total.strip() else "0"
if active_col.isnumeric():
active = row[int(active_col) - 1]
active = active if active.strip() else "0"
if death_col.isnumeric():
deceased = row[int(death_col) - 1]
deceased = deceased if deceased.strip() else "0"
if recovered_col.isnumeric():
recovered = row[int(recovered_col) - 1]
recovered = recovered if recovered.strip() else "0"
else:
try:
recovered = str(
int(sanitize_digit(total)) -
int(sanitize_digit(deceased)) -
int(sanitize_digit(active)))
except Exception:
print(region, total, deceased, active)
d = dict(
country=country,
region=region,
infected=total,
deaths=deceased,
recoveries=recovered,
active=active,
last_updated=self.last_updated.strftime("%Y-%m-%d %H:%M:%S"))
result.append(d)
return result
def get_features_for_row(self,
country,
region,
infected,
deaths,
recoveries,
long,
lat,
last_updated,
active="",
total_per_mil="",
deaths_per_mil="",
total_tests=""):
if active:
current = str(active)
else:
try:
current = int(infected) - int(deaths) - int(recoveries)
current = str(current)
except Exception as e:
current = ""
if lat == "" or long == "":
lat, long = self.get_lat_long(country, region)
if not lat:
return
point = Point((float(long), float(lat)))
data_type = "Regional" if region else "National"
feature = Feature(geometry=point,
properties={
"Data Type": data_type,
"Country": sanitize_text(country),
"City": sanitize_text(region),
"Current Cases": sanitize_digit(current),
"Total Cases": sanitize_digit(infected),
"Deceased": sanitize_digit(deaths),
"Recovered": sanitize_digit(recoveries),
"Total Cases/1M pop":
sanitize_digit(total_per_mil),
"Deaths/1M pop": sanitize_digit(deaths_per_mil),
"Total Tests": sanitize_digit(total_tests),
"Last Updated": last_updated
})
return feature
def write_output_for_country(self, output, country=None, file_name=None):
if file_name is None:
file_name = self.get_output_file("default")
for row in output:
if country is None:
country_str = row.get("country", "")
else:
country_str = country
region = sanitize_text(row.get("region", ""))
lat, long = self.geojson_service.get_lat_long(country_str, region)
record = dict(country=sanitize_text(country_str),
region=region,
infected=sanitize_digit(row.get("infected", "")),
deaths=sanitize_digit(row.get("deaths", "")),
recoveries=sanitize_digit(row.get("recoveries", "")),
long=long,
lat=lat,
last_updated=self.last_updated.strftime("%Y-%m-%d %H:%M:%S"))
if country is None:
record["active"] = sanitize_digit(row.get("active", ""))
record["total_per_mil"] = sanitize_digit(row.get("total_per_mil", ""))
record["deaths_per_mil"] = sanitize_digit(row.get("deaths_per_mil", ""))
record["total_tests"] = sanitize_digit(row.get("total_tests", ""))
record["active_per_mil"] = sanitize_digit(row.get("active_per_mil", ""))
record["recovered_per_mil"] = sanitize_digit(row.get("recovered_per_mil", ""))
record["tests_per_mil"] = sanitize_digit(row.get("tests_per_mil", ""))
record["new_cases"] = sanitize_digit(row.get("new_cases", ""))
record["new_deaths"] = sanitize_digit(row.get("new_deaths", ""))
write_record_to_output(record, file_name)
def process_table(self, table, start_row, end_row, country_col, total_col,
death_col, recovered_col, active_col, total_per_mil_col,
deaths_per_mil_col, total_tests_col, new_cases_col,
new_deaths_col, population_col):
if start_row.isnumeric():
table = table[int(start_row) - 1:]
if end_row.lstrip('-+').isnumeric():
table = table[:int(end_row)]
result = []
region = ""
for row in table:
try:
country = row[int(country_col) - 1]
total = deceased = recovered = active = total_per_mil = total_tests = deaths_per_mil = "0"
active_per_mil = recovered_per_mil = tests_per_mil = new_cases = new_deaths = pop = "0"
if total_col.isnumeric():
total = row[int(total_col) - 1]
total = total if total.strip() else "0"
if active_col.isnumeric():
active = row[int(active_col) - 1]
active = active if active.strip() else "0"
if deaths_per_mil_col.isnumeric():
deaths_per_mil = row[int(deaths_per_mil_col) - 1]
deaths_per_mil = deaths_per_mil if deaths_per_mil.strip(
) else "0"
if total_per_mil_col.isnumeric():
total_per_mil = row[int(total_per_mil_col) - 1]
total_per_mil = total_per_mil if total_per_mil.strip(
) else "0"
if total_tests_col.isnumeric():
total_tests = row[int(total_tests_col) - 1]
total_tests = total_tests if total_tests.strip() else "0"
if death_col.isnumeric():
deceased = row[int(death_col) - 1]
deceased = deceased if deceased.strip() else "0"
if recovered_col.isnumeric():
recovered = row[int(recovered_col) - 1]
recovered = recovered if recovered.strip() else "0"
if population_col.isnumeric():
pop = row[int(population_col) - 1]
pop = pop if pop.strip() else "0"
if pop != "0":
population_per_mil = int(sanitize_digit(pop)) / 1000000
if population_per_mil > 0:
active_per_mil = int(
int(sanitize_digit(active)) / population_per_mil)
recovered_per_mil = int(
int(sanitize_digit(recovered)) /
population_per_mil)
tests_per_mil = int(
int(sanitize_digit(total_tests)) /
population_per_mil)
if new_cases_col.isnumeric():
new_cases = row[int(new_cases_col) - 1]
new_cases = sanitize_digit(
new_cases) if new_cases.strip() else "0"
if new_deaths_col.isnumeric():
new_deaths = row[int(new_deaths_col) - 1]
new_deaths = sanitize_digit(
new_deaths) if new_deaths.strip() else "0"
d = dict(country=country,
region=region,
infected=total,
deaths=deceased,
recoveries=recovered,
active=active,
total_per_mil=total_per_mil,
deaths_per_mil=deaths_per_mil,
total_tests=total_tests,
active_per_mil=active_per_mil,
recovered_per_mil=recovered_per_mil,
tests_per_mil=tests_per_mil,
new_cases=new_cases,
new_deaths=new_deaths,
pop=pop,
last_updated=self.last_updated.strftime(
"%Y-%m-%d %H:%M:%S"))
result.append(d)
except Exception as e:
print(row, e)
return result