python读取扫描形成的pdf_使用python从PDF中提取扫描页面

这个问题在以前的堆栈溢出帖子中已经讨论过。在

请在提问前检查之前的帖子。在

编辑：

包括供将来参考的工作脚本。程序适用于Windows上的Python3.6：# coding=utf-8

# Extract jpg's from pdf's. Quick and dirty.

import sys

with open("Link/To/PDF/File.pdf", "rb") as file:

pdf = file.read()

startmark = b"\xff\xd8"

startfix = 0

endmark = b"\xff\xd9"

endfix = 2

i = 0

njpg = 0

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

print("JPG %d from %d to %d" % (njpg, istart, iend))

jpg = pdf[istart:iend]

with open("jpg%d.jpg" % njpg, "wb") as jpgfile:

jpgfile.write(jpg)

njpg += 1

i = iend