|
|
|
@ -20,6 +20,7 @@ handler.setFormatter(logging.Formatter('%(asctime)s - %(name)s - %(levelname)s -
|
|
|
|
|
logger.addHandler(handler)
|
|
|
|
|
logging.basicConfig(format="%(levelname)s:%(message)s", level=logging.INFO)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def resize_images_in_directory(directory_path, max_width=640, max_height=480):
|
|
|
|
|
"""
|
|
|
|
|
遍历目录下所有图片并缩放到指定尺寸
|
|
|
|
@ -55,6 +56,7 @@ def resize_images_in_directory(directory_path, max_width=640, max_height=480):
|
|
|
|
|
|
|
|
|
|
import hashlib
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def calculate_docx_md5(docx_file_path):
|
|
|
|
|
"""
|
|
|
|
|
计算docx文件的MD5哈希值
|
|
|
|
@ -73,6 +75,8 @@ def calculate_docx_md5(docx_file_path):
|
|
|
|
|
|
|
|
|
|
# 返回16进制格式的哈希值
|
|
|
|
|
return md5_hash.hexdigest()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def get_docx_content_by_pandoc(docx_file):
|
|
|
|
|
# 最后拼接的内容
|
|
|
|
|
content = ""
|
|
|
|
@ -83,6 +87,8 @@ def get_docx_content_by_pandoc(docx_file):
|
|
|
|
|
prefix = docx_file.split(".")[0].split("/")[-1]
|
|
|
|
|
temp_markdown = os.path.join('./static/markdown/', prefix + '.md')
|
|
|
|
|
# 调用pandoc将docx文件转换成markdown
|
|
|
|
|
path = "./static/Images/" + md5_value
|
|
|
|
|
if not os.path.exists(path):
|
|
|
|
|
os.mkdir("./static/Images/" + md5_value)
|
|
|
|
|
subprocess.run(['pandoc', docx_file, '-f', 'docx', '-t', 'markdown', '-o', temp_markdown,
|
|
|
|
|
'--extract-media=./static/Images/' + md5_value])
|
|
|
|
|