Python如何实现删除pdf空白页

pip install PyPDF2

# 每一个页都是一个字典对象，看第一层没区别
# 参考文章中 第一层 keys 一样， 但是 /Resources下结构有所不同，空白页没有"/XObject"键
# 我的第一层keys 不一样，  但是 /Resources下结构一样
# 另外 PyPDF2 版本不一样，各个模块有更新，自己看源码进行更新，或者根据报错提示进行更新

from PyPDF2 import PdfReader, PdfWriter

def remove_pdf_blank_pages(path):
    pdfReader = PdfReader(open(path, 'rb'))
    writer = PdfWriter()
    pages = len(pdfReader.pages)
    # blank = pdfReader.pages[1]
    # full = pdfReader.pages[2]
    #print('*'*10)
    #print(blank.keys())# dict_keys(['/Type', '/Parent', '/Resources', '/MediaBox', '/Contents'])
    #print(full.keys())# dict_keys(['/Type', '/Parent', '/Resources', '/MediaBox', '/Annots', '/Tabs', '/StructParents', '/Contents'])
    #print(blank['/Resources'])
    #{'/Font': IndirectObject(600, 0, 139632281578944), '/XObject': {'/Im553': IndirectObject(553, 0, 139632281578944), '/Im7': IndirectObject(7, 0, 139632281578944)}, '/ProcSet': ['/PDF', '/Text', '/ImageC', '/ImageI', '/ImageB']}
    #print(full['/Resources'])
    #{'/Font': IndirectObject(600, 0, 139632281578944), '/XObject': {'/Im553': IndirectObject(553, 0, 139632281578944), '/Im7': IndirectObject(7, 0, 139632281578944)}, '/ProcSet': ['/PDF', '/Text', '/ImageC', '/ImageI', '/ImageB']}
    #print('*' * 10)
    for i in range(pages):
        page = pdfReader.pages[i]
        # if "/XObject" in page["/Resources"].keys() or "/Font" in page["/Resources"].keys():
        #     writer.add_page(page)
        if "/StructParents" in page.keys() or "/Tabs" in page.keys() or "/Annots" in page.keys():
            writer.add_page(page)

    writer.write(open(path, 'wb'))

from PyPDF2 import PdfFileReader, PdfFileWriter

path=r"D:\ebook\PDF\test.pdf"

reader = PdfFileReader(open(path, 'rb'))
"""
注意PyPDF2中页码从0开始
"""
blank= reader.getPage(16)
full = reader.getPage(17)

blank.keys()
Out[24]: dict_keys(['/Type', '/Contents', '/Parent', '/Resources', '/MediaBox'])

full.keys()
Out[25]: dict_keys(['/Type', '/Contents', '/Parent', '/Resources', '/MediaBox'])

blank['/Resources']
Out[26]: {'/ExtGState': {'/Opa0': {'/Type': '/ExtGState', '/CA': 1}}}

full['/Resources']
Out[27]: 
{'/ExtGState': {'/Opa0': {'/Type': '/ExtGState', '/CA': 1},
  '/Opa1': {'/Type': '/ExtGState', '/ca': 1}},
 '/XObject': {'/Image0': {'/BitsPerComponent': 8,
   '/Height': 1130,
   '/Filter': ['/DCTDecode'],
   '/ColorSpace': '/DeviceRGB',
   '/Type': '/XObject',
   '/Subtype': '/Image',
   '/DL': 434222,
   '/Width': 792}}}

from PyPDF2 import PdfFileReader, PdfFileWriter

path = r"D:\ebook\PDF\test.pdf"
path_output = r"D:\ebook\PDF\output.pdf"

reader = PdfFileReader(open(path, 'rb'))
writer = PdfFileWriter()
pages = pdfReader.getNumPages()

for i in range(pages):
    page = reader.getPage(i)
    if "/XObject" in page["/Resources"].keys() or "/Font" in page["/Resources"].keys():
        writer.addPage(page)
    
writer.write(open(path_output, 'wb'))