process excel

RFtools.py

@@ -22,7 +22,6 @@ if __name__ == "__main__":
     pdf_dir = (cwd_dir / config["pdf_dir"]).resolve()
     rst_dir = (cwd_dir / config["result_path"]).resolve()
     excel_path = (cwd_dir / config["excel_path"]).resolve()
-    sheet_name = config["sheet_name"]
 
     # print(excel_path)
 
@@ -42,4 +41,4 @@ if __name__ == "__main__":
                     base_url=config["base_url"])
 
     # RE.main( pdf_dir, rst_dir, config["model"], client)
-    RE.read_rough_nameIndex_from_excel(excel_path, sheet_name)
+    RE.read_rough_nameIndex_from_excel(excel_path)

config.json

@@ -5,6 +5,5 @@
     "pdf_dir": "./Papers",
     "result_path": "./result.json",
     "excel_path": "./others/reference.xlsx",
-    "sheet_name": "j24-DianNao family",
     "logLevel": 20
 }
\ No newline at end of file

psrc/rename_extractInfo.py

@@ -69,20 +69,24 @@ def extract_first_page_text(pdf_path):
         logging.warning(f"PDF has no pages: {pdf_path.name}")
         return None
 
-def read_rough_nameIndex_from_excel(excel_path: Path, sheet_name: str):
+# excel表格的第4行开始读取索引和论文名称
+def read_rough_nameIndex_from_excel(excel_path: Path):
 
     # 读取 Excel 文件中的某个工作表
-    df = pd.read_excel( excel_path, sheet_name)
-
-    # 显示前几行数据
-    print(df.head())
-
-    # 获取所有工作表的数据
-    # excel_data = pd.read_excel('example.xlsx', sheet_name=None)
-    # for sheet_name, data in excel_data.items():
-    #     print(f"工作表: {sheet_name}")
-    #     print(data.head())
-
+    # 当你读取多个工作表时，pandas.read_excel(sheet_name=None) 会返回一个字典，其中：
+        # 键 是工作表的名称（sheet_name）；
+        # 值 是每个工作表对应的 DataFrame。
+    # 通过 items()，你可以在一个循环中轻松地访问这两个部分
+
+    # 获取工作表的数据
+    excel_data = pd.read_excel(excel_path, sheet_name=None)
+    for sname, data in excel_data.items():
+        df = data.iloc[2:]
+
+        for index, row in df.iterrows():
+            print(row.iloc[0])
+            print(row.iloc[1])
+ 
 def main(pdf_directory: Path, result_path: Path, configModel: str, client):
 
     with open(result_path, "w", encoding="utf-8") as f:

result.json

@@ -4,8 +4,7 @@
     {
       "name": "Jia Si",
       "affiliations": [
-        "Key Laboratory for the Physics and Chemistry of Nanodevices and Center for Carbon-based Electronics, School of Electronics, Peking University, Beijing, China",
-        "Beijing Institute of Carbon-based Integrated Circuits, Beijing, China"
+        "Key Laboratory for the Physics and Chemistry of Nanodevices and Center for Carbon-based Electronics, School of Electronics, Peking University, Beijing, China"
       ]
     },
     {