Download the first image of a wikipedia article

wiki_first_image.py

import sys
import lxml.html
from path import Path
import wikipedia
import requests

def dl_image(search_str):
  page = wikipedia.page(search_str)
  html = lxml.html.fromstring(page.html())
  imgs = html.xpath("//img")
  if imgs:
    im_name = Path(imgs[0].attrib['src']).name
    matching_img = [x for x in page.images if Path(x).name in im_name]
    if matching_img:
      data = requests.get(matching_img[0])
      name = Path(matching_img[0]).name
      Path(name).write_bytes(data.content)
      print("Image written to %s" % name)
    else:
      print("No matching picture found")
  else:
    print("No picture found")



if __name__ == '__main__':
  dl_image(sys.argv[1:])