Python自动化操作Excel/Word/PDF的实战指南

pip install openpyxl

from openpyxl import Workbook

# 创建工作簿
wb = Workbook()

# 获取默认激活的工作表
ws = wb.active

# 设置工作表标题
ws.title = "员工数据"

# 创建新工作表
ws1 = wb.create_sheet("部门统计")  # 插入在最后
ws2 = wb.create_sheet("薪资汇总", 0)  # 插入在第一个位置

# 保存工作簿
wb.save("公司数据.xlsx")

from openpyxl import load_workbook

# 加载现有工作簿
wb = load_workbook('公司数据.xlsx')

# 选择工作表
ws = wb['员工数据']

# 写入数据
ws['A1'] = '员工ID'
ws['B1'] = '姓名'
ws['C1'] = '部门'
ws['D1'] = '薪资'

# 批量写入数据
data = [
    [1, '张三', '技术部', 15000],
    [2, '李四', '市场部', 12000],
    [3, '王五', '财务部', 13000],
    [4, '赵六', '技术部', 16000]
]

for row in data:
    ws.append(row)

# 读取数据
for row in ws.iter_rows(min_row=2, max_row=5, values_only=True):
    print(f"员工{row[1]} 在{row[2]}部门，薪资为{row[3]}")

# 保存更改
wb.save('公司数据.xlsx')

from openpyxl.styles import Font, Alignment, PatternFill
from openpyxl.chart import BarChart, Reference

# 设置标题行样式
bold_font = Font(bold=True, size=12)
fill = PatternFill(fill_type="solid", fgColor="DDDDDD")
align_center = Alignment(horizontal="center")

for cell in ws[1]:
    cell.font = bold_font
    cell.fill = fill
    cell.alignment = align_center

# 添加公式计算平均薪资
ws['E1'] = '平均薪资'
ws['E2'] = '=AVERAGE(D2:D5)'

# 创建图表
chart = BarChart()
chart.title = "部门薪资对比"
chart.x_axis.title = "员工"
chart.y_axis.title = "薪资"

data = Reference(ws, min_col=4, min_row=1, max_row=5)
categories = Reference(ws, min_col=2, min_row=2, max_row=5)
chart.add_data(data, titles_from_data=True)
chart.set_categories(categories)

ws.add_chart(chart, "G2")

wb.save('公司数据_增强.xlsx')

pip install python-docx

from docx import Document
from docx.shared import Inches, Pt
from docx.enum.text import WD_ALIGN_PARAGRAPH

# 创建新文档
doc = Document()

# 添加标题
doc.add_heading('公司季度报告', 0)

# 添加段落
p = doc.add_paragraph('本季度公司业绩表现良好，各部门均完成了既定目标。')
p.add_run('特别是技术部门').bold = True
p.add_run('，超额完成了项目开发任务。')

# 添加二级标题
doc.add_heading('部门业绩详情', level=2)

# 添加表格
table = doc.add_table(rows=1, cols=3)
table.style = 'Table Grid'

# 设置表头
hdr_cells = table.rows[0].cells
hdr_cells[0].text = '部门'
hdr_cells[1].text = '目标完成率'
hdr_cells[2].text = '同比增长'

# 添加数据
data = [
    ['技术部', '120%', '15%'],
    ['市场部', '95%', '8%'],
    ['财务部', '100%', '5%']
]

for dept, rate, growth in data:
    row_cells = table.add_row().cells
    row_cells[0].text = dept
    row_cells[1].text = rate
    row_cells[2].text = growth

# 添加分页符
doc.add_page_break()

# 添加另一个章节
doc.add_heading('下一步计划', level=2)
doc.add_paragraph(
    '1. 扩大技术团队规模', style='List Number'
)
doc.add_paragraph(
    '2. 开拓新市场', style='List Number'
)
doc.add_paragraph(
    '3. 优化财务管理流程', style='List Number'
)

# 保存文档
doc.save('季度报告.docx')

from docx import Document

# 打开现有文档
doc = Document('季度报告.docx')

# 读取内容
full_text = []
for paragraph in doc.paragraphs:
    full_text.append(paragraph.text)

print('\n'.join(full_text))

# 修改内容
for paragraph in doc.paragraphs:
    if '技术部门' in paragraph.text:
        paragraph.text = paragraph.text.replace('技术部门', '研发中心')

# 保存修改后的文档
doc.save('季度报告_修改版.docx')

import PyPDF2

def merge_pdfs(paths, output):
    pdf_writer = PyPDF2.PdfWriter()
    
    for path in paths:
        pdf_reader = PyPDF2.PdfReader(path)
        for page in range(len(pdf_reader.pages)):
            pdf_writer.add_page(pdf_reader.pages[page])
    
    with open(output, 'wb') as out:
        pdf_writer.write(out)

# 使用示例
merge_pdfs(['file1.pdf', 'file2.pdf'], 'merged.pdf')

from pdfminer.high_level import extract_text

text = extract_text('document.pdf')
print(text)

from openpyxl import load_workbook
from docx import Document
import pdfkit

# 1. 从Excel读取数据
wb = load_workbook('公司数据.xlsx')
ws = wb.active

dept_data = {}
for row in ws.iter_rows(min_row=2, values_only=True):
    dept = row[2]
    salary = row[3]
    if dept not in dept_data:
        dept_data[dept] = {
            'count': 0,
            'total_salary': 0,
            'max_salary': 0
        }
    
    dept_data[dept]['count'] += 1
    dept_data[dept]['total_salary'] += salary
    if salary > dept_data[dept]['max_salary']:
        dept_data[dept]['max_salary'] = salary

# 计算平均薪资
for dept in dept_data:
    dept_data[dept]['avg_salary'] = dept_data[dept]['total_salary'] / dept_data[dept]['count']

# 2. 生成Word报告
doc = Document()
doc.add_heading('公司部门统计报告', 0)

# 添加摘要段落
doc.add_paragraph(
    f本报告基于员工数据统计分析，共涵盖{len(dept_data)}个部门。'
)

# 添加表格
table = doc.add_table(rows=1, cols=4)
table.style = 'Table Grid'

# 表头
hdr_cells = table.rows[0].cells
hdr_cells[0].text = '部门'
hdr_cells[1].text = '员工数'
hdr_cells[2].text = '平均薪资'
hdr_cells[3].text = '最高薪资'

# 表格数据
for dept, data in dept_data.items():
    row_cells = table.add_row().cells
    row_cells[0].text = dept
    row_cells[1].text = str(data['count'])
    row_cells[2].text = f"{data['avg_salary']:.2f}"
    row_cells[3].text = str(data['max_salary'])

doc.add_paragraph('\n报告生成时间：2023年11月1日')
doc.save('部门统计报告.docx')

# 3. 转换为PDF
# 需要先安装wkhtmltopdf并设置路径
# path_wkhtmltopdf = r'C:\Program Files\wkhtmltopdf\bin\wkhtmltopdf.exe'
# config = pdfkit.configuration(wkhtmltopdf=path_wkhtmltopdf)
# pdfkit.from_file('部门统计报告.docx', '部门统计报告.pdf')  # 注意：这种方法需要docx能正确转换为HTML

print("报告生成完成！")