利用Python实现读取Word文档里的Excel附件

#zipfile为python自带包
from zipfile import ZipFile
with ZipFile("test.docx", "r") as zip:
    for entry in zip.infolist():
        if not entry.filename.startswith("word/embeddings/"):
            continue
        zip.extract(entry.filename)

unzip  test.docx word/embeddings/*
#返回
Archive:  test.docx
   creating: word/embeddings/
  inflating: word/embeddings/oleObject1.bin
  inflating: word/embeddings/oleObject2.bin
  inflating: word/embeddings/oleObject3.bin

file word/embeddings/oleObject1.bin
#返回
word/embeddings/oleObject1.bin: Composite Document File V2 Document, Cannot read section info

pip install olefile

import olefile
f = "word/embeddings/oleObject1.bin"
if olefile.isOleFile(f):
    with olefile.OleFileIO(f) as ole:
        print(ole.listdir())
    #返回[['\x01Ole'], ['\x03ObjInfo'], ['package']]
    # 经分析只有package里放着我们需要的信息
        bin_data = ole.openstream("package").read()
        fn = f.replace("word/embeddings/","")
        with open(fn, "wb") as output_file:
            output_file.write(bin_data)

file oleObject1.bin
#返回
oleObject1.bin: Microsoft Excel 2007+

import olefile
from zipfile import ZipFile
def get_ole(filename):
    with ZipFile(filename, "r") as zip:
        for entry in zip.infolist():
            if not entry.filename.startswith("word/embeddings/"):
                continue
            with zip.open(entry.filename) as f:
                if not olefile.isOleFile(f):
                    continue
                with olefile.OleFileIO(f) as ole:
                    bin_data = ole.openstream("package").read()
                    fn = entry.filename.replace("word/embeddings/","")
           #如果想直接读取，可以把下面两行代码换成需要的代码。
                    with open(fn, "wb") as output_file:
                        output_file.write(bin_data)
if __name__ == '__main__':
    get_ole("/Users/steven/temp/test.docx")

pip install git+https://github.com/h2non/filetype.py

import filetype
ext = filetype.guess_extension("oleObject1.bin")
print(ext)
#返回
xlsx

pip install python-magic-bin

import magic
m = magic.Magic(extension=True)
ext = m.from_file("oleObject1.bin")
print(ext)
#返回
xlsx