who.py

import os
import re
    
from bs4 import BeautifulSoup
from urllib.request import urlopen
     
    
url = "https://www.who.int/emergencies/diseases/novel-coronavirus-2019/situation-reports"
    
soup = BeautifulSoup(urlopen(url), features="html.parser")
div = soup.findAll("div", {"id": "PageContent_C006_Col01"})
reports = div[0].findAll("a")
     
urlhead = "https://www.who.int"
     
for pdf in reports:
    urltail = pdf["href"]
    full_url = urlhead + urltail
    matched = re.search("2020.*pdf", urltail )
    try: 
        filename = matched.group()
        print(filename)
        command = 'wget -O pdf/{} {}'.format(filename, full_url)
        # print(command)
        os.system(command)
    except:
        print("nono")