Python脚本解析BitTorrent种子文件内容

mmdbcn

　　有很多种子文件，有时候记不清里面都是什么东西，又不想一个一个的拖放到迅雷或BT软件里头看，
　　上网查了一下Python的脚本，自己也稍微修改了一下，代码如下，粘贴到文本编辑器中：
　　保存成py后缀的，直接运行
　　import redef tokenize(text, match=re.compile("([idel])|(/d+):|(-?/d+)").match):i = 0while 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 ValueErrorelif 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 ValueErrorreturn datadef decode(text):try:src = tokenize(text)data = decode_item(src.next, src.next())for token in src: # look for more tokensraise 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("Riko.Tachibana.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 "-----------------------------------------------------------------"
　　注意要保存成Utf-8格式的文件，不能使用ASCII编码格式保存，否则中文会乱码或无法编译