网易云微专业 职场人必学的Python技能课 答案已更新P22-P37

之前up主把资源删掉了，重新找的资源，从P22 01 输出目录下所有文件及文件夹 开始
答案不定时更新（已更新P22-P35），目前我也在跟着学习。课程链接是在https://www.bilibili.com/video/BV1CQ4y1K7MK?p=30

怕大家把答案和视频资源匹配出错，这是那个课件的老师，应该认不错了吧。废话不多说，上代码。.

'''----------1、统计文件名中含python的文件------------'''
# def check_python():
#     a = []
#     c=[]
#     sum = 0
#     for file in os.scandir():
#         if file.is_dir() is False:
#             a.append(file.name)
#             c.append(file.name.lower())
#     print(a,c)
#     for i in a:
#         b = re.findall('python', i, re.I)
#         # if ('python' or 'Python') in b:
#         #     sum += 1
#         if bool(b) is True:
#             sum+=1
#
#     # for i in a:
#     #     b = re.findall('python', i,re.I)
#     #     if len(b) is not 0:
#     #         sum+=1
#
#     print('the document included python is :')
#     print(a)
#     print('the number of document included python is :' + str(sum))
#
# check_python()

'''-------------2、自动筛选日期和大小的文件--------------'''
# def check(path):
#     # zip_file = (glob.glob('C:/Users/Administrator/Desktop/课题汇总/**/*.zip', recursive=True))  # 把zip文件输出保存成列表
#     zip_file = (glob.glob(path+'\**\*.zip', recursive=True))  # 把zip文件输出保存成列表
#     print(zip_file) #输出路径为 反双斜杠   指具体文件的路径，非文件夹的路径 文件路径=文件夹路径+文件名
#     for zip_path in zip_file:
#         container = os.stat(zip_path).st_size / 1024 / 1024  # 把文件转化成以M为单位
#         container_time = os.stat(zip_path).st_atime  # unxi时间戳
#         # 1577808000 2019-12-31 24h
#         if (container > 100) and (container_time > 1577808000):
#             print('-------')
#             print(zip_path)
#             print('文件容量：', os.stat(zip_path).st_size / 1024 / 1024)
#             print('Unix时间戳：', os.stat(zip_path).st_atime)
#             print('时间：', datetime.datetime.fromtimestamp(os.stat(zip_path).st_atime))
# check(r'C:\Users\Administrator\Desktop\课题汇总') #书写格式 r'文件路径'
# check(r'F:\\')#转义字符

'''3、批量修改文件名并移动'''
import os
import shutil
import time
'''重命名文件要使用 文件夹路径和文件名，使用os.walk（）可以获得'''
# for dirpath, dirnames, files in os.walk(r'C:\Users\Administrator\Desktop\邴栋-毕业课题资料包 - 副本'):
#     for file_name in files:
#         if '.zip' in file_name:
#             print(file_name,dirpath)
#             time_inserted=time.ctime(os.stat(os.path.join(dirpath,file_name)).st_atime)
#             print(type(time_inserted))
#             os.rename(os.path.join(dirpath,file_name),os.path.join(dirpath,'time_inserted'+file_name))
# zip_file_list = (glob.glob(r'C:\Users\Administrator\Desktop\邴栋-毕业课题资料包 - 副本\**\*.zip', recursive=True))  # 把zip文件输出保存成列表
# print(zip_file_list)
# if not os.path.exists('C:\\Users\\Administrator\\Desktop\\邴栋-毕业课题资料包 - 副本\\Abackup'):#创建文件夹
#     os.mkdir(r'C:\Users\Administrator\Desktop\邴栋-毕业课题资料包 - 副本\Abackup')
# for zip_file in zip_file_list:#将zip文件放进去
#     shutil.copy(zip_file,r'C:\Users\Administrator\Desktop\邴栋-毕业课题资料包 - 副本\Abackup')

'''4、自动打包过期文件并移动到备份文件夹'''
import os
import datetime
from time import strftime
import zipfile
# file_list=[]
# for dirpath,dirname,files in os.walk('C:\\Users\\Administrator\\Desktop\\邴栋-毕业课题资料包 - 副本'):
#     for file_name in files:
#         file_path = os.path.join(dirpath,file_name)
#         if datetime.datetime.fromtimestamp(os.stat(file_path).st_mtime) < datetime.datetime(2020, 2, 18, 13, 58, 0,111111):
#             os.rename(file_path,os.path.join(dirpath,time.strftime("%Y-%m-%d")+file_name))
#             print(dirpath, file_name)
#             file_list.append(os.path.join(dirpath,time.strftime("%Y-%m-%d")+file_name))
# print(file_list)
# if not os.path.exists('C:\\Users\\Administrator\\Desktop\\backup'):
#     os.mkdir('C:\\Users\\Administrator\\Desktop\\backup')
# with zipfile.ZipFile('C:\\Users\\Administrator\\Desktop\\backup\\20200518.zip','w')as zipobj:
#     for file in file_list:
#         zipobj.write(file)
# for file in file_list:
#     os.remove(file)

'''5、找到空缺数据位置'''
from openpyxl import load_workbook
workbook=load_workbook(filename='C:\\Users\\Administrator\\Desktop\\离子浓度记录数据.xlsx')
print(workbook.sheetnames)
sheet=workbook['测试数据'] # 通过sheet名称获取表格
space_cell=[]
for row in sheet.rows:
    for cell in row:
        # print(cell.value,cell.coordinate)
        if cell.value== None:  #None代指空白值
            space_cell.append(cell.coordinate)
            # print(cell.coordinate)
print(len(space_cell),space_cell)

'''6、寻找数据并放入新表格'''
from openpyxl import load_workbook
from openpyxl import Workbook

'''新建excel准备存储数据'''
workbook1=Workbook()
sheet1=workbook1.active
sheet1.title=('筛选数据')

'''打开需要筛选表格，筛选需要数据'''
workbook=load_workbook(filename='C:\\Users\\Administrator\\Desktop\\7月下旬入库表.xlsx')
sheet=workbook.active

'''筛选D列，找出列中数值<40.5的数据所在的 行'''
cells=sheet['D']
SelectRowsNumber=[]
for cell in cells:
    if str(cell.value)<str(40.5):
        SelectRowsNumber.append(cell.row)#列表中保存筛选出的‘行’
print(SelectRowsNumber)

'''将筛选出的行，复制到新表 '''
for i in SelectRowsNumber:
    SelectRows = []  #保证不重复
    for cell in sheet[i]:
        print(cell.value)
        SelectRows.append(cell.value)
        print(SelectRows)
    print(SelectRows)
    sheet1.append(SelectRows) #保证每次添加的列表不重复之前存在的内容
    
workbook1.save(filename='C:\\Users\\Administrator\\Desktop\\selset.xlsx')

'''7、省事省力让程序自动美化你的表格'''

from openpyxl import load_workbook

'''打开需要筛选表格，筛选需要数据'''
workbook=load_workbook(filename='C:\\Users\\Administrator\\Desktop\\7月下旬入库表.xlsx')
sheet=workbook['7月下旬入库表']


# '''筛选A列，找出列中数值日期在20180722以前的数据所在的 行'''
def SelsctRow(sheetname,col,number):
    SelectRowsNumber = []
    cells = workbook[sheetname][col]
    for cell in cells:
        # print(cell.value)
        if str(cell.value) < str(number):
           SelectRowsNumber.append(cell.row)
    return SelectRowsNumber

FirstSelectRowsNumber=SelsctRow('7月下旬入库表','A','2018-07-22 00:00:00')
print(FirstSelectRowsNumber)

'''针对筛选出的行 根据E列数值低于41再次筛选 行'''
def TwiceSelectRow(firstSelectRowList,col,number):
    SelectRowsNumber = []
    for i in firstSelectRowList:
        if str(sheet[col + str(i)].value) < str(number):
            SelectRowsNumber.append(sheet[col + str(i)].row)
    return SelectRowsNumber

FinalSelectRowsNumber=TwiceSelectRow(FirstSelectRowsNumber,'E',41)
print(FinalSelectRowsNumber)

'''将最终数据转移至新表'''
workbook.create_sheet('表1')
sheet1=workbook['表1']
def SelectRowToNew_sheet(SelectList,NewSheet):
    for i in SelectList:
        SelectRows = []  # 保证不重复
        for cell in sheet[i]:
            # print(cell.value)
            SelectRows.append(cell.value)
            # print(SelectRows)
        # print(SelectRows)
        NewSheet.append(SelectRows)  # 保证每次添加的列表不重复之前存在的内容
SelectRowToNew_sheet(FinalSelectRowsNumber,sheet1)
'''将最终筛选数据 数值小于40.5 上色'''
from openpyxl.styles import Font,PatternFill
pattern_fill=PatternFill(fill_type='solid',fgColor='FFFF0000')
font=Font(color='FFFFFFFF')
ColorSelectRow=SelsctRow('表1','E','40.5')
print(ColorSelectRow)
for i in ColorSelectRow:
    for cell in sheet1[i]:  #注意，此处是 新表
        # print(cell)
        cell.fill= pattern_fill
        cell.font = font

'''删掉多余行 这个过程运行时间很长 比较鸡肋'''
for i in range(2,1847):
    if i not in FinalSelectRowsNumber:
        sheet.delete_rows(idx=i)
        sheet.insert_rows(idx=i)
workbook.remove(sheet)
sheet1.title=('筛选')

workbook.save(filename='C:\\Users\\Administrator\\Desktop\\7月下旬入库表.xlsx')

import PyPDF2
import pdfplumber
from openpyxl import Workbook
workbook=Workbook()#新建工作簿
sheet=workbook.active#激活工作表
sheet.title='No13data'#
workbook.create_sheet('No14data')
sheet1=workbook['No14data']
with pdfplumber.open('C:\\Users\\Administrator\\Desktop\\网易2019第二季度财报.pdf') as pdf:

    table_page = pdf.pages[13]  # 打开pdf第14页
    table = table_page.extract_table(  # 提取单个表格
        table_settings={  # 提取表格时的设定
            "vertical_strategy": "text",
            "horizontal_strategy": "text"
        }
    )
    print(table)
    for row in table:
        if not (''.join([str(item) for item in row])) == ('NoneNoneNone'):  # 列表推导式 把每一行数据搞成一个字符串 保证非空值时进行下一步操作
            if not (''.join([str(item) for item in row])) == ('NoneNoneNoneNoneNoneNoneNoneNone'):
                new_row = []
                new_row.append(''.join([str(item) if item else '' for item in row[0:5]]))  # 对于每一行前2个数据 如果非空 搞成一个字符串
                # new_row += row[5:]  # 把每一行 后几个数据加进列表里
                for item in row[5:]:
                    if not item == None:
                        new_row.append(item)
                sheet1.append(new_row)

    workbook.save(filename='C:\\Users\\Administrator\\Desktop\\网易2019第二季度财报.xlsx')

'''9、分割合并排序PDF文件'''
from PyPDF2 import PdfFileReader,PdfFileWriter
pdf_reader=PdfFileReader('C:\\Users\\Administrator\\Desktop\\网易2019第二季度财报.pdf')
# print(pdf_reader.getNumPages())
pdf_writer=PdfFileWriter()
for page in range(pdf_reader.getNumPages()):
    if page%2==0:
        pdf_writer.addPage(pdf_reader.getPage(page))
with open('C:\\Users\\Administrator\\Desktop\\reordered.pdf','wb') as out:
    pdf_writer.write(out)
pdf_reader=PdfFileReader('C:\\Users\\Administrator\\Desktop\\reordered.pdf')
pdf_writer=PdfFileWriter()
for page in range(pdf_reader.getNumPages()-1,-1,-1):
    pdf_writer.addPage(pdf_reader.getPage(page))
with open('C:\\Users\\Administrator\\Desktop\\reordered.pdf','wb') as out:
    pdf_writer.write(out)
'''10、加水印并加密pdf'''
from PyPDF2 import PdfFileReader,PdfFileWriter
from copy import copy
watermark_pdf=PdfFileReader('C:\\Users\\Administrator\\Desktop\\watermark.pdf')
watermark_page=watermark_pdf.getPage(0)
pdf_reader=PdfFileReader('C:\\Users\\Administrator\\Desktop\\reordered.pdf')
pdf_writer=PdfFileWriter()
for page in range(pdf_reader.getNumPages()):
    original_page=pdf_reader.getPage(page)
    new_page=copy(watermark_page)
    new_page.mergePage(original_page)
    pdf_writer.addPage(new_page)
pdf_writer.encrypt('1')
with open('C:\\Users\\Administrator\\Desktop\\encrypted.pdf','wb') as out:
    pdf_writer.write(out)

'''11、word文档内某一内容出现的次数'''
from docx import Document
import re
doc=Document('C:\\Users\\Administrator\\Desktop\\编程代码.docx')
num=0
for i in range(len(doc.paragraphs)):#文档内段落数目
    paragraph=doc.paragraphs[i]
    runs=paragraph.runs#具体段落内文字块
    for run in runs:
        if len(re.findall('file',run.text,re.I))>0:# run.text为字符串，利用正则表达式将文字块内‘file’找出来，忽略大小写
            print(run.text)
            print(re.findall('file',run.text,re.I))
            num=num+len(re.findall('file',run.text,re.I))
            print('-----------------')
print('number of ''file'' is '+str(num))