python文档统计字数、页数、文件个数的统计工具

提示：文章写完后，目录可以自动生成，如何生成可参考右边的帮助文档

---

前言

`随着人工智能的不断发展，Python开发语言也越来越普遍，针对文档的操作更是便捷，在办公时使用编写文档工具可大大简化工作难度，提升效率。

---

一、文档页数，字数，文档数统计工具

本文主要针对大批量文档的一个统计工作。

二、使用步骤

1.引入库

代码如下（示例）：

import re
from tkinter import *
import tkinter as tk
from tkinter import ttk
from tkinter import filedialog
from spire.doc import *
from spire.doc import Document

其中前端框架采用tkinter，文档操作使用的spire.doc第三方库，功能丰富，操作文档，基本已经内置了相应接口，直接拿来即用。

2.代码逻辑

代码如下（示例）：

window = Tk() # 创建窗口对象
window.title("代码统计工具") # 设置窗口标题
window.geometry("1280x720") # 设置窗口大小

# 第5步，创建一个主frame，长在主window窗口上
frameT = tk.Frame(window).grid(row=0,column=0,columnspan=40)

chooseQueryType = 0
abnormalComList = ['.java','.vue']


# 用于获取文件夹下，Java文件中包含特定字符的内容
def getWordContent(folderPath):
    paragraphCount = 0
    charCount = 0
    charCountWithspaces = 0
    wordCount = 0
    doc = Document()
    pageCount = 0
    wordCountNum = 0
    for root, dirs, files in os.walk(folderPath):
        for file in files:
            if file.endswith(('.doc','.docx')):
                # 载入lord文档
                wordCountNum = wordCountNum +1
                doc.LoadFromFile(os.path.join(root,file))
                #更新字数统计(确保字数统计是最新的)doc.Updatewordcount()#获取文档内置属性
                builtinProperties = doc.BuiltinDocumentProperties
                # 获取页数
                ttt = builtinProperties.PageCount
                if ttt >= 0:
                    pageCount = pageCount + builtinProperties.PageCount
                # 获取段落数
                paragraphCount = paragraphCount + builtinProperties.ParagraphCount
                # 获取字符数
                charCount = charCount + builtinProperties.CharCount
                # 获取包含空格的字符数
                charCountWithspaces = charCountWithspaces + builtinProperties.CharCountWithSpace
                # 获取字数
                ttt = builtinProperties.WordCount
                if ttt >= 0:
                    wordCount = wordCount + builtinProperties.WordCount
              


    tk.Label(frameT, text="页数："+str(pageCount), width=100).grid(row=2, column=0, columnspan=2)
    # tk.Label(frameT, text="段落数："+str(paragraphCount), width=100).grid(row=3, column=0, columnspan=2)
    tk.Label(frameT, text="字符数："+str(charCount), width=100).grid(row=4, column=0, columnspan=2)
    tk.Label(frameT, text="包含空格的字符数："+str(charCountWithspaces), width=100).grid(row=5, column=0, columnspan=2)
    # tk.Label(frameT, text="字数："+str(wordCount), width=100).grid(row=6, column=0, columnspan=2)
    tk.Label(frameT, text="文件数："+str(wordCountNum), width=100).grid(row=7, column=0, columnspan=2)

def tempCreate():
    folderPath = filedialog.askdirectory()
    tk.Label(frameT, text=folderPath, width=100).grid(row=1, column=1, columnspan=2)
    print(folderPath)
    getWordContent(folderPath)





# 第一行
b = tk.Button(frameT, text='文档统计选择文件夹', font=('Arial', 12), width=20, height=1, command=tempCreate)
b.grid(row=0,column=0)
tk.Label(frameT, text="文件夹路径:").grid(row=1,column=0)






# 用于获取文件夹下，Java文件中包含特定字符的内容
def getSpecificContent(folderPath, specificStr, specificStr2):
    global chooseQueryType
    rs = []
    lineNum = 0
    port_num = 0
    for root, dirs, files in os.walk(folderPath):
        for file in files:
            if file.endswith(abnormalComList[chooseQueryType]):
                file_path = os.path.join(root, file)
                with open(file_path, 'r', encoding='utf-8') as f:
                    content = f.read()
                    lineNum = lineNum + len(content.splitlines())
                    print(lineNum)
                    if re.search(specificStr, content):
                        """
                        lines = content.splitlines()
                        for line in lines:
                            # print(line.find(specificStr))
                            if line.find(specificStr) != -1 and line.find('http') == -1:
                                con = extract_quote_data(line)
                                for ser in con:
                                    rs.append(ser)
                        """
                        port_num = port_num+content.count(specificStr2)

                                # print(con)
                        # print("File: " + file_path)
                        # print("Content:")
                        # print(re.findall(specificStr, content))
    print("-------------->所有代码行数："+str(lineNum))
    print("-------------->所有代码接口数：" + str(port_num))
    tk.Label(frameT, text="-------------->所有代码行数："+str(lineNum), width=100).grid(row=12, column=0, columnspan=2)
    tk.Label(frameT, text="-------------->所有代码接口数：" + str(port_num), width=100).grid(row=13, column=0, columnspan=2)
    return rs

def tempCreateCode():
    kw = "@FeignClient"

    kw1 = '@RestController'
    kw2 = '@ApiOperation'
    folderPath = filedialog.askdirectory()
    tk.Label(frameT, text=folderPath, width=100).grid(row=11, column=1, columnspan=2)
    print(folderPath)
    # folderPath = 'D://project'
    con = getSpecificContent(folderPath, kw1, kw2)
    unique_set = set(tuple(con))
    print(unique_set)


# 第二行
b = tk.Button(frameT, text='代码统计选择文件夹', font=('Arial', 12), width=20, height=1, command=tempCreateCode)
b.grid(row=10,column=0)
def abnorSele (event):
    global chooseQueryType
    chooseQueryType = abnorBox.current()
abnorBox = ttk.Combobox(frameT,values=abnormalComList,width=20,state="readonly")
abnorBox.set(abnormalComList[0]) # 设置默认选项
abnorBox.grid(row=10,column=1,columnspan=2)
abnorBox.bind("<<ComboboxSelected>>", abnorSele)

tk.Label(frameT, text="文件夹路径:").grid(row=11,column=0)

window.mainloop() # 运行窗口主循环

开发工具为pycharm，代码直接运行即可使用，前提是先导入对应第三方库。spire.doc使用的是12.4.0版本

---