Torrent file analyzer

torrent.py

#!/usr/bin/env python
# =============================================================================
# @file   torrent.py
# @author Albert Puig (albert.puig@epfl.ch)
# @date   05.07.2014
# =============================================================================
"""Torrent file-info decoder, extracted from

http://effbot.org/zone/bencode.htm

"""
import re

def tokenize(text, match=re.compile("([idel])|(\d+):|(-?\d+)").match):
    i = 0
    while i < len(text):
        m = match(text, i)
        s = m.group(m.lastindex)
        i = m.end()
        if m.lastindex == 2:
            yield "s"
            yield text[i:i+int(s)]
            i = i + int(s)
        else:
            yield s

def decode_item(next, token):
    if token == "i":
        # integer: "i" value "e"
        data = int(next())
        if next() != "e":
            raise ValueError
    elif token == "s":
        # string: "s" value (virtual tokens)
        data = next()
    elif token == "l" or token == "d":
        # container: "l" (or "d") values "e"
        data = []
        tok = next()
        while tok != "e":
            data.append(decode_item(next, tok))
            tok = next()
        if token == "d":
            data = dict(zip(data[0::2], data[1::2]))
    else:
        raise ValueError
    return data

def decode(text):
    try:
        src = tokenize(text)
        data = decode_item(src.next, src.next())
        for token in src: # look for more tokens
            raise SyntaxError("trailing junk")
    except (AttributeError, ValueError, StopIteration):
        raise SyntaxError("syntax error")
    return data

if __name__ == '__main__':
    import sys
    import os
    # Check args
    if len(sys.argv) < 2:
        print "Specify at least one torrent file!"
        sys.exit(0)
    for file_name in sys.argv[1:]:
        if not os.path.exists(file_name):
            print "File doesn't exist, skipping -> %s" % file_name
            continue
        torrent_data = decode(open(file_name, 'rb').read())
        print "Torrent name:", torrent_data["info"]["name"]
        if 'files' in torrent_data["info"]:
            for file_ in torrent_data["info"]["files"]:
                print " *%r - %d bytes" % ("/".join(file_["path"]), file_["length"])
        else:
            print " *No file info available"

# EOF