Finds references to external scripts and stylesheets from HTML page and prints download instructions for those files.

asset_finder.py

import sys
import argparse
from HTMLParser import HTMLParser

file_list = []


class AssetFinder(HTMLParser):

    def handle_starttag(self, tag, attrs):
        if tag == 'script':
            for attr in attrs:
                if attr[0] == 'src':
                    file_list.append(attr[1])
            if tag == 'link':
                for attr in attrs:
                    if attr[0] == 'href':
                        file_list.append(attr[1])

    def handle_endtag(self, tag):
        pass
    
    def handle_data(self, data):
        pass

if __name__ == "__main__":
    arg_parser = argparse.ArgumentParser()
    arg_parser.add_argument('-i', '--input', required=True)
    args = arg_parser.parse_args()
    
    f = open(args.input, 'r')
    html = f.read()

    parser = AssetFinder()
    parser.feed(html)
    for f in file_list:
        print "curl -lsO", f