Created
May 5, 2012 11:16
-
-
Save dehowell/2601637 to your computer and use it in GitHub Desktop.
Python script for searching a large binary file for .NEF file headers.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import sys | |
# .NEF (Nikon Electronic Format) headers | |
SIGNATURE = '\x4d\x4d\x00\x2a\x00\x00\x00\x08\x00' | |
def read_chunks(stream, overlap = len(SIGNATURE), size = 100 * 2 ** 20): | |
'''Read chunks from the stream with a small overlap.''' | |
data = stream.read(size) | |
while True: | |
yield data | |
new_data = stream.read(size) | |
if new_data == '': | |
break | |
data = data[-overlap:] + new_data | |
f = open(sys.argv[1]) | |
for chunk in read_chunks(f): | |
n = chunk.count(SIGNATURE) | |
if n > 0: | |
print 'Found %d potential NEF file headers near chunk starting at %d' % (n, f.tell()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment