python 简易表格封装+路径+xml

import xlsxwriter
import openpyxl
import os
import operator
import xml.etree.ElementTree as ET

import requests
# import json
from bs4 import BeautifulSoup


class MyXlsx:
    def __init__(self):
        self._book1 = None    # 新表工作簿
        self._sheet1 = None    # 新表工作簿
        self._book2 = None    # 追加方式操作表工作簿
        self._sheet2 = None   # 追加方式操作表工作簿
        self._type_new = False   # 新表模式默认
        self._path_name = ""
        self._currow = 0

    '''
    打开表格
    '''
    def open_xlsx(self, str_path="", str_book_name=""):
        if os.path.exists(str_path) is False:
            self._book1 = xlsxwriter.Workbook(str_path)
            self._sheet1 = self._book1.add_worksheet(str_book_name)
        else:
            self._book2 = openpyxl.load_workbook(str_path)
            self._sheet2 = self._book2[str_book_name]
            self._type_new = True
            self._path_name = str_path
        return MyXlsx

    '''
    写数据 效率慢
    '''
    def write(self, str_data=list, row=1, low=1):
        if self._type_new:
            if row > 1 or low > 1:
                for x, y in enumerate(str_data):
                    self._sheet2.cell(row, low + x, y)    # 效率慢
            else:
                # max_row = self._sheet2.max_row
                # for x, y in enumerate(str_data):
                #     self._sheet2.cell(max_row, low + x, y)    # 效率慢
                self._sheet2.append(str_data)
        else:
            self._sheet1.write_row(self._currow, low - 1, str_data)
            self._currow += 1

    '''
    读数据 按行读取默认
    '''
    def read(self, row=0, low=0, isbyrow=True):
        lt = []
        if isbyrow:
            for i in range(low, self._sheet2.max_col):
                lt.append(self._sheet2.cell(row, i))
        else:
            for i in range(row, self._sheet2.max_row):
                lt.append(self._sheet2.cell(i, low))
        return lt

    '''
    保存数据
    '''
    def save(self):
        if self._type_new:
            self._book2.save(self._path_name)
        else:
            self._book1.close()

class Mypath:
    def __init__(self):
        ...

    '''
    删除路径下的所有文件以及文件夹  os.removedirs()不好用的样子
    '''
    @staticmethod
    def remove_all_file(input_path):
        if operator.eq(os.path.exists(input_path), False) is True:
            return
        for ft in os.listdir(input_path):
            f_file = input_path + "\\" + ft
            if os.path.isfile(f_file) is True:
                os.remove(f_file)
            else:
                Mypath.remove_all_file(f_file)
                os.rmdir(f_file)
        os.rmdir(input_path)

    '''
    创建文件夹
    '''
    @staticmethod
    def make_dirs(input_path):
        return os.makedirs(input_path)


    '''
    获取路径下的所有文件
    '''
    @staticmethod
    def get_file_name(input_path, houzhui=""):
        all_path = dict()
        for root, dirs, files in os.walk(input_path):
            for file in files:
                # if os.path.splitext(file)[1] == '.jpeg':
                if len(houzhui) > 0 :
                   if os.path.splitext(file)[1] == houzhui:
                        all_path[os.path.join(root, file)] = houzhui
                   else:
                       continue
                else:
                    all_path[os.path.join(root, file)] = ""
        return all_path

class Myxml:
    def __init__(self, path=""):
        self._path = path
        self._root = None
        self._xml = None


    '''
    打开xml文件，返回根节点
    '''
    def open_xml(self):
        self._xml = ET.parse(self._path)
        self._root = self._xml.getroot()

    '''
    获取文件是有节点，返回字典类型,去重
    或者指定节点tag
    '''
    def getall_tag(self):
        dt = dict()
        for one_tag in self._root.iter():
            dt[one_tag] = ""

    '''
    获取文件节点tag 的值 ;返回dict
    '''
    def get_tag_value(self, user_tag=None):
        dt = dict()
        for one_tag in self._root.iter(tag=user_tag):
            lt = [one_tag.tag, one_tag.attrib, one_tag.text]
            dt[lt] = ""
        return dt


    '''
    爬虫
    '''

class PC:
    def __init__(self):
        ...

    def testpc(self):
        url = 'https://www.sojson.com/ascii.html'
        strhtml = requests.get(url)  # Get方式获取网页数据
        soup = BeautifulSoup(strhtml.text, 'lxml')

        # 选中文字-》右键-》元素审查（有些浏览器是检查）-》 “Copy”➔“Copy Selector” #so_box > div.layui-row.layui-anim-scale.pt10 >aqwdq
        # div.layui-col-md9 > div:nth-child(3) > div:nth-child(3) > div div:nth-child(3) 冒号部分不要 txt = soup.select('#so_box > div.layui-row.layui-anim-scale.pt10 > div.layui-col-md9 > div:nth-child(3) > div> div') body >
        # div.layout > footer > div > div.layui-row.footer-site-desc > div.layui-col-md7.footer-left > p

        txt = soup.select('body > div.layout > footer > div > div.layui-row.footer-site-desc')
        for x, y in enumerate(txt[0].children):
            # json_t = {
            #     "title": i.get_text(),
            #     "link": i.get('href')
            # }
            # print(i.get_text())
            # print(i.get())
            print(x)
            print(y)