Browse Source

feat: update input and output paths in document parser for new PDF file, adjusting page processing range

zhch158_admin 2 days ago
parent
commit
e057701985
1 changed files with 6 additions and 3 deletions
  1. 6 3
      zhch/universal_doc_parser/main_v2.py

+ 6 - 3
zhch/universal_doc_parser/main_v2.py

@@ -403,8 +403,11 @@ if __name__ == "__main__":
             # "input": "/Users/zhch158/workspace/data/流水分析/B用户_扫描流水.pdf",
             # "output_dir": "/Users/zhch158/workspace/data/流水分析/B用户_扫描流水/bank_statement_yusys_v2",
 
-            "input": "/Users/zhch158/workspace/data/流水分析/2023年度报告母公司.pdf",
-            "output_dir": "/Users/zhch158/workspace/data/流水分析/2023年度报告母公司/bank_statement_yusys_v2",
+            # "input": "/Users/zhch158/workspace/data/流水分析/2023年度报告母公司.pdf",
+            # "output_dir": "/Users/zhch158/workspace/data/流水分析/2023年度报告母公司/bank_statement_yusys_v2",
+
+            "input": "/Users/zhch158/workspace/data/流水分析/施博深.pdf",
+            "output_dir": "/Users/zhch158/workspace/data/流水分析/施博深/bank_statement_yusys_v2",
 
             # 配置文件
             "config": "./config/bank_statement_yusys_v2.yaml",
@@ -415,7 +418,7 @@ if __name__ == "__main__":
             "scene": "bank_statement",
             
             # 页面范围(可选)
-            "pages": "4",  # 只处理前4页
+            "pages": "1",  # 只处理前4页
             # "pages": "1-3,5,7-10",  # 处理指定页面
 
             "streaming": True,