使用Python进行PDF文档处理的常见操作

pip install PyPDF2 pdfplumber reportlab

import PyPDF2

# 打开 PDF 文件
with open('sample.pdf', 'rb') as file:
    reader = PyPDF2.PdfReader(file)
    
    # 提取每一页的文本
    for page_num in range(len(reader.pages)):
        page = reader.pages[page_num]
        text = page.extract_text()
        print(f"第 {page_num + 1} 页的文本:\n{text}")

import pdfplumber

# 打开 PDF 文件
with pdfplumber.open('sample.pdf') as pdf:
    for page_num in range(len(pdf.pages)):
        page = pdf.pages[page_num]
        text = page.extract_text()
        print(f"第 {page_num + 1} 页的文本:\n{text}")

import PyPDF2

pdf_files = ['file1.pdf', 'file2.pdf', 'file3.pdf']
merger = PyPDF2.PdfMerger()

for pdf in pdf_files:
    merger.append(pdf)

# 保存合并后的 PDF 文件
with open('merged_output.pdf', 'wb') as output_file:
    merger.write(output_file)

import PyPDF2

# 打开 PDF 文件
with open('sample.pdf', 'rb') as file:
    reader = PyPDF2.PdfReader(file)
    
    # 按页拆分并保存
    for page_num in range(len(reader.pages)):
        writer = PyPDF2.PdfWriter()
        writer.add_page(reader.pages[page_num])
        
        with open(f'split_page_{page_num + 1}.pdf', 'wb') as output_file:
            writer.write(output_file)

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

# 创建 PDF 文件
c = canvas.Canvas("output.pdf", pagesize=letter)
c.drawString(100, 750, "Hello, this is a PDF created with ReportLab!")

# 创建矩形
c.rect(100, 700, 400, 100)

# 保存 PDF
c.showPage()
c.save()

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("output_with_image.pdf", pagesize=letter)
c.drawString(100, 750, "This is a PDF with an image:")

# 插入图片
c.drawImage("image.png", 100, 600, width=200, height=150)

c.showPage()
c.save()

import pdfplumber

# 打开 PDF 文件
with pdfplumber.open('table_sample.pdf') as pdf:
    first_page = pdf.pages[0]
    
    # 提取表格数据
    tables = first_page.extract_table()
    
    # 打印提取到的表格数据
    for row in tables:
        print(row)

import PyPDF2

# 打开 PDF 文件
with open('sample.pdf', 'rb') as file:
    reader = PyPDF2.PdfReader(file)
    writer = PyPDF2.PdfWriter()

    for page_num in range(len(reader.pages)):
        writer.add_page(reader.pages[page_num])

    # 设置密码
    writer.encrypt(user_password='user123', owner_password='owner123')

    with open('encrypted_output.pdf', 'wb') as output_file:
        writer.write(output_file)

import PyPDF2

# 打开加密的 PDF 文件
with open('encrypted_output.pdf', 'rb') as file:
    reader = PyPDF2.PdfReader(file)
    
    # 提供密码
    reader.decrypt('user123')
    
    # 提取文本
    for page_num in range(len(reader.pages)):
        page = reader.pages[page_num]
        print(page.extract_text())

import PyPDF2

# 打开 PDF 文件
with open('sample.pdf', 'rb') as file:
    reader = PyPDF2.PdfReader(file)
    writer = PyPDF2.PdfWriter()
    
    # 旋转每页 90 度
    for page in reader.pages:
        page.rotate_clockwise(90)
        writer.add_page(page)
    
    # 保存旋转后的 PDF 文件
    with open('rotated_output.pdf', 'wb') as output_file:
        writer.write(output_file)