'commit'

dsRag/Test/TestPandoc.py

@@ -1,11 +1,11 @@
 import re
 import subprocess
-
+import os
 
 def html_to_word_pandoc(html_file, output_file):
     subprocess.run(['pandoc', html_file, '-o', output_file])
 
-
+# docx 转 markdown
 def docx_to_markdown_pandoc(docx_file, output_file):
     subprocess.run(['pandoc', docx_file, '-f', 'docx', '-t', 'markdown', '-o', output_file])
 
@@ -16,7 +16,7 @@ docx_to_markdown_pandoc(docx_file, output_file)
 finalFile = "c:/new.txt"
 
 # 读取然后修改内容，输出到新的文件
-idx=0
+idx = 0
 with open(finalFile, 'w', encoding='utf-8') as f1:
     with open(output_file, 'r', encoding='utf-8') as f:
         for line in f:
@@ -24,11 +24,13 @@ with open(finalFile, 'w', encoding='utf-8') as f1:
                 # 改进后的正则表达式，匹配更多格式的MathType公式
                 if re.search(r'!\[]\(media/image\d+\.\w+\)', line) or \
                         re.search(r'\.!\[]\(media/image\d+\.\w+\)\.', line):
-                    idx=idx+1
+                    idx = idx + 1
-                    f1.write("【MathType"+str(idx)+"】\n")
+                    f1.write("【MathType" + str(idx) + "】\n")
                 else:
-                    f1.write(line.strip()+"\n")
+                    f1.write(line.strip() + "\n")
+# 删除临时文件 output_file
+os.remove(output_file)
 
 # 输出finalFile
 with open(finalFile, 'r', encoding='utf-8') as f:
-    print(f.read())
+    print(f.read())