Python中操作PDF文件的常用方法

pip install PyPDF2
pip install pdfminer.six
pip install reportlab

import PyPDF2
 
# 创建一个 PDF 合并器对象
pdf_merger = PyPDF2.PdfMerger()
 
# 需要合并的 PDF 文件列表
pdf_files = ['file1.pdf', 'file2.pdf', 'file3.pdf']
 
# 合并 PDF 文件
for pdf in pdf_files:
    pdf_merger.append(pdf)
 
# 输出合并后的 PDF 文件
pdf_merger.write('merged_output.pdf')
pdf_merger.close()
 
print("PDF 文件合并完成！")

import PyPDF2
 
# 打开 PDF 文件
with open('sample.pdf', 'rb') as file:
    reader = PyPDF2.PdfReader(file)
 
    # 获取 PDF 文件的页数
    total_pages = len(reader.pages)
 
    # 创建一个 PDF 写入器对象
    writer = PyPDF2.PdfWriter()
 
    # 拆分为每一页一个 PDF 文件
    for page_num in range(total_pages):
        writer.add_page(reader.pages[page_num])
 
        # 写入到新的 PDF 文件
        with open(f'page_{page_num + 1}.pdf', 'wb') as output_file:
            writer.write(output_file)
 
    print("PDF 文件拆分完成！")

import PyPDF2
 
# 打开 PDF 文件
with open('sample.pdf', 'rb') as file:
    reader = PyPDF2.PdfReader(file)
    text = ""
    
    # 提取所有页的文本
    for page_num in range(len(reader.pages)):
        page = reader.pages[page_num]
        text += page.extract_text()
 
print("PDF 文件内容：")
print(text)

from pdfminer.high_level import extract_text
 
# 提取 PDF 文件中的文本
text = extract_text('sample.pdf')
 
print("提取的文本内容：")
print(text)

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
 
# 创建一个 PDF 文件并绘制文本
def create_pdf(output_filename):
    c = canvas.Canvas(output_filename, pagesize=letter)
    c.drawString(100, 750, "Hello, this is a simple PDF created with ReportLab!")
    c.save()
 
# 调用函数生成 PDF 文件
create_pdf("output.pdf")
print("PDF 文件创建完成！")

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
 
def create_pdf_with_image(output_filename):
    c = canvas.Canvas(output_filename, pagesize=letter)
    c.drawString(100, 750, "Here is an image below:")
    
    # 添加图像
    c.drawImage("image.jpg", 100, 500, width=200, height=150)  # 图像位置和大小
    
    c.save()
 
create_pdf_with_image("pdf_with_image.pdf")
print("PDF 文件（带图像）创建完成！")

import fitz  # PyMuPDF
 
# 打开 PDF 文件
doc = fitz.open('sample.pdf')
 
# 提取所有页面的文本
text = ""
for page_num in range(len(doc)):
    page = doc.load_page(page_num)
    text += page.get_text()
 
print("PDF 文件的内容：")
print(text)

import PyPDF2
 
# 打开 PDF 文件
with open('sample.pdf', 'rb') as file:
    reader = PyPDF2.PdfReader(file)
    writer = PyPDF2.PdfWriter()
    
    # 将 PDF 中的所有页面添加到 writer 对象中
    for page in reader.pages:
        writer.add_page(page)
    
    # 设置密码
    password = "your_password"
    writer.encrypt(password)
    
    # 写入加密后的文件
    with open('encrypted_sample.pdf', 'wb') as encrypted_file:
        writer.write(encrypted_file)
 
print("PDF 文件加密完成！")

import PyPDF2
 
# 打开加密的 PDF 文件
with open('encrypted_sample.pdf', 'rb') as file:
    reader = PyPDF2.PdfReader(file)
    
    # 解密 PDF 文件
    password = "your_password"
    if reader.is_encrypted:
        reader.decrypt(password)
    
    # 创建一个 PDF 写入器对象
    writer = PyPDF2.PdfWriter()
    
    # 将解密后的页面添加到写入器中
    for page in reader.pages:
        writer.add_page(page)
    
    # 输出解密后的 PDF 文件
    with open('decrypted_sample.pdf', 'wb') as decrypted_file:
        writer.write(decrypted_file)
 
print("PDF 文件解密完成！")