'commit'

dsLightRag/ShiTi/T3_DocxToMd.py

@@ -7,7 +7,7 @@ async def main():
     # 要处理的文件路径
     file_path = "Docx/《动能定理》巩固练习.docx"
     # 转换docx为md
-    get_docx_content_by_pandoc(file_path, '../Word转试题.md')
+    get_docx_content_by_pandoc(file_path, '../Word转试题.md',extract_media='../static/Images/')
 
 if __name__ == "__main__":
     asyncio.run(main())

dsLightRag/Util/DocxUtil.py

@@ -3,7 +3,7 @@ import subprocess
 import uuid
 
 
-def get_docx_content_by_pandoc(docx_file, output_file=None):
+def get_docx_content_by_pandoc(docx_file, output_file=None, extract_media=None):
     # 最后拼接的内容
     content = ""
     # output_file 设置为临时目录下的uuid.md
@@ -12,9 +12,11 @@ def get_docx_content_by_pandoc(docx_file, output_file=None):
     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
-    os.mkdir("./static/Images/" + file_name)
+    if extract_media is None:
+        os.mkdir("./static/Images/" + file_name)
+        extract_media = "./static/Images/"
     subprocess.run(['pandoc', docx_file, '-f', 'docx', '-t', 'markdown', '-o', temp_markdown,
-                    '--extract-media=./static/Images/' + file_name])
+                    '--extract-media=' + extract_media + file_name])
     # 读取然后修改内容，输出到新的文件
     img_idx = 0  # 图片索引
     with open(temp_markdown, 'r', encoding='utf-8') as f: