Update common_parse.py

magic_pdf/parse/common_parse.py

@@ -33,13 +33,13 @@ def parse_args():
     args = parser.parse_args()
     return args
 
-def process_file(file_path, pdf_ocr, excel_ocr, output_dir,config_path):
+def process_file(file_path, pdf_ocr, excel_ocr, output_dir):
     """Process a single file for OCR based on its extension."""
     try:
         res = ''
         if file_path.endswith('.pdf'):
 
-            res = pdf_ocr.ocr_pdf_client(path=file_path, output_dir=output_dir,config_path=config_path)
+            res = pdf_ocr.ocr_pdf_client(path=file_path, output_dir=output_dir)
         elif file_path.endswith('.xls') or file_path.endswith('.xlsx'):
             res = excel_ocr.parse(file_path, output_dir)
 
@@ -63,17 +63,17 @@ def determine_output_dir(output_dir):
         return os.path.join(current_working_directory, output_dir)
     return output_dir
 
-def process_input(input_path, pdf_ocr, excel_ocr, output_dir,config_path):
+def process_input(input_path, pdf_ocr, excel_ocr, output_dir):
     """Process the input path, which can be a directory or a single file."""
     if os.path.isdir(input_path):
         for root, _, files in os.walk(input_path):
             for file in files:
                 file_path = os.path.join(root, file)
                 logger.info(f'正在处理文件: {file_path}')
-                process_file(file_path, pdf_ocr, excel_ocr, output_dir,config_path)
+                process_file(file_path, pdf_ocr, excel_ocr, output_dir)
     else:
         logger.info(f'正在处理单个文件: {input_path}')
-        process_file(input_path, pdf_ocr, excel_ocr, output_dir,config_path)
+        process_file(input_path, pdf_ocr, excel_ocr, output_dir)
 
 def main():
     args = parse_args()
@@ -88,7 +88,7 @@ def main():
     logger.info(f'输入目录或文件的路径为: {input_path}')
     logger.info(f'输出目录为: {output_dir}')
 
-    process_input(input_path, pdf_ocr, excel_ocr, output_dir,args.config_path)
+    process_input(input_path, pdf_ocr, excel_ocr, output_dir)
 
 
 if __name__ == "__main__":