我正在尝试通过读取每个字节来读取 zip 文件(在 python 2.7.2 中)。我能够通过本地文件头和数据。但是,我在尝试读取中央文件头时被卡住了。
这有很大帮助http://en.wikipedia.org/wiki/File:ZIP-64_Internal_Layout.svg
我不知道如何找出存档中有多少项目,因此我可以切换到格式化中央文件头,或者如何知道如何从格式化文件切换到中央文件头。
这就是我现在所拥有的——
import sys
def main(debug=0,arg_file=''):
if debug==2:
print "- Opening %s" % arg_file
with open(arg_file) as archive:
if debug==2:
print "- Reading %s" % arg_file
bytes = archive.read()
if debug==2:
print "-------------Binary-------------"
print bytes
#Read file headers
end = 0
while end != bytes.__len__():
print end
end = process_sub_file(debug,end,bytes)
def process_sub_file(debug,startbytes, bytes):
header = bytes[startbytes + 0] + bytes[startbytes + 1] + bytes[startbytes + 2] + bytes[startbytes + 3]
version = bytes[startbytes + 4] + bytes[startbytes + 5]
flags = bytes[startbytes + 6] + bytes[startbytes + 7]
comp_method = bytes[startbytes + 8] + bytes[startbytes + 9]
mod_time = bytes[startbytes + 10] + bytes[startbytes + 11]
mod_date = bytes[startbytes + 12] + bytes[startbytes + 13]
crc = bytes[startbytes + 14] + bytes[startbytes + 15] + bytes[startbytes + 16] + bytes[startbytes + 17]
comp_size_bytes = bytes[startbytes + 18] + bytes[startbytes + 19] + bytes[startbytes + 20] + bytes[startbytes + 21]
comp_size = ord(comp_size_bytes[0]) + ord(comp_size_bytes[1]) + ord(comp_size_bytes[2]) + ord(comp_size_bytes[3])
uncomp_size_bytes = bytes[startbytes + 22] + bytes[startbytes + 23] + bytes[startbytes + 24] + bytes[startbytes + 25]
uncomp_size = ord(uncomp_size_bytes[0]) + ord(uncomp_size_bytes[1]) + ord(uncomp_size_bytes[2]) + ord(uncomp_size_bytes[3])
name_len_bytes = bytes[startbytes + 26] + bytes[startbytes + 27]
name_len = int(ord(name_len_bytes[0])+ord(name_len_bytes[1]))
extra_len_bytes = bytes[startbytes + 28] + bytes[startbytes + 29]
extra_len = int(ord(extra_len_bytes[0])+ord(extra_len_bytes[1]))
file_name = ""
for i in range(name_len):
file_name = file_name + bytes[startbytes + 30 + i]
extra_field = ""
for i in range(extra_len):
file_name = file_name + bytes[startbytes + 30 + name_len + i]
data = ""
for i in range(comp_size):
data = data + bytes[startbytes + 30 + name_len + extra_len + i]
if debug>=1:
print "-------------Header-------------"
print "Header Signature: %s" % header
print "Version: %s" % version
print "Flags: %s" % flags
print "Compression Method: %s" % comp_method
print "Modification Time: %s" % (ord(mod_time[0]) + ord(mod_time[1]))
print "Modification Date: %s" % (ord(mod_date[0]) + ord(mod_time[1]))
print "CRC-32: %s" % crc
print "Compressed Size: %s" % comp_size
print "Uncompressed Size: %s" % uncomp_size
print "File Name Length: %s" % name_len
print "Extra Field Length: %s" % extra_len
print "File Name: %s" % file_name
print "Extra Field: %s" % extra_field
print "Data:\n%s" % data
return startbytes + 30 + name_len + extra_len + comp_size