здесь, как сделать цикл для получения URL отчета
import requests
root_url = 'https://www.iea.org'
def getLinks(url):
all_links = []
page = requests.get(url)
soup = BeautifulSoup(page.text, 'html.parser')
for href in soup.find_all(class_='omrlist'):
all_links.append(root_url + href.find('a').get('href')) # add prefix 'http://....'
return all_links
yearLinks = getLinks(root_url + '/oilmarketreport/reports/')
# get report URL
reportLinks = []
for url in yearLinks:
links = getLinks(url)
reportLinks.extend(links)
print(reportLinks)
for url in reportLinks:
if '.pdf' in url:
url = url.replace('../../..', '')
# do download pdf file
....
else:
# do extract pdf url from html and download it
....
....
теперь вы можете зациклить reportLinks
, чтобы получить pdf url