Scrape Data from PDF Documents

scrape.py

tables = tabula.read_pdf('https://www.who.int/docs/default-source/coronaviruse/situation-reports/20200715-covid-19-sitrep-177.pdf', pages="all", multiple_tables=True)
countries = []
for data_frame in tables:
    data_dicts = data_frame.T.to_dict().values()
    for data_item in data_dicts:
        for key in data_item:
            if 'Country' in key:  # if key is 'Reporting Country/Territory/Area'
                country = find(who_name=data_item[key])  # if Country Exists in the List
                if country:
                    confirmed = data_item.get('Total confirmed', None)
                    confirmed_new = data_item.get('Total confirmed.1', None)
                    deaths = data_item.get('Total deaths', None)
                    deaths_new = data_item.get('Total new deaths', None)

                    if isinstance(confirmed, str):
                        confirmed = confirmed.replace(' ', '')
                        confirmed = decimal.Decimal(confirmed)

                    if isinstance(confirmed_new, str):
                        confirmed_new = confirmed_new.replace(' ', '')
                        confirmed_new = decimal.Decimal(confirmed_new)

                    if isinstance(deaths, str):
                        deaths = deaths.replace(' ', '')
                        deaths = decimal.Decimal(deaths)

                    if isinstance(deaths_new, str):
                        deaths_new = deaths_new.replace(' ', '')
                        deaths_new = decimal.Decimal(deaths_new)

                    country['confirmed'] = replace_nam(confirmed)
                    country['confirmed_new'] = replace_nam(confirmed_new)
                    country['deaths'] = replace_nam(deaths)
                    country['deaths_new'] = replace_nam(deaths_new)
                    country['date'] = date

                    countries.append(country)

return countries