问使用Python从pdf中提取图像

EN

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 metadata from the object
                # so we can make sense of the image data
                size = tuple(map(int, (vobj['/Width'], vobj['/Height'])))
                img = PIL.Image.frombytes('RGB', size, buf,
                                          decoder_name='raw')
                # Obviously we can't really yield here, do something with `img`...
                yield img
            elif vobj['/Filter'] == '/DCTDecode':
                # A compressed image
                img = PIL.Image.open(io.BytesIO(vobj._data))
                yield img

#!python3.6
import fitz  # PyMuPDF


def get_pixmaps_in_pdf(pdf_filename):
    doc = fitz.open(pdf_filename)
    xrefs = set()
    for page_index in range(doc.pageCount):
        for image in doc.getPageImageList(page_index):
            xrefs.add(image[0])  # Add XREFs to set so duplicates are ignored
    pixmaps = [fitz.Pixmap(doc, xref) for xref in xrefs]
    doc.close()
    return pixmaps


def write_pixmaps_to_pngs(pixmaps):
    for i, pixmap in enumerate(pixmaps):
        pixmap.writePNG(f'{i}.png')  # Might want to come up with a better name


pixmaps = get_pixmaps_in_pdf(r'C:\StackOverflow\09_chapter 4.pdf')
write_pixmaps_to_pngs(pixmaps)