问用pymupdf按正确的顺序提取pdf格式的图片

EN

import fitz
import sys
import re

checkXO = r"/Type(?= */XObject)"       # finds "/Type/XObject"   
checkIM = r"/Subtype(?= */Image)"      # finds "/Subtype/Image"
doc = fitz.open(fr"{pdfpath}")

lenXREF = doc._getXrefLength()         # number of objects 
pixmaps = {}
imgcount=0
count=0
imglist=[]
for i in range(1, lenXREF):            # scan through all objects
    text = doc._getXrefString(i)     # string defining the object

    isXObject = re.search(checkXO, text)    # tests for XObject
    isImage   = re.search(checkIM, text)    # tests for Image
    if not isXObject or not isImage:   # not an image object if not both True
        continue
    count+=1
    pix = fitz.Pixmap(doc, i)          # make pixmap from image
    if re.search(r'Name \WIm(\d+)',text) != None:
        imglist.append(re.search(r'Name \W(Im\d+)',text).group(1))
        pixmaps[re.search(r'Name \W(Im\d+)',text).group(1)]=pix
    if re.search(r'Name \W(Im\d+)',text) == None:
        imglist.append(count)
        pixmaps[count]=pix
imglist1=[]
for i in range(1,doc.pageCount):
    if len(doc.getPageImageList(i))>1:
        for entry in doc.getPageImageList(i):
            imglist1.append(entry[7])
        break
for entry in imglist1:    
    pixmaps[entry].writeImage(fr"{dirpath}\%s.jpg" % (imgcount),'jpg')        
    imgcount+=1