shovel/main.py

import httplib2
import re
import argparse
from bs4 import BeautifulSoup

if __name__ == '__main__':
    parser = argparse.ArgumentParser(description="Dig out links from a website.")
    parser.add_argument('site', type=str, help="Website that you want to scrape for links.")
    parser.add_argument('-f', '--filter', type=str, default='\..*$', help="Only return filenames matching this regular expression.")
    args = parser.parse_args()
    
    h = httplib2.Http('.cache')
    response, content = h.request(args.site)
    s = BeautifulSoup(content)
    """find only file names"""
    links = s.find_all(href=re.compile(args.filter))
    if not links or links == 0:
        exit("No filenames found with the given filter.")
    for link in links:
        print(args.site + link['href'])