import os
import os.path
import string
import sys
import urllib

try: set()
except NameError: import sets; set = sets.Set

ALPHANUMERALS = set(string.letters + string.digits)
WGET_CMD = 'wget -O "%s" --quiet "%s"'

def clean(text):
    return ''.join([c for c in text if c in ALPHANUMERALS])

def save_link_to_file(link, fname):
    print 'getting link "%s" to file "%s" ...' % (link, fname)
    error = os.system(WGET_CMD % (fname, link))
    return bool(error)

def main(output_dir):
    books = []
    for l in sys.stdin:
        l = l[:-1]
        book_data = eval(l)
        books.append(book_data)

    if not os.path.exists(output_dir):
        os.mkdir(output_dir)

    for class_number, subject, book, html_link, image_link, pdf_links in books:
        subject = clean(subject)
        book = clean(book)
        book_name = 'class_%(class_number)s.%(subject)s.%(book)s' % locals()

        book_dir = os.path.join(output_dir, book_name)
        if not os.path.exists(book_dir):
            os.mkdir(book_dir)

        image_path = os.path.join(book_dir, 'image.jpg')
        error = save_link_to_file(image_link, image_path)
        if error:
            print >> sys.stderr, 'could not get image link "%s"' % (image_link)

        for index, pdf_link in enumerate(pdf_links):
            pdf_fname = os.path.basename(pdf_link)
            pdf_fname = urllib.unquote(pdf_fname).decode('latin1').encode('ascii', 'ignore')
            pdf_fname = os.path.join(book_dir, pdf_fname)
            error = save_link_to_file(pdf_link, pdf_fname)
            if error:
                print >> sys.stderr, 'could not get pdf link "%s"' % (pdf_link)

if __name__ == '__main__':
    if len(sys.argv) < 2:
        print 'Usage: %s <output_dir>' % (sys.argv[0])
        sys.exit(2)

    output_dir = sys.argv[1]
    main(output_dir)