使用Python读取CR2(原始佳能图像)标题 [英] Reading a CR2 (Raw Canon Image) header using Python

问题描述

我正在尝试从CR2(原始图片的佳能格式)提取拍摄照片的日期/时间。

我知道CR2 specification，并且我知道我可以使用Pythonstruct模块从二进制缓冲区提取片段。

简而言之，规范说我可以在标记0x0132 / 306中找到一个长度为20的字符串-日期和时间。

我尝试使用以下命令获取该标记：

struct.unpack_from(20*'s', buffer, 0x0132)

但我得到

('x00', 'x00', "'", 'x88, ...[and more crap])

有什么想法吗？

编辑

非常感谢您的努力！答案是惊人的，我学到了很多关于处理二进制数据的知识。

推荐答案

您是否考虑到应该(根据规范)位于您谈论的IFD挡路之前的标头？

我看了一下规范，上面说第一个IFD挡路跟在16字节头后面。因此，如果我们读取字节16和17(在偏移量0x10祸不单行处)，我们应该得到第一个IFD挡路中的条目数量。然后，我们只需搜索每个条目，直到找到一个匹配的标记ID(据我所知)，它将提供日期/时间字符串的字节偏移量。

这对我有效：

from struct import *

def FindDateTimeOffsetFromCR2( buffer, ifd_offset ):
    # Read the number of entries in IFD #0
    (num_of_entries,) = unpack_from('H', buffer, ifd_offset)
    print "ifd #0 contains %d entries"%num_of_entries

    # Work out where the date time is stored
    datetime_offset = -1
    for entry_num in range(0,num_of_entries-1):
        (tag_id, tag_type, num_of_value, value) = unpack_from('HHLL', buffer, ifd_offset+2+entry_num*12)
        if tag_id == 0x0132:
            print "found datetime at offset %d"%value
            datetime_offset = value
    return datetime_offset

if __name__ == '__main__':
    with open("IMG_6113.CR2", "rb") as f:
        buffer = f.read(1024) # read the first 1kb of the file should be enough to find the date / time
        datetime_offset = FindDateTimeOffsetFromCR2(buffer, 0x10)
        print unpack_from(20*'s', buffer, datetime_offset)

我的示例文件的输出为：

ifd #0 contains 14 entries
found datetime at offset 250
('2', '0', '1', '0', ':', '0', '8', ':', '0', '1', ' ', '2', '3', ':', '4', '5', ':', '4', '6', 'x00')

[编辑]-a修订/更详细的示例

from struct import *

recognised_tags = { 
    0x0100 : 'imageWidth',
    0x0101 : 'imageLength',
    0x0102 : 'bitsPerSample',
    0x0103 : 'compression',
    0x010f : 'make',    
    0x0110 : 'model',
    0x0111 : 'stripOffset',
    0x0112 : 'orientation', 
    0x0117 : 'stripByteCounts',
    0x011a : 'xResolution',
    0x011b : 'yResolution',
    0x0128 : 'resolutionUnit',
    0x0132 : 'dateTime',
    0x8769 : 'EXIF',
    0x8825 : 'GPS data'};

def GetHeaderFromCR2( buffer ):
    # Unpack the header into a tuple
    header = unpack_from('HHLHBBL', buffer)

    print "
byte_order = 0x%04X"%header[0]
    print "tiff_magic_word = %d"%header[1]
    print "tiff_offset = 0x%08X"%header[2]
    print "cr2_magic_word = %d"%header[3]
    print "cr2_major_version = %d"%header[4]
    print "cr2_minor_version = %d"%header[5]
    print "raw_ifd_offset = 0x%08X
"%header[6]

    return header

def FindDateTimeOffsetFromCR2( buffer, ifd_offset, endian_flag ):
    # Read the number of entries in IFD #0
    (num_of_entries,) = unpack_from(endian_flag+'H', buffer, ifd_offset)
    print "Image File Directory #0 contains %d entries
"%num_of_entries

    # Work out where the date time is stored
    datetime_offset = -1

    # Go through all the entries looking for the datetime field
    print " id  | type |  number  |  value   "
    for entry_num in range(0,num_of_entries):

        # Grab this IFD entry
        (tag_id, tag_type, num_of_value, value) = unpack_from(endian_flag+'HHLL', buffer, ifd_offset+2+entry_num*12)

        # Print out the entry for information
        print "%04X | %04X | %08X | %08X "%(tag_id, tag_type, num_of_value, value),
        if tag_id in recognised_tags:
            print recognised_tags[tag_id]

        # If this is the datetime one we're looking for, make a note of the offset
        if tag_id == 0x0132:
            assert tag_type == 2
            assert num_of_value == 20
            datetime_offset = value

    return datetime_offset

if __name__ == '__main__':
    with open("IMG_6113.CR2", "rb") as f:
        # read the first 1kb of the file should be enough to find the date/time
        buffer = f.read(1024) 

        # Grab the various parts of the header
        (byte_order, tiff_magic_word, tiff_offset, cr2_magic_word, cr2_major_version, cr2_minor_version, raw_ifd_offset) = GetHeaderFromCR2(buffer)

        # Set the endian flag
        endian_flag = '@'
        if byte_order == 0x4D4D:
            # motorola format
            endian_flag = '>'
        elif byte_order == 0x4949:
            # intel format
            endian_flag = '<'

        # Search for the datetime entry offset
        datetime_offset = FindDateTimeOffsetFromCR2(buffer, 0x10, endian_flag)

        datetime_string = unpack_from(20*'s', buffer, datetime_offset)
        print "
Datetime: "+"".join(datetime_string)+"
"

这篇关于使用Python读取CR2(原始佳能图像)标题的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！