Python实现解析Bit Torrent种子文件内容的方法

import redef 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 sdef 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 datadef 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 dataif __name__ == "__main__":#需要读取的文件名称放到这里 data = open("The_Shawshank_Redemption.torrent", "rb").read() torrent = decode(data) myfile = file("testit.txt", 'w') a = u'文件名称'.encode('gbk') b = u'文件大小'.encode('gbk') print "%s /t %s /n" % (a,b) for file in torrent["info"]["files"]:  print "%s /t %d Mb " % ("/".join(file["path"]), file["length"]/1024/1024)  print "-----------------------------------------------------------------"