test_9

55d95f40-a71c-46ab-9619-9a632c530e4f.py

# name the urls
NRS_ROOT = 'https://www.nrscotland.gov.uk'
NRS_DEATH_STRING = 'statistics/covid19/covid-deaths-21'
# request website, parse and identify from the html only the url link elements
req = Request(NRS_ROOT+'/covid19stats', headers=hdr)
html_page = urlopen(req)
soup = BeautifulSoup(html_page, "lxml")
links = []
for link in soup.findAll('a'):
    l = link.get('href')
    if l != None:
        links.append(l)

NRS_COD_ZIP = NRS_ROOT + [x for x in links if NRS_DEATH_STRING in x and '.zip' in x][0]
print("Scottish COD data at: {}".format(NRS_COD_ZIP))

# request the zip file and display the contents
r = requests.get(NRS_COD_ZIP)
zips = zipfile.ZipFile(io.BytesIO(r.content))
print("Files contained within the zip:")
zips.namelist()[:5]