PDF 一体化处理指南

概述

本指南涵盖全面的 PDF 处理操作，包括转换为图像。高级功能请参阅 REFERENCE.md。

工作区目录：/pdf-all-in-one-workspace/

快速开始

from pypdf import PdfReader, PdfWriter

# 读取 PDF
reader = PdfReader("document.pdf")
print(f"页数：{len(reader.pages)}")

# 提取文本
text = ""
for page in reader.pages:
    text += page.extract_text()

PDF 转图像

将 PDF 页面转换为 PNG/JPG

from pdf2image import convert_from_path
import os

# 配置
pdf_path = "input.pdf"
output_dir = "pdf-all-in-one-workspace/output_images"
os.makedirs(output_dir, exist_ok=True)

# 将 PDF 转换为图像
images = convert_from_path(pdf_path, dpi=150)

# 将每页保存为 PNG
for i, image in enumerate(images):
    output_path = f"{output_dir}/page_{i+1}.png"
    image.save(output_path, "PNG")
    print(f"已保存：{output_path}")

print(f"共转换页数：{len(images)}")

按指定页码范围转换

from pdf2image import convert_from_path

# 仅转换第 1–5 页
images = convert_from_path("document.pdf", 
                          dpi=200, 
                          first_page=1, 
                          last_page=5)

for i, image in enumerate(images):
    image.save(f"pdf-all-in-one-workspace/page_{i+1}.jpg", "JPEG", quality=95)

前提条件

# 安装 Python 库
pip install pdf2image

# 安装系统依赖（poppler）
# Ubuntu/Debian：
sudo apt-get install poppler-utils

# CentOS/RHEL：
sudo yum install poppler-utils

# macOS：
brew install poppler

Python 库

pypdf — 基础操作

合并 PDF

from pypdf import PdfWriter, PdfReader

writer = PdfWriter()
for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]:
    reader = PdfReader(pdf_file)
    for page in reader.pages:
        writer.add_page(page)

with open("merged.pdf", "wb") as output:
    writer.write(output)

拆分 PDF

reader = PdfReader("input.pdf")
for i, page in enumerate(reader.pages):
    writer = PdfWriter()
    writer.add_page(page)
    with open(f"pdf-all-in-one-workspace/page_{i+1}.pdf", "wb") as output:
        writer.write(output)

提取元数据

reader = PdfReader("document.pdf")
meta = reader.metadata
print(f"标题：{meta.title}")
print(f"作者：{meta.author}")
print(f"主题：{meta.subject}")
print(f"创建者：{meta.creator}")

旋转页面

reader = PdfReader("input.pdf")
writer = PdfWriter()

page = reader.pages[0]
page.rotate(90)  # 顺时针旋转 90 度
writer.add_page(page)

with open("rotated.pdf", "wb") as output:
    writer.write(output)

pdfplumber — 文本与表格提取

带版式结构的文本提取

import pdfplumber

with pdfplumber.open("document.pdf") as pdf:
    for page in pdf.pages:
        text = page.extract_text()
        print(text)

表格提取

with pdfplumber.open("document.pdf") as pdf:
    for i, page in enumerate(pdf.pages):
        tables = page.extract_tables()
        for j, table in enumerate(tables):
            print(f"第 {i+1} 页上的表格 {j+1}：")
            for row in table:
                print(row)

高级表格提取

import pandas as pd

with pdfplumber.open("document.pdf") as pdf:
    all_tables = []
    for page in pdf.pages:
        tables = page.extract_tables()
        for table in tables:
            if table:
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)

if all_tables:
    combined_df = pd.concat(all_tables, ignore_index=True)
    combined_df.to_excel("pdf-all-in-one-workspace/extracted_tables.xlsx", index=False)

reportlab — 创建 PDF

基础 PDF 创建

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

c = canvas.Canvas("pdf-all-in-one-workspace/hello.pdf", pagesize=letter)
width, height = letter

c.drawString(100, height - 100, "Hello World!")
c.drawString(100, height - 120, "This is a PDF created with reportlab")
c.line(100, height - 140, 400, height - 140)
c.save()

下标与上标

from reportlab.platypus import Paragraph
from reportlab.lib.styles import getSampleStyleSheet

styles = getSampleStyleSheet()
chemical = Paragraph("H2O", styles['Normal'])
squared = Paragraph("x2 + y2", styles['Normal'])

命令行工具

pdftotext（poppler-utils）

# 提取文本
pdftotext input.pdf output.txt

# 提取文本并保留原始版式
pdftotext -layout input.pdf output.txt

# 提取指定页码范围的文本
pdftotext -f 1 -l 5 input.pdf output.txt

qpdf

# 合并 PDF
qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf

# 拆分页面
qpdf input.pdf --pages . 1-5 -- pages1-5.pdf

# 旋转页面
qpdf input.pdf output.pdf --rotate=+90:1

# 移除密码保护
qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf

pdftk

# 合并
pdftk file1.pdf file2.pdf cat output merged.pdf

# 拆分（逐页导出）
pdftk input.pdf burst

# 旋转
pdftk input.pdf rotate 1east output rotated.pdf

pdfimages — 从 PDF 中提取图像

# 将所有嵌入图像提取为 JPG 格式
pdfimages -j input.pdf pdf-all-in-one-workspace/output_prefix

常见任务

从扫描版 PDF 中提取文本（OCR）

import pytesseract
from pdf2image import convert_from_path

images = convert_from_path('scanned.pdf')

text = ""
for i, image in enumerate(images):
    text += f"第 {i+1} 页：n"
    text += pytesseract.image_to_string(image)
    text += "nn"

print(text)

添加水印

from pypdf import PdfReader, PdfWriter

watermark = PdfReader("watermark.pdf").pages[0]
reader = PdfReader("document.pdf")
writer = PdfWriter()

for page in reader.pages:
    page.merge_page(watermark)
    writer.add_page(page)

with open("pdf-all-in-one-workspace/watermarked.pdf", "wb") as output:
    writer.write(output)

密码保护

from pypdf import PdfReader, PdfWriter

reader = PdfReader("input.pdf")
writer = PdfWriter()

for page in reader.pages:
    writer.add_page(page)

writer.encrypt("userpassword", "ownerpassword")

with open("pdf-all-in-one-workspace/encrypted.pdf", "wb") as output:
    writer.write(output)

速查表

工作区目录结构

/
└── pdf-all-in-one-workspace/
    ├── input/          # 输入 PDF 文件存放于此
    ├── output_images/  # 图像转换输出目录
    ├── output_pdfs/    # 生成的 PDF 输出目录
    └── temp/           # 临时文件目录

注意：为保持文件组织有序，请始终将 pdf-all-in-one-workspace/ 作为 PDF 处理操作的工作目录。

后续步骤

• 如需了解高级 pypdfium2 用法，请参阅 REFERENCE.md
• 如需了解 JavaScript 库（pdf-lib），请参阅 REFERENCE.md
• 如需了解 PDF 表单填充，请参阅 FORMS.md
• 如需查阅故障排除指南，请参阅 REFERENCE.md