python 读取pdf图片_使用Python从pdf中提取图像

下面是一些使用pyPdf读取PDF文件、提取图像并将它们生成为PIL.Image的代码。你需要根据自己的需要修改它，这里只是演示如何遍历对象树。在import io

import pyPdf

import PIL.Image

infile_name = 'my.pdf'

with open(infile_name, 'rb') as in_f:

in_pdf = pyPdf.PdfFileReader(in_f)

for page_no in range(in_pdf.getNumPages()):

page = in_pdf.getPage(page_no)

# Images are part of a page's `/Resources/XObject`

r = page['/Resources']

if '/XObject' not in r:

continue

for k, v in r['/XObject'].items():

vobj = v.getObject()

# We are only interested in images...

if vobj['/Subtype'] != '/Image' or '/Filter' not in vobj:

continue

if vobj['/Filter'] == '/FlateDecode':

# A raw bitmap

buf = vobj.getData()

# Notice that we need me