Python 实现自动化办公：文件、文档与邮件操作指南

Python 实现自动化办公：文件、文档与邮件操作指南 | 极客日志

from shutil import copy

from shutil import copyfile

from shutil import move

# coding:utf-8
import os
from shutil import move

# 获取来源文件路径
path = os.path.join(os.getcwd(), 'xxx.txt')
# 获取目标地址
target = os.path.join(os.getcwd(), 'test1')
# 将 xxx.txt 文件移动到 test1 目录下并重命名
move(path, target+'/abc.txt')

import os

from shutil import make_archive

from shutil import unpack_archive

from glob import glob

# coding:utf-8
import os
from glob import glob

path = os.path.join(os.getcwd(), '*')
final_result = []

def search(path, target):
    result = glob(path)
    for data in result:
        if os.path.isdir(data):  # 如果是一个目录
            _path = os.path.join(data, '*')
            print('%s is filepath' % data)
            search(_path, target)  # 继续往下找
        else:  # 如果不是一个目录
            if target in data:
                final_result.append(data)
    return final_result

if __name__ == '__main__':
    result = search(path, target='abc.txt')
    print(result)

# coding:utf-8
import os
from glob import glob

path = os.path.join(os.getcwd(), '*')
final_result = []

def search(path, target):
    result = glob(path)
    for data in result:
        if os.path.isdir(data):  # 如果是一个目录
            _path = os.path.join(data, '*')
            print('%s is filepath' % data)
            search(_path, target)
        else:  # 如果不是一个目录
            f = open(data, 'r', encoding='utf-8')
            try:
                content = f.read()
                if target in content:
                    final_result.append(data)
            except:
                print('data read failed: %s' % data)
                continue
            finally:
                f.close()
    return final_result

if __name__ == '__main__':
    result = search(path, target='YiQie99903')
    print(result)

# coding:utf-8
import glob
import hashlib
import os

data = {}

def clear(path):
    result = glob.glob(path)
    for _data in result:
        if os.path.isdir(_data):
            _path = os.path.join(_data, '*')
            clear(_path)
        else:
            name = os.path.split(_data)[-1]
            if_byte = False
            if 'zip' in name:
                if_byte = True
                f = open(_data, 'rb')
            else:
                f = open(_data, 'r', encoding='utf-8')
            
            content = f.read()
            f.close()
            
            if if_byte:
                hash_content_obj = hashlib.md5(content)
            else:
                hash_content_obj = hashlib.md5(content.encode('utf-8'))
            
            hash_content = hash_content_obj.hexdigest()
            
            if name in data:
                sub_data = data[name]
                is_delete = False
                for k, v in sub_data.items():
                    if v == hash_content:
                        os.remove(_data)
                        print('%s will delete' % _data)
                        is_delete = True
                if not is_delete:
                    data[name][_data] = hash_content
            else:
                data[name] = {
                    _data: hash_content
                }

if __name__ == '__main__':
    path = os.path.join(os.getcwd(), '*')
    clear(path)
    print(path)
    for k, v in data.items():
        print(k)

# coding:utf-8
import glob
import shutil
import os

def update_name(path):
    result = glob.glob(path)
    for index, data in enumerate(result):
        if os.path.isdir(data):
            _path = os.path.join(data, '*')
            update_name(_path)
        else:
            path_list = os.path.split(data)
            name = path_list[-1]
            new_name = '%s_%s' % (index, name)
            new_data = os.path.join(path_list[0], new_name)
            shutil.move(data, new_data)

if __name__ == '__main__':
    path = os.path.join(os.getcwd(), '*')
    update_name(path)

from shutil import copytree

from shutil import rmtree

from shutil import move

move(path, target+'/test4') # 移动并重命名

pip install python-docx

from docx import Document

# coding:utf-8
from docx import Document

# docx 只支持 .docx 这样的格式 如果是 doc 请转换成 docx
doc = Document('test.docx')
for p in doc.paragraphs:
    print(p.text)

# coding:utf-8
from docx import Document

doc = Document('test.docx')
for t in doc.tables:
    for row in t.rows:
        _row_str = ''
        for cell in row.cells:
            _row_str += cell.text + ','
        print(_row_str)

# coding:utf-8
import glob
from docx import Document

class ReadDoc(object):
    def __init__(self, path):
        self.doc = Document(path)
        self.p_text = ''
        self.table_text = ''
        self.get_para()
        self.get_table()

    def get_para(self):
        for p in self.doc.paragraphs:
            self.p_text += p.text + '\n'

    def get_table(self):
        for table in self.doc.tables:
            for row in table.rows:
                _cell_str = ''
                for cell in row.cells:
                    _cell_str += cell.text + ','
                self.table_text += _cell_str + '\n'

def search_word(path, targets):
    result = glob.glob(path)
    final_result = []
    for i in result:
        isuse = True
        if os.path.isfile(i):
            if i.endswith('.docx'):
                doc = ReadDoc(i)
                p_text = doc.p_text
                t_text = doc.table_text
                all_text = p_text + t_text
                for target in targets:
                    if target not in all_text:
                        isuse = False
                        break
                if not isuse:
                    continue
                final_result.append(i)
    return final_result

if __name__ == '__main__':
    path = os.path.join(os.getcwd(), '*')
    res = search_word(path, ['Java', '本科'])
    print(res)

# coding:utf-8
from docx import Document

doc = Document()
# 添加标题 参数：标题内容，标题样式等级
title = doc.add_heading('My title', 0)
# 追加内容
title.add_run('\n Sample Text')
# 生成 word 文档
doc.save('test.docx')

# coding:utf-8
from docx import Document

doc = Document()
title = doc.add_heading('My title', 0)
p = doc.add_paragraph('欢迎来到这里学习 python')
p.add_run('\nSample Content')
doc.save('test.docx')

# coding:utf-8
from docx import Document
from docx.shared import Inches

doc = Document()
title = doc.add_heading('My title', 0)
image = doc.add_picture('这是一张图片.png', width=Inches(5), height=Inches(5))
doc.save('test.docx')

# coding:utf-8
from docx import Document
from docx.shared import Inches

doc = Document()
title = doc.add_heading('My title', 0)
# 表格内容
title_list = ['name', 'age', 'sex']
# 生成表格  参数：行数 列数
table = doc.add_table(rows=1, cols=3)
# 插入参数
title_cells = table.rows[0].cells
title_cells[0].text = title_list[0]
title_cells[1].text = title_list[1]
title_cells[2].text = title_list[2]
# 追加内容
data = [
    ('一切', '2', '男'),
    ('总会', '2', '男'),
    ('归于平淡', '4', '男')
]
for d in data:
    row_cells = table.add_row().cells
    row_cells[0].text = d[0]
    row_cells[1].text = d[1]
    row_cells[2].text = d[2]
doc.save('test.docx')

# coding:utf-8
from docx import Document

doc = Document()
title = doc.add_heading('My title', 0)
doc.add_page_break()
title2 = doc.add_heading('My title2', 0)
doc.save('test.docx')

# coding:utf-8
from docx import Document
from docx.shared import RGBColor, Pt

doc = Document()
style = doc.styles['Normal']
style.font.name = '微软雅黑'
style.font.color.rgb = RGBColor(255, 0, 0)
style.font.size = Pt(16)

# coding:utf-8
from docx import Document
from docx.shared import RGBColor, Pt
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT

doc = Document()
title = doc.add_heading('My title', 0)
title.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER
title.style.font.size = Pt(50)
_t = title.add_run('\n Sample Text')
_t.italic = True
_t.bold = True

p = doc.add_paragraph('欢迎来到这里学习 python')
p.add_run('\nSample Content').italic = True
p.alignment = WD_PARAGRAPH_ALIGNMENT.RIGHT
doc.save('test.docx')

# coding:utf-8
from docx import Document
from docx.shared import RGBColor, Pt, Inches
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT, WD_ALIGN_PARAGRAPH

doc = Document()
title = doc.add_heading('My title', 0)
title.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER
title.style.font.size = Pt(50)

p = doc.add_paragraph()
p.alignment = WD_ALIGN_PARAGRAPH.RIGHT
_p = p.add_run()
image = _p.add_picture('这是一张图片.png', width=Inches(3), height=Inches(2))
doc.save('test.docx')

for i in doc.styles:
    if i.type == doc.styles.WD_STYLE_TYPE.TABLE:
        print(i.name)

pip install pdfkit

pdfkit.from_url('网址','保存的路径')

# coding:utf-8
import pdfkit
config = pdfkit.configuration(wkhtmltopdf=r"D:\installPath\wkhtmltopdf\bin\wkhtmltopdf.exe")
pdfkit.from_url('https://www.baidu.com', 'baidu.pdf', configuration=config)

# coding:utf-8
import pdfkit
config = pdfkit.configuration(wkhtmltopdf=r"D:\installPath\wkhtmltopdf\bin\wkhtmltopdf.exe")
htmlStr = """<html>
    <head>
        <meta charset="utf-8" />
    </head>
    <body>
        <h1>Sample Title</h1>
    </body>
</html>"""
pdfkit.from_string(htmlStr, 'sample.pdf', configuration=config)

pip install pydocx

# coding:utf-8
import pdfkit
from pydocx import PyDocX

config = pdfkit.configuration(wkhtmltopdf=r"D:\installPath\wkhtmltopdf\bin\wkhtmltopdf.exe")
html = PyDocX.to_html('resume.docx')
f = open('html1.html', 'w')
f.write(html)
f.close()
pdfkit.from_file('html1.html', 'resume.pdf', configuration=config)

html2 = PyDocX.to_html('resume2.docx')
pdfkit.from_string(html2, 'resume2.pdf', configuration=config)

pip install -i https://pypi.tuna.tsinghua.edu.cn/simple xlrd==1.2.0

函数名	说明
book.sheet_by_name()	按照工作薄名称获取
book.sheet_by_index()	按照索引获取
book.sheets()	获取所有工作薄列表

# coding:utf-8
import xlrd

excel = xlrd.open_workbook('user_detail.xlsx')
# 按照工作薄名称获取
book = excel.sheet_by_name('用户明细')
print(book.name)
# 按照索引获取
book = excel.sheet_by_index(0)
print(book.name)
# 获取所有的工作簿列表
for i in excel.sheets():
    print(i.name)

函数名	说明
sheet.nrows	返回总行数
sheet.ncols	返回总列数
sheet.get_rows()	返回每行内容列表

# coding:utf-8
import xlrd

excel = xlrd.open_workbook('user_detail.xlsx')
book = excel.sheet_by_name('用户明细')
print(book.name)
print('%s 行' % book.nrows)
print('%s 列' % book.ncols)
for i in book.get_rows():
    content = []
    for j in i:
        content.append(j.value)
    print(content)

pip install -i https://pypi.tuna.tsinghua.edu.cn/simple xlsxwriter

函数名	说明	参数
xlsxwriter.Workbook()	生成 excel 对象	Excel 文件名
add_worksheet()	添加工作薄	工作薄名称
sheet.write()	书写内容	行索引，列索引，内容
book.close()	关闭 excel 对象	无

import xlrd
import xlsxwriter

def read():
    result = []
    excel = xlrd.open_workbook('user_detail.xlsx')
    book = excel.sheet_by_name('用户明细')
    for i in book.get_rows():
        content = []
        for j in i:
            content.append(j.value)
        result.append(content)
    return result

def write(content):
    excel = xlsxwriter.Workbook('test.xlsx')
    book = excel.add_worksheet("test")
    for index, data in enumerate(content):
        for sub_index, sub_date in enumerate(data):
            book.write(index, sub_index, sub_date)
    excel.close()

if __name__ == '__main__':
    result = read()
    write(result)

函数名	说明	参数
add_chart()	创建图表对象	{type: 样式}
add_series()	定义需要展示的数据	字典
set_title()	定义图表 title	字符串

参数	说明	值
categories	展示的标题	=Sheet1!1:4
values	展示的数据	=Sheet1!1:4
name	表名

样式名	说明
area	区域样式表
bar	条形样式
column	柱状样式
line	线条样式
pie	饼图样式
doughnut	圆环样式
scatter	散点样式
stock	库存样式
radar	雷达样式

import xlsxwriter

excel = xlsxwriter.Workbook('test.xlsx')
book = excel.add_worksheet('用户角色')
data = [
    ['社区成员', '社区之星', '社区管理员', '区长'],
    [20, 23, 2, 1]
]
book.write_column('A1', data[0])
book.write_column('B1', data[1])
chart = excel.add_chart({'type': 'pie'})
chart.add_series({
    'categories': '=用户角色!$A1:$A4',
    'values': '=用户角色!$B1:$B4',
    'name': '角色占比'
})
chart.set_title({
    'name': '角色占比图表'
})
book.insert_chart('A7', chart)
excel.close()

pip install -i https://pypi.tuna.tsinghua.edu.cn/simple python-pptx

import pptx

p = pptx.Presentation()
layout = p.slide_layouts[7]
slide = p.slides.add_slide(layout)
p.save('test.ppt')

import pptx
from pptx.dml.color import RGBColor
from pptx.enum.text import PP_PARAGRAPH_ALIGNMENT
from pptx.util import Pt

p = pptx.Presentation()
layout = p.slide_layouts[1]
slide = p.slides.add_slide(layout)

title = slide.placeholders[0]
title.text = 'PPT 自动化'

placeholder = slide.placeholders[1]
placeholder.text = 'Sample Text\nSample Content'

placeholder1 = placeholder.text_frame.add_paragraph()
placeholder1.text = '点赞'
placeholder1.font.bold = True
placeholder1.font.italic = True
placeholder1.font.size = Pt(16)
placeholder1.font.underline = True
placeholder1.alignment = PP_PARAGRAPH_ALIGNMENT.CENTER

placeholder2 = placeholder.text_frame.add_paragraph()
placeholder2.text = '转发'
placeholder2.font.size = Pt(32)
placeholder2.alignment = PP_PARAGRAPH_ALIGNMENT.RIGHT
placeholder2.font.color.rgb = RGBColor(255, 0, 0)

p.save('test.ppt')

import pptx
from pptx.util import Inches

p = pptx.Presentation()
layout = p.slide_layouts[1]
slide = p.slides.add_slide(layout)

title = slide.placeholders[0]
title.text = 'PPT 自动化'

placeholder = slide.placeholders[1]
placeholder.text = 'Sample Text'

layout = p.slide_layouts[1]
slide = p.slides.add_slide(layout)
title = slide.placeholders[0]
title.text = '第二页'

rows = 10
cols = 2
left = top = Inches(2)
width = Inches(6.0)
height = Inches(1.0)

table = slide.shapes.add_table(rows, cols, left, top, width, height).table
for index, _ in enumerate(range(rows)):
    for sub_index in range(cols):
        table.cell(index, sub_index).text = '%s:%s' % (index, sub_index)

layout = p.slide_layouts[6]
slide = p.slides.add_slide(layout)
image = slide.shapes.add_picture(
    image_file='C:\\Users\\Desktop\\cover.jpg',
    left=Inches(1),
    top=Inches(1),
    width=Inches(6),
    height=Inches(6)
)
p.save('test.ppt')

# coding:utf-8
import pptx

p = pptx.Presentation('test.ppt')
for slide in p.slides:
    for shape in slide.shapes:
        if shape.has_text_frame:
            print(shape.text_frame.text)
        if shape.has_table:
            for cell in shape.table.iter_cells():
                print(cell.text)

# coding:utf-8
import smtplib
from email.header import Header
from email.mime.text import MIMEText

mail_host = 'smtp 服务器'
mail_user = '你的邮箱'
mail_pass = '密钥'

sender = '发送人的邮箱'
receivers = ['接收者的邮箱']

message = MIMEText('这是一个测试', 'plain', 'utf-8')
message['From'] = Header(sender)
message['Subject'] = Header('python 脚本测试', 'utf-8')

try:
    smtpobj = smtplib.SMTP()
    smtpobj.connect(mail_host, 25)
    smtpobj.login(mail_user, mail_pass)
    smtpobj.sendmail(sender, receivers, message.as_string())
except smtplib.SMTPException as e:
    print('error: %s' % e)

# coding:utf-8
import smtplib
from email.header import Header
from email.mime.text import MIMEText

mail_host = 'smtp 服务器'
mail_user = '你的邮箱'
mail_pass = '密钥'

sender = '发送人的邮箱'
receivers = ['接收者的邮箱']

message = MIMEText('<p style="color:red;">这是一个测试</p>', 'html', 'utf-8')
message['From'] = Header(sender)
message['Subject'] = Header('python 脚本测试', 'utf-8')

try:
    smtpobj = smtplib.SMTP()
    smtpobj.connect(mail_host, 25)
    smtpobj.login(mail_user, mail_pass)
    smtpobj.sendmail(sender, receivers, message.as_string())
except smtplib.SMTPException as e:
    print('error: %s' % e)

# coding:utf-8
import smtplib
from email.header import Header
from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText

mail_host = 'smtp 服务器'
mail_user = '你的邮箱'
mail_pass = '密钥'

sender = '发送人的邮箱'
receivers = ['接收者的邮箱']

message = MIMEMultipart()
message['From'] = Header(sender)
message['Subject'] = Header('python 脚本测试', 'utf-8')

attr = MIMEText(open('test.ppt', 'rb').read(), 'base64', 'utf-8')
attr['Content-Type'] = 'application/octet-stream'
attr['Content-Disposition'] = 'attachment;filename="test.ppt"'
message.attach(attr)
message.attach(MIMEText('这是一个带附件的邮件', 'plain', 'utf-8'))

try:
    smtpObj = smtplib.SMTP()
    smtpObj.connect(mail_host, 25)
    smtpObj.login(mail_user, mail_pass)
    smtpObj.sendmail(sender, receivers, message.as_string())
except smtplib.SMTPException as e:
    print('error: %s' % e)

pip install schedule

时间格式	描述
@once	在程序启动时运行一次
@hourly	每小时运行一次
@daily	每天运行一次
@weekly	每周运行一次
@monthly	每月运行一次
@yearly	每年运行一次
@cron	使用 crontab 格式
datetime object	使用 Python 的 datetime 对象

# coding:utf-8
import smtplib
import time
from email.header import Header
from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText
import schedule

mail_host = 'smtp 服务器'
mail_user = '你的邮箱'
mail_pass = '密钥'

sender = '发送人的邮箱'
receivers = ['接收者的邮箱']

message = MIMEMultipart()
message['From'] = Header(sender)
message['Subject'] = Header('python 脚本测试', 'utf-8')

attr = MIMEText(open('test.ppt', 'rb').read(), 'base64', 'utf-8')
attr['Content-Type'] = 'application/octet-stream'
attr['Content-Disposition'] = 'attachment;filename="test.ppt"'
message.attach(attr)
message.attach(MIMEText('这是一个带附件的邮件', 'plain', 'utf-8'))

def send():
    try:
        smtpObj = smtplib.SMTP()
        smtpObj.connect(mail_host, 25)
        smtpObj.login(mail_user, mail_pass)
        smtpObj.sendmail(sender, receivers, message.as_string())
    except smtplib.SMTPException as e:
        print('error: %s' % e)

if __name__ == '__main__':
    schedule.every().monday.at("00:00").do(send)
    while True:
        schedule.run_pending()
        time.sleep(60)

if __name__ == '__main__':
    schedule.every(10).seconds.do(send)
    while True:
        schedule.run_pending()
        time.sleep(60)

Python 实现自动化办公：文件、文档与邮件操作指南

前言

1. 普通文件自动化管理

1.1 文件的复制

1.2 文件内容的复制

1.3 文件的移动（裁剪）

1.4 文件的删除

1.5 文件的压缩与解压缩

1.6 文件的查找

1.7 查找含有指定内容的文件

1.8 清理重复的文件

1.9 批量修改目录中的文件名称

2. 文件夹的自动化管理

2.1 文件夹的复制

2.2 文件夹的删除

2.3 文件夹的移动

3. Word 自动化 – 高效做文档

3.1 读取 Word 文档

3.2 小练习：简历筛选

3.3 生成 Word 文档

3.3.1 标题

3.3.2 段落

3.3.3 图片

3.3.4 表格

3.3.5 分页

3.4 设置 Word 文档样式

3.4.1 全局样式

3.4.2 文本样式

3.4.3 图片样式

3.4.4 表格样式

3.5 WORD 转 PDF

3.5.1 网址 转 PDF

3.5.2 HTML 字符串 转 PDF

3.5.3 WORD 转 PDF

4. Excel 自动化

4.1 获取 Excel 对象

4.1.1 获取工作簿

4.1.2 读取工作簿内容

4.2 写入 Excel 数据

4.2.1 常用函数

4.2.2 代码书写

4.3 Excel 写入图表

4.3.1 常用函数

4.3.2 图表样式

4.3.3 代码书写

5. PPT 自动化

5.1 创建 PPT

5.2 段落的使用

5.3 插入表格 + 图片

5.4 读取 PPT

6. 邮件的操作

6.1 发送邮件的常规流程

6.2 认识邮件协议

6.3 邮箱服务商开通 SMTP 服务

6.4 普通邮件发送

6.5 HTML 邮件发送

6.6 带附件的邮件

6.7 定时发送邮件

6.8 为什么要使用 while True 循环？

6.9 踩的一个坑

微信扫一扫，关注极客日志

更多推荐文章

相关免费在线工具

3.5.1 网址转 PDF

3.5.2 HTML 字符串转 PDF