Python二进制数据读取

有一段二进制数据，其结构如下：

DATA, TYPE, DESCRIPTION

00 00 00 01, 4 bytes, Symbol Count =1

00 04, 2 bytes, Symbol Length = 4

41 4D 54 44, 6 bytes, Symbol = AMTD

00, 1 byte, Error code = 0 (OK)

00 00 00 02, 4 bytes, Bar Count =  2

FIRST BAR

41 97 33 33, 4 bytes, Close = 18.90

41 99 5C 29, 4 bytes, High = 19.17

41 90 3D 71, 4 bytes, Low = 18.03

41 91 D7 0A, 4 bytes, Open = 18.23

47 0F C6 14, 4 bytes, Volume = 3,680,608

00 00 01 16 6A E0 68 80, 8 bytes, Timestamp = November 23,2007

SECOND BAR

41 93 B4 05, 4 bytes, Close = 18.4629

41 97 1E B8, 4 bytes, High = 18.89

41 90 7A E1, 4 bytes, Low = 18.06

41 96 8F 57, 4 bytes, Open = 18.82

46 E6 2E 80, 4 bytes, Volume = 2,946,325

00 00 01 16 7A 53 7C 80, 8 bytes, Timestamp = November 26,2007

TERMINATOR

FF FF, 2 bytes,

如何读取这样的二进制数据？

2、解决方案

1. 导入必要的模块。

import struct
import datetime

2. 定义必要的类和函数。

class Printable(object):
  specials = ()
  def __str__(self):
    resultlines = []
    for pair in self.__dict__.items():
      if pair[0] in self.specials: continue
      resultlines.append('%10s %s' % pair)
    return '\n'.join(resultlines)

head_fmt = '>IH6sBH'
head_struct = struct.Struct(head_fmt)
class Header(Printable):
  specials = ('bars',)
  def __init__(self, symbol_count, symbol_length,
               symbol, error_code, bar_count):
    self.__dict__.update(locals())
    self.bars = []
    del self.self

bar_fmt = '>5fQ'
bar_struct = struct.Struct(bar_fmt)
class Bar(Printable):
  specials = ('header',)
  def __init__(self, header, close, high, low,
               open, volume, timestamp):
    self.__dict__.update(locals())
    self.header.bars.append(self)
    del self.self
    self.timestamp /= 1000.0
    self.timestamp = datetime.date.fromtimestamp(self.timestamp)

def showdata(data):
  terminator = '\xff' * 2
  assert data[-2:] == terminator
  head_data = head_struct.unpack(data[:head_struct.size])
  try:
    assert head_data[4] * bar_struct.size + head_struct.size == \
           len(data) - len(terminator)
  except AssertionError:
    print 'data length is %d' % len(data)
    print 'head struct size is %d' % head_struct.size
    print 'bar struct size is %d' % bar_struct.size
    print 'number of bars is %d' % head_data[4]
    print 'head data:', head_data
    print 'terminator:', terminator
    print 'so, something is wrong, since',
    print head_data[4] * bar_struct.size + head_struct.size, '!=',
    print len(data) - len(terminator)
    raise

  head = Header(*head_data)
  for i in range(head.bar_count):
    bar_substr = data[head_struct.size + i * bar_struct.size:
                      head_struct.size + (i+1) * bar_struct.size]
    bar_data = bar_struct.unpack(bar_substr)
    Bar(head, *bar_data)
  assert len(head.bars) == head.bar_count
  print head
  for i, x in enumerate(head.bars):
    print 'Bar #%s' % i
    print x

3. 读取二进制数据并进行解析。

datas = '''
00 00 00 01 00 04 41 4D 54 44 00 00 00 00 02 41
97 33 33 41 99 5C 29 41 90 3D 71 41 91 D7 0A 47
0F C6 14 00 00 01 16 6A E0 68 80 41 93 B4 05 41
97 1E B8 41 90 7A E1 41 96 8F 57 46 E6 2E 80 00
00 01 16 7A 53 7C 80 FF FF
'''

data = ''.join(chr(int(x, 16)) for x in datas.split())
showdata(data)

4. 输出解析结果。

symbol_count 1
 bar_count 2
    symbol AMTD
error_code 0
symbol_length 4
Bar #0
    volume 36806.078125
 timestamp 2007-11-22
      high 19.1700000763
       low 18.0300006866
     close 18.8999996185
      open 18.2299995422
Bar #1
    volume 29463.25
 timestamp 2007-11-25
      high 18.8899993896
       low 18.0599994659
     close 18.4629001617
      open 18.8199901581