tools.py更新

tools.py

@@ -1,101 +1,60 @@
-from enum import Enum, auto
-from typing import Any, Optional
-from pdfminer.pdfdocument import PDFDocument, PDFNoOutlines
-from pdfminer.pdfpage import PDFPage, LITERAL_PAGE
-from pdfminer.pdfparser import PDFParser, PDFSyntaxError
-from pdfminer.pdftypes import PDFObjRef
-
-
-class PDFRefType(Enum):
-    """PDF reference type."""
-
-    PDF_OBJ_REF = auto()
-    DICTIONARY = auto()
-    LIST = auto()
-    NAMED_REF = auto()
-    UNK = auto()  # fallback
-
-
-class RefPageNumberResolver:
-    """PDF Reference to page number resolver.
-
-    .. note::
-
-       Remote Go-To Actions (see 12.6.4.3 in
-       `https://www.adobe.com/go/pdfreference/`__)
-       are out of the scope of this resolver.
-
-    Attributes:
-        document (:obj:`pdfminer.pdfdocument.PDFDocument`):
-            The document that contains the references.
-        objid_to_pagenum (:obj:`dict[int, int]`):
-            Mapping from an object id to the number of the page that contains
-            that object.
-    """
-
-    def __init__(self, document: PDFDocument):
-        self.document = document
-        # obj_id -> page_number
-        self.objid_to_pagenum: dict[int, int] = {
-            page.pageid: page_num
-            for page_num, page in enumerate(PDFPage.create_pages(document), 1)
-        }
-
-    @classmethod
-    def get_ref_type(cls, ref: Any) -> PDFRefType:
-        """Get the type of a PDF reference."""
-        if isinstance(ref, PDFObjRef):
-            return PDFRefType.PDF_OBJ_REF
-        elif isinstance(ref, dict) and "D" in ref:
-            return PDFRefType.DICTIONARY
-        elif isinstance(ref, list) and any(isinstance(e, PDFObjRef) for e in ref):
-            return PDFRefType.LIST
-        elif isinstance(ref, bytes):
-            return PDFRefType.NAMED_REF
-        else:
-            return PDFRefType.UNK
-
-    @classmethod
-    def is_ref_page(cls, ref: Any) -> bool:
-        """Check whether a reference is of type '/Page'.
-
-        Args:
-            ref (:obj:`Any`):
-                The PDF reference.
-
-        Returns:
-            :obj:`bool`: :obj:`True` if the reference references
-            a page, :obj:`False` otherwise.
-        """
-        return isinstance(ref, dict) and "Type" in ref and ref["Type"] is LITERAL_PAGE
-
-    def resolve(self, ref: Any) -> Optional[int]:
-        """Resolve a PDF reference to a page number recursively.
-
-        Args:
-            ref (:obj:`Any`):
-                The PDF reference.
-
-        Returns:
-            :obj:`Optional[int]`: The page number or :obj:`None`
-            if the reference could not be resolved (e.g., remote Go-To
-            Actions or malformed references).
-        """
-        ref_type = self.get_ref_type(ref)
-
-        if ref_type is PDFRefType.PDF_OBJ_REF and self.is_ref_page(ref.resolve()):
-            return self.objid_to_pagenum.get(ref.objid)
-        elif ref_type is PDFRefType.PDF_OBJ_REF:
-            return self.resolve(ref.resolve())
-
-        if ref_type is PDFRefType.DICTIONARY:
-            return self.resolve(ref["D"])
-
-        if ref_type is PDFRefType.LIST:
-            # Get the PDFObjRef in the list (usually first element).
-            return self.resolve(next(filter(lambda e: isinstance(e, PDFObjRef), ref)))
-
-        if ref_type is PDFRefType.NAMED_REF:
-            return self.resolve(self.document.get_dest(ref))
-
-        return None  # PDFRefType.UNK
+''' helper methods
+'''
+import pandas as pd
+import numpy as np
+import re
+from Timer import timer
+import json
+import os
+import requests
+from pprint import pprint
+
+
+class BaseMethods():
+    ''' base methods class
+    '''
+    def __init__(self) -> None:
+        pass
+
+    def pandas_read_xls(self, file_path:str, sheetname:str="Sheet1"):
+        ''' 读取xls文件方法
+        '''
+        return pd.read_excel(file_path,sheet_name=sheetname)
+
+    def json_read(self, file_path:str):
+        ''' 读取json文件方法
+        '''
+        with open(file_path, "r", encoding='utf-8') as fp:
+            return json.load(fp)
+        
+    def save_file(self, save_data:list, save_path:str, file_format:str):
+        ''' 保存文件
+        '''
+        print(len(save_data))
+        if file_format == "json":
+            with open(save_path,'w',encoding='utf-8') as sf:
+                sf.write(json.dumps(save_data,ensure_ascii=False))
+        elif file_format == "xlsx" or file_format == "xls":
+            with pd.ExcelWriter(save_path) as fp:
+                save_data.to_excel(fp, sheet_name="Sheet1")
+        elif file_format == 'txt':
+            with open(save_path, 'w', encoding='utf-8') as tx:
+                for data in save_data:
+                    tx.write(data+"\n")
+    
+    def traverse_file(self, dirpath:str):
+        '''
+        遍历文件夹下文件
+        '''
+        filename = tuple()
+        for root, dir, files in os.walk(dirpath):
+            for name in files:
+                filename = filename.__add__((name,))
+        return filename
+
+
+
+    
+
+if __name__ == "__main__":
+    pass