Only image files with the HTML parsing and extraction

extractimages.py

# -*- coding: utf-8 -*-

import re, sys

def extractimgs(html):
    exp = re.compile(r'<img.+?src="(http://imgcomic\.naver\.net/webtoon/[0-9]+/[0-9]+/(.+?\.(jpg|png|gif)))".*?>')
    imgs = exp.findall(html)
    return imgs

def main(argv):
    if len(argv) != 2:
        print 'Usage: extractimgs.py <filename>'
        return 1

    f = open(argv[1], 'r')
    html = f.read()
    f.close()

    imgs = extractimgs(html)

    if len(imgs) == 0:
        print >> sys.stderr, "No images!"
        return 1

    for img in imgs:
        print img[0] # full link
        print img[1] # file name
        print img[2] # extension

    return 0

if __name__ == '__main__':
    sys.exit(main(sys.argv))