Extract the SHA1 hash from a torrent file

Question

I've had a look around for the answer to this, but I only seem to be able to find software that does it for you. Does anybody know how to go about doing this in python?

Answer 1

Updated script for python3 based on the accepted answer. Also added progression and no need for external libraries.

import sys, os, hashlib, io, re

decimal_match = re.compile(r'\d')

def bdecode(data):
    '''Main function to decode bencoded data'''
    chunks = [i.to_bytes() for i in data]
    print(chunks[:100])
    chunks.reverse()
    root = _dechunk(chunks)
    return root

def _dechunk(chunks):
    item = chunks.pop()
    #print(item)

    if item == b'd':
        item = chunks.pop()
        hash = {}
        while item != b'e':
            chunks.append(item)
            key = _dechunk(chunks)
            hash[key.decode("utf-8")] = _dechunk(chunks)
            item = chunks.pop()
        return hash
    elif item == b'l':
        item = chunks.pop()
        list = []
        while item != b'e':
            chunks.append(item)
            list.append(_dechunk(chunks))
            item = chunks.pop()
        return list
    elif item == b'i':
        item = chunks.pop()
        num = b''
        while item != b'e':
            num  += item
            item = chunks.pop()
        return int(num)
    elif decimal_match.search(item.decode("utf-8")):
        num = b''
        while decimal_match.search(item.decode("utf-8")):
            num += item
            item = chunks.pop()
        line = b''
        for i in range(int(num)):
            line += chunks.pop()
        return line

    print(item)
    raise ValueError("Invalid input!")

currentTestedPath = ""

def pieces_generator(info):
    global currentTestedPath
    """Yield pieces from download file(s)."""
    piece_length = info['piece length']
    if 'files' in info: # yield pieces from a multi-file torrent
        piece = b""
        for file_info in info['files']:
            path = os.sep.join([info['name'].decode("utf-8")] + [p.decode("utf-8") for p in file_info['path']])
            currentTestedPath = path
            print(currentTestedPath)
            sfile = open(path, "rb")
            while True:
                piece += sfile.read(piece_length-len(piece))
                if len(piece) != piece_length:
                    sfile.close()
                    break
                yield piece
                piece = b""
        if piece != b"":
            yield piece
    else: # yield pieces from a single file torrent
        path = info['name'].decode("utf-8")
        print(path)
        sfile = open(path.decode('UTF-8'), "rb")
        while True:
            piece = sfile.read(piece_length)
            if not piece:
                sfile.close()
                return
            yield piece

def corruption_failure():
    """Display error message and exit"""
    print("download corrupted")
    exit(1)

def main():
    # Open torrent file
    torrent_file = open(sys.argv[1], "rb")
    metainfo = bdecode(torrent_file.read())
    print(metainfo)
    info = metainfo['info']
    pieces = io.BytesIO(info['pieces'])
    # Iterate through pieces
    nbTestedPieces = 0
    for piece in pieces_generator(info):
        nbTestedPieces += 1
        # Compare piece hash with expected hash
        piece_hash = hashlib.sha1(piece).digest()
        #if nbTestedPieces%100 == 0:
        print("Testing hash "+piece_hash.hex()+" for '"+currentTestedPath+"' ("+str(nbTestedPieces)+"/"+str(int(len(info['pieces'])/20))+")")
        if (piece_hash != pieces.read(20)):
            corruption_failure()

    # ensure we've read all pieces
    if pieces.read():
        corruption_failure()

if __name__ == "__main__":
    main()

Answer 2

In case if anybody wonders how to extract file hashes from BitTorrent v2 compatible torrents, you can use this command line tool.

Answer 3

I wrote a piece of python code that verifies the hashes of downloaded files against what's in a .torrent file. Assuming you want to check a download for corruption you may find this useful.

You need the bencode package to use this. Bencode is the serialization format used in .torrent files. It can marshal lists, dictionaries, strings and numbers somewhat like JSON.

The code takes the hashes contained in the info['pieces'] string:

torrent_file = open(sys.argv[1], "rb")
metainfo = bencode.bdecode(torrent_file.read())
info = metainfo['info']
pieces = StringIO.StringIO(info['pieces'])

That string contains a succession of 20 byte hashes (one for each piece). These hashes are then compared with the hash of the pieces of on-disk file(s).

The only complicated part of this code is handling multi-file torrents because a single torrent piece can span more than one file (internally BitTorrent treats multi-file downloads as a single contiguous file). I'm using the generator function pieces_generator() to abstract that away.

You may want to read the BitTorrent spec to understand this in more details.

Full code bellow:

import sys, os, hashlib, StringIO, bencode

def pieces_generator(info):
    """Yield pieces from download file(s)."""
    piece_length = info['piece length']
    if 'files' in info: # yield pieces from a multi-file torrent
        piece = ""
        for file_info in info['files']:
            path = os.sep.join([info['name']] + file_info['path'])
            print path
            sfile = open(path.decode('UTF-8'), "rb")
            while True:
                piece += sfile.read(piece_length-len(piece))
                if len(piece) != piece_length:
                    sfile.close()
                    break
                yield piece
                piece = ""
        if piece != "":
            yield piece
    else: # yield pieces from a single file torrent
        path = info['name']
        print path
        sfile = open(path.decode('UTF-8'), "rb")
        while True:
            piece = sfile.read(piece_length)
            if not piece:
                sfile.close()
                return
            yield piece

def corruption_failure():
    """Display error message and exit"""
    print("download corrupted")
    exit(1)

def main():
    # Open torrent file
    torrent_file = open(sys.argv[1], "rb")
    metainfo = bencode.bdecode(torrent_file.read())
    info = metainfo['info']
    pieces = StringIO.StringIO(info['pieces'])
    # Iterate through pieces
    for piece in pieces_generator(info):
        # Compare piece hash with expected hash
        piece_hash = hashlib.sha1(piece).digest()
        if (piece_hash != pieces.read(20)):
            corruption_failure()
    # ensure we've read all pieces 
    if pieces.read():
        corruption_failure()

if __name__ == "__main__":
    main()

Answer 4

Here how I've extracted HASH value from torrent file:

#!/usr/bin/python

import sys, os, hashlib, StringIO
import bencode



def main():
    # Open torrent file
    torrent_file = open(sys.argv[1], "rb")
    metainfo = bencode.bdecode(torrent_file.read())
    info = metainfo['info']
    print hashlib.sha1(bencode.bencode(info)).hexdigest()    

if __name__ == "__main__":
    main()

It is the same as running command:

transmissioncli -i test.torrent 2>/dev/null | grep "^hash:" | awk '{print $2}'

Hope, it helps :)

Answer 5

According to this, you should be able to find the md5sums of files by searching for the part of the data that looks like:

d[...]6:md5sum32:[hash is here][...]e

(SHA is not part of the spec)