Update common_parse.py

magic_pdf/parse/common_parse.py

@@ -7,13 +7,15 @@ import argparse
 import os
 from pdf_client import ocrPdfClient
 from excel_parse import ExcelParser
-
+import os
+import requests
+import configparser
 
 def parse_args():
     parser = argparse.ArgumentParser()
     parser.add_argument(
-        '--url',
-        default='http://0.0.0.0:6030',
+        '--config_path',
+        default='/home/practice/magic_pdf-main/magic_pdf/config.ini',
         )
     parser.add_argument(
         '--path',
@@ -28,16 +30,13 @@ def parse_args():
     args = parser.parse_args()
     return args
 
-
-import os
-import requests
-
-def process_file(file_path, pdf_ocr, excel_ocr, output_dir):
+def process_file(file_path, pdf_ocr, excel_ocr, output_dir,config_path):
     """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)
+
+            res = pdf_ocr.ocr_pdf_client(path=file_path, output_dir=output_dir,config_path=config_path)
         elif file_path.endswith('.xls') or file_path.endswith('.xlsx'):
             res = excel_ocr.parse(file_path, output_dir)
 
@@ -61,33 +60,32 @@ 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):
+def process_input(input_path, pdf_ocr, excel_ocr, output_dir,config_path):
     """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)
+                process_file(file_path, pdf_ocr, excel_ocr, output_dir,config_path)
     else:
         logger.info(f'正在处理单个文件: {input_path}')
-        process_file(input_path, pdf_ocr, excel_ocr, output_dir)
+        process_file(input_path, pdf_ocr, excel_ocr, output_dir,config_path)
 
 def main():
     args = parse_args()
     input_path = normalize_path(args.path)
     output_dir = determine_output_dir(args.output_dir)
-
-    pdf_ocr = ocrPdfClient(args.url)
+    config = configparser.ConfigParser()
+    config.read(args.config_path)
+    pdf_server = config.get('server', 'pdf_server')
+    pdf_ocr = ocrPdfClient(pdf_server)
     excel_ocr = ExcelParser()
 
     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)
-
-# Example usage:
-# main()
+    process_input(input_path, pdf_ocr, excel_ocr, output_dir,args.config_path)
 
 
 if __name__ == "__main__":