1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
|
# -*- coding: utf-8 -*-
#
# Copyright (c) 2012-2014 Ciro Mattia Gonano <ciromattia@gmail.com>
# Copyright (c) 2013-2018 Pawel Jastrzebski <pawelj@iosphe.re>
#
# Based upon the code snippet by Ned Batchelder
# (http://nedbatchelder.com/blog/200712/extracting_jpgs_from_pdfs.html)
#
# Permission to use, copy, modify, and/or distribute this software for
# any purpose with or without fee is hereby granted, provided that the
# above copyright notice and this permission notice appear in all
# copies.
#
# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL
# WARRANTIES WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED
# WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE
# AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL
# DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA
# OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
# TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
# PERFORMANCE OF THIS SOFTWARE.
#
import os
from random import choice
from string import ascii_uppercase, digits
class PdfJpgExtract:
def __init__(self, fname):
self.fname = fname
self.filename = os.path.splitext(fname)
self.path = self.filename[0] + "-KCC-" + ''.join(choice(ascii_uppercase + digits) for _ in range(3))
def getPath(self):
return self.path
def extract(self):
pdf = open(self.fname, "rb").read()
startmark = b"\xff\xd8"
startfix = 0
endmark = b"\xff\xd9"
endfix = 2
i = 0
njpg = 0
os.makedirs(self.path)
while True:
istream = pdf.find(b"stream", i)
if istream < 0:
break
istart = pdf.find(startmark, istream, istream + 20)
if istart < 0:
i = istream + 20
continue
iend = pdf.find(b"endstream", istart)
if iend < 0:
raise Exception("Didn't find end of stream!")
iend = pdf.find(endmark, iend - 20)
if iend < 0:
raise Exception("Didn't find end of JPG!")
istart += startfix
iend += endfix
jpg = pdf[istart:iend]
jpgfile = open(self.path + "/jpg%d.jpg" % njpg, "wb")
jpgfile.write(jpg)
jpgfile.close()
njpg += 1
i = iend
return self.path, njpg
|
