Python删除指定PDF页面的完整方案

from PyPDF2 import PdfReader, PdfWriter

def delete_page_pypdf2(input_path, output_path, page_to_delete):
    reader = PdfReader(input_path)
    writer = PdfWriter()
    
    for page_num in range(len(reader.pages)):
        if page_num != page_to_delete:
            writer.add_page(reader.pages[page_num])
    
    with open(output_path, "wb") as f:
        writer.write(f)

# 示例：删除input.pdf的第2页（索引从0开始）
delete_page_pypdf2("input.pdf", "output_pypdf2.pdf", 1)

from spire.pdf import PdfDocument

def delete_page_spire(input_path, output_path, page_to_delete):
    doc = PdfDocument()
    doc.load_from_file(input_path)
    
    if 0 <= page_to_delete < doc.pages.count:
        doc.pages.remove_at(page_to_delete)
        doc.save_to_file(output_path)
    else:
        print("Invalid page index")
    
    doc.close()

# 示例：删除input.pdf的第3页
delete_page_spire("input.pdf", "output_spire.pdf", 2)

import fitz  # PyMuPDF的别名

def delete_page_pymupdf(input_path, output_path, page_to_delete):
    doc = fitz.open(input_path)
    
    if 0 <= page_to_delete < len(doc):
        doc.delete_page(page_to_delete)
        doc.save(output_path)
    else:
        print("Invalid page index")
    
    doc.close()

# 示例：删除input.pdf的第1页
delete_page_pymupdf("input.pdf", "output_pymupdf.pdf", 0)

# PyPDF2实现
def delete_multiple_pages(input_path, output_path, pages_to_delete):
    reader = PdfReader(input_path)
    writer = PdfWriter()
    pages_to_keep = [i for i in range(len(reader.pages)) if i not in pages_to_delete]
    
    for page_num in pages_to_keep:
        writer.add_page(reader.pages[page_num])
    
    with open(output_path, "wb") as f:
        writer.write(f)

# 删除第1、3、5页（索引0,2,4）
delete_multiple_pages("input.pdf", "output_multi.pdf", [0, 2, 4])

# Spire.PDF实现
def delete_page_range(input_path, output_path, start_page, end_page):
    doc = PdfDocument()
    doc.load_from_file(input_path)
    
    # 验证范围有效性
    if start_page < 0 or end_page >= doc.pages.count or start_page > end_page:
        print("Invalid page range")
        return
    
    # 从后向前删除避免索引变化
    for page_num in range(end_page, start_page - 1, -1):
        doc.pages.remove_at(page_num)
    
    doc.save_to_file(output_path)
    doc.close()

# 删除第2-4页（索引1-3）
delete_page_range("input.pdf", "output_range.pdf", 1, 3)

# PyMuPDF实现
def delete_blank_pages(input_path, output_path):
    doc = fitz.open(input_path)
    pages_to_delete = []
    
    for i in range(len(doc)):
        page = doc[i]
        text = page.get_text("text")
        if not text.strip():  # 判断是否为空白页
            pages_to_delete.append(i)
    
    # 从后向前删除
    for page_num in sorted(pages_to_delete, reverse=True):
        doc.delete_page(page_num)
    
    doc.save(output_path)
    doc.close()

# 示例：删除input.pdf中的所有空白页
delete_blank_pages("input.pdf", "output_no_blank.pdf")

# 使用PyMuPDF的压缩功能
def delete_and_compress(input_path, output_path, page_to_delete):
    doc = fitz.open(input_path)
    if 0 <= page_to_delete < len(doc):
        doc.delete_page(page_to_delete)
        doc.save(output_path, garbage=4, deflate=True)  # 深度清理
    doc.close()

# PyPDF2处理加密文档
def delete_encrypted_page(input_path, output_path, page_to_delete, password):
    reader = PdfReader(input_path)
    if reader.is_encrypted:
        reader.decrypt(password)
    
    writer = PdfWriter()
    for page_num in range(len(reader.pages)):
        if page_num != page_to_delete:
            writer.add_page(reader.pages[page_num])
    
    with open(output_path, "wb") as f:
        writer.write(f)