python脚本自动提取Java中的中文并写入excel表格中

 中文提取

import re
import os
import xlwt
import xlrd
import xlsxwriter
import numpy as np
import xlutils.copy

def findChineseCharacter(path,file_name)  :
    #匹配中文
    pattern = re.compile(r"^\"[\u4e00-\u9fa5]+\".+\"|\"[\u4e00-\u9fa5]+.*[\u4e00-\u9fa5]+.*\"")
    #返回结果
    result = []
    #异常处理
    try:
        file = open(path, encoding="UTF-8")
    except FileNotFoundError:
        print("============")
    strfile=file.read()
    #遍历字符串，一次处理一行
    i = 0
    for line in strfile.splitlines():
        i += 1 #记录中文行号
        rel111 = pattern.findall(line)
        if not len(rel111) is 0:
            result_line = []
            result_line.append(rel111)
            result_line.append(i)
            result.append(result_line)
    file.close()
    return result

def write(datas, java_name,path):
    wb = xlrd.open_workbook(path)#打开工作簿
    ws = xlutils.copy.copy(wb) #复制之前表里存在的数据
    table = ws.get_sheet("java")#根据sheet_name获取工作表
    nownrows = readline(path)
    for i in range(len(datas)):
        '''通过索引取出对应的信息'''
        row_content = datas[i]
        print(row_content)
        row_content = str(row_content[0])
        row_content = row_content.replace("[", "")#组织字符串格式
        row_content = row_content.replace("]", "")
        row_content = row_content.replace("\'", "")
        row_content = row_content.replace("\"", "")
        table.write(nownrows+i, 0, java_name+" 第"+str(datas[i][1])+"行")#写入目标xlsx
        table.write(nownrows+i, 1, row_content)
    ws.save(path)  #保存的有旧数据和新数据
def readline(path):
    wb = xlrd.open_workbook(path)  #打开excel，保留文件格式
    sheet1 = wb.sheet_by_name("java")
    nrows = sheet1.nrows  #获取总行数
    return nrows

def file_name(file_dir):
    for root, dirs, files in os.walk(file_dir):
        for file in files:
            if file.endswith(".java"):#判断是否为Java文件
                result = findChineseCharacter(os.path.join(root, file), file)
                result2 = []
                result3 = []
                for i in result:
                    if i[0] not in result2:
                        result2.append(i[0])
                        result3.append(i)
                write(result3, str(file), xlsx_path)
                print(result3, str(file))


xlsx_path = r"test.xlsx"
project_path =r"Multithread"

file_name(project_path)

运行结果：