#!/usr/bin/env python3 # -*- coding: utf-8 -*- import scrape_common as sc from scrape_fr_common import get_fr_xls xls_url, xls = get_fr_xls() rows = sc.parse_xls(xls, header_row=0, sheet_name='tests COVID19', enable_float=True) for row in rows: td = sc.TestData(canton='FR', url=xls_url) td.week = sc.find(r'S (\d+)', row['Semaine']) td.year = '2020' tot = int(row['Total Testing Pop FR']) pos = int(row['Total POS Pop FR']) td.positive_tests = pos td.total_tests = tot print(td)
for i in range(len(weeks)): district = tds[0].string if district in inhabitants: dd = sc.DistrictData(canton='FR', district=district) dd.url = url dd.week = weeks[i] # TODO restore once all weeks are in 2021 # dd.year = '20' + year dd.year = years[i] dd.new_cases = tds[i + 1].string dd.population = inhabitants[district] dd.district_id = district_ids[district] print(dd) # daily data from xls xls_url, xls, main_url = get_fr_xls() rows = sc.parse_xls(xls, header_row=0) for row in rows: row_date = row.search(r'.*Date.*') for district, d_id in district_ids.items(): district_cell = row.search(r'.*' + district + '.*') dd = sc.DistrictData(canton='FR', district=district) dd.url = url dd.date = row_date.date().isoformat() dd.new_cases = district_cell dd.population = inhabitants[district] dd.district_id = d_id print(dd)