Extract all image links from wikiΒΆ
Extract and display all the image links from en.wikipedia.org/wiki/peter_jeffrey_(raaf_officer).
from urllib.request import urlopen
from bs4 import BeautifulSoup
import re
html = urlopen('https://en.wikipedia.org/wiki/Peter_Jeffrey_(RAAF_officer)')
bs = BeautifulSoup(html, 'html.parser')
images = bs.find_all('img', {'src':re.compile('.jpg')})
for image in images:
print(image['src']+'\n')
Output:
//upload.wikimedia.org/wikipedia/commons/thumb/a/af/NlaJeffrey1942-43.jpg/220px-NlaJeffrey1942-43.jpg
//upload.wikimedia.org/wikipedia/commons/thumb/c/c5/008315JeffreyTurnbull1941.jpg/260px-008315JeffreyTurnbull1941.jpg
//upload.wikimedia.org/wikipedia/commons/e/ea/021807CameronJeffrey1941.jpg
//upload.wikimedia.org/wikipedia/commons/thumb/9/92/AC0072JeffreyTruscottKittyhawks1942.jpg/280px-AC0072JeffreyTruscottKittyhawks1942.jpg
//upload.wikimedia.org/wikipedia/commons/thumb/2/26/VIC1689Jeffrey1945.jpg/280px-VIC1689Jeffrey1945.jpg