【随笔】用 Python 轻松提取、合并和压缩 PDF 文件

$ pip install pdfplumber PyPDF2 pymupdf

import os
import pdfplumber
import fitz  # PyMuPDF
from PyPDF2 import PdfReader, PdfWriter

def extract_and_merge_pages(pdf_path):
    print("开始处理 PDF 文件，请稍等...")

    # 设置主输出文件夹
    output_dir = f"{os.path.splitext(os.path.basename(pdf_path))[0]}_merged_pages"
    os.makedirs(output_dir, exist_ok=True)

    # 字典存储内容标识与页面编号的映射
    content_page_map = {}

    # 第一步：提取每一页的第二行内容并分组
    with pdfplumber.open(pdf_path) as pdf:
        for page_num, page in enumerate(pdf.pages):
            text = page.extract_text()
            if text:
                lines = text.split('\n')
                # 确保有第二行内容
                if len(lines) > 1:
                    second_line = lines[1]

                    # 提取空格前的部分
                    content_key = second_line.split()[0]
                    # 将页码按内容标识分组
                    if content_key not in content_page_map:
                        content_page_map[content_key] = []
                    content_page_map[content_key].append(page_num)

    # 第二步：根据内容标识合并相应页面并保存为单个 PDF
    reader = PdfReader(pdf_path)
    for content_key, pages in content_page_map.items():
        writer = PdfWriter()
        for page_num in pages:
            writer.add_page(reader.pages[page_num])

        # 设置临时 PDF 文件路径
        temp_pdf_path = os.path.join(output_dir, f"{content_key}_temp.pdf")
        with open(temp_pdf_path, "wb") as temp_pdf_file:
            writer.write(temp_pdf_file)

        # 压缩 PDF 文件
        compressed_pdf_path = os.path.join(output_dir, f"{content_key}.pdf")
        compress_pdf(temp_pdf_path, compressed_pdf_path)

        # 删除临时未压缩的 PDF 文件
        os.remove(temp_pdf_path)
        print(f"已保存并压缩合并文件: {compressed_pdf_path}")

    print("处理完成，所有文件已保存至：", output_dir)

def compress_pdf(input_path, output_path):
    # 使用 PyMuPDF 读取和压缩 PDF
    doc = fitz.open(input_path)
    doc.save(output_path, garbage=4, deflate=True)
    doc.close()

# 示例使用
print("请输入 PDF 文件的路径，注意使用斜杠 (/) 作为路径分隔符。例如：C:/path/to/file.pdf")
pdf_path = input("路径：")
extract_and_merge_pages(pdf_path)

with pdfplumber.open(pdf_path) as pdf:
    for page_num, page in enumerate(pdf.pages):
        text = page.extract_text()
        if text:
            lines = text.split('\n')
            if len(lines) > 1:
                second_line = lines[1]
                content_key = second_line.split()[0]

reader = PdfReader(pdf_path)
for content_key, pages in content_page_map.items():
    writer = PdfWriter()
    for page_num in pages:
        writer.add_page(reader.pages[page_num])

doc = fitz.open(input_path)
doc.save(output_path, garbage=4, deflate=True)
doc.close()