python提取word文件中的图片并上传阿里云OSS

AccessKeyId = '你的 AccessKeyId'
AccessKeySecret = '你的 AccessKeySecret'
oos_auth = oss2.Auth(AccessKeyId, AccessKeySecret)
endpoint = 'http://oss-cn-beijing.aliyuncs.com'

bucket = oss2.Bucket(oos_auth, endpoint, 'Bucket 名称')  
print(bucket)

import oss2
import time

from docx import Document

def get_questions():
    document = Document(docx='测试 Word 文档.docx')
    for p in document.paragraphs:
        print(p.text)

if __name__ == '__main__':
    get_questions()

import oss2
import time

from docx import Document

# 获取 Word 文档中的图片
def get_picture(document, paragraph):
    img = paragraph._element.xpath('.//pic:pic')
    if not img:
        return
    img = img[0]
    embed = img.xpath('.//a:blip/@r:embed')[0]
    related_part = document.part.related_parts[embed]
    image = related_part.image
    return image

def get_questions():
    document = Document(docx='测试 Word 文档.docx')

    for p in document.paragraphs:
    	# 读取图片
        img = get_picture(document, p)

        print(img)
        if img is not None:
        	# 输出图片名
            print(img.filename)
            # 输出图片后缀
            print(img.ext)
            # 输出图片的二进制流
        	# print(img.blob)
        print(p.text)

if __name__ == '__main__':
    get_questions()

import oss2
import time

from docx import Document

# 获取 Word 文档中的图片
def get_picture(document, paragraph):
    img = paragraph._element.xpath('.//pic:pic')
    if not img:
        return
    img = img[0]
    embed = img.xpath('.//a:blip/@r:embed')[0]
    related_part = document.part.related_parts[embed]
    image = related_part.image
    return image

def ret_up_imgurl(image):
    blob = image.blob
    # 后缀
    ext = image.ext

    AccessKeyId = '你的 AccessKeyId'
    AccessKeySecret = '你的 AccessKeySecret '
    oos_auth = oss2.Auth(AccessKeyId, AccessKeySecret)
    endpoint = 'http://oss-cn-beijing.aliyuncs.com'

    bucket = oss2.Bucket(oos_auth, endpoint, 'Bucket 名称')  

    base_file_url = 'https://Bucket 名称.oss-cn-beijing.aliyuncs.com/'
    # 获取一个文件名
    file_name = str(int(time.time())) + "." + ext
    # 上传二进制流
    res = bucket.put_object(file_name, blob)
    if res.status == 200:
    	# 返回标签
        img_format = '<img src="{}" />'
        return img_format.format(base_file_url + file_name)
    else:
        return False

def get_questions():
    document = Document(docx='测试 Word 文档.docx')

    for p in document.paragraphs:
        print(p.text)
        img = get_picture(document, p)

        print(img)
        if img is not None:
            print(img.filename)
            print(img.ext)
            ret_up_imgurl(img.blob)

if __name__ == '__main__':
    get_questions()