python生成表格文件_python脚本提取flutter项目的中文字符生成表格文件

思路： # 获取文件内连续的中文字符(筛选规则为冒号内的字符串如果出现\u4e00到\u9fa5字符串 提取冒号内容作为目标文本 (.*?)非贪婪模式)

用法：运行main.py，生成result excel文件。

library requirements

pip3 install xlwt

main.py

import os

import datetime

import re

import xlwt

class FileRead:

def __init__(self):

self.root_dir = r"C:\Users\Administrator\Desktop\flutter\your_project\lib"

# 递归获取所有文件

def find_file(self, dir_path):

file_list = []

if len(dir_path) == 0:

path = os.path.join(self.root_dir, dir_path)

else:

path = dir_path

temp_list = os.listdir(path)

for file in temp_list:

if os.path.isfile(os.path.join(path, file)):

file_list.append(os.path.join(path, file))

else:

file_list.extend(self.find_file(os.path.join(path, file)))

return file_list

# 获取文件内连续的中文字符(不包括注释，筛选规则为冒号内的字符串如果出现\u4e00到\u9fa5 则提取冒号内容作为目标文本 (.*?)非贪婪模式)

def find_chinese_in_file(self, file):

file = open(file, mode='r', encoding='UTF-8')

file_content = file.read()

result = set( )

# 正则匹配规则1 # 中文的编码范围是：\u4e00到\u9fa5

patten = re.compile(r'\'([\u4e00-\u9fa5].*?)\'')

result.update(patten.findall(file_content))

# 正则匹配规则2

patten = re.compile(r'"([\u4e00-\u9fa5].*?)"')

result.update(patten.findall(file_content))

# 清除空格

for text in result.copy():

if len(str.strip(text)) == 0:

result.remove(text)

file.close()

return result

class ExeclHelper:

def set_style(self, name, height, bold=False):

style = xlwt.XFStyle() # 初始化样式

font = xlwt.Font() # 为样式创建字体

font.name = name # 'Times New Roman'

font.bold = bold

font.color_index = 4

font.height = height

style.font = font

return style

def write_execl(self, result):

# 格式化输出

f = xlwt.Workbook()

# 创建sheet

sheet1 = f.add_sheet(u'translate', cell_overwrite_ok=True)

row0 = [u'chinese', u'english']

# 生成第一行

for i in range(0, len(row0)):

sheet1.write(0, i, row0[i], self.set_style('Times New Roman', 220, True))

# 填充数据

for i in range(0, len(result)):

sheet1.write(i+1, 0, result[i])

# 设置宽度

first_col = sheet1.col(0)

first_col.width = 256*40

second_col = sheet1.col(1)

second_col.width = 256*40

f.save("result.xls")

if __name__ == '__main__':

print(datetime.datetime.now())

file_read = FileRead()

file_path_list = file_read.find_file("")

# 找出所有中文字符

result = []

for file_path in file_path_list:

result.extend(file_read.find_chinese_in_file(file_path))

execl_helper = ExeclHelper()

execl_helper.write_execl(result)

print(datetime.datetime.now())