PDF 处理指南

概述

本指南涵盖使用 Python 库和命令行工具进行 PDF 处理的基本操作。高级功能、JavaScript 库和详细示例请参见 reference.md。如需填写 PDF 表单，请阅读 forms.md 并遵循其说明。

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()

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"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 - 文本和表格提取

带布局的文本提取

import pdfplumber

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

提取表格

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} 页第 {j+1} 个表格：")
            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:  # 检查表格是否为空
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)

# 合并所有表格
if all_tables:
    combined_df = pd.concat(all_tables, ignore_index=True)
    combined_df.to_excel("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("hello.pdf", pagesize=letter)
width, height = letter

# 添加文本
c.drawString(100, height - 100, "Hello World!")
c.drawString(100, height - 120, "这是使用 reportlab 创建的 PDF")

# 添加线条
c.line(100, height - 140, 400, height - 140)

# 保存
c.save()

创建多页 PDF

from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak
from reportlab.lib.styles import getSampleStyleSheet

doc = SimpleDocTemplate("report.pdf", pagesize=letter)
styles = getSampleStyleSheet()
story = []

# 添加内容
title = Paragraph("报告标题", styles['Title'])
story.append(title)
story.append(Spacer(1, 12))

body = Paragraph("这是报告的正文内容。" * 20, styles['Normal'])
story.append(body)
story.append(PageBreak())

# 第 2 页
story.append(Paragraph("第 2 页", styles['Heading1']))
story.append(Paragraph("第 2 页的内容", styles['Normal']))

# 构建 PDF
doc.build(story)

命令行工具

pdftotext（poppler-utils）

# 提取文本
pdftotext input.pdf output.txt

# 保留布局提取文本
pdftotext -layout input.pdf output.txt

# 提取特定页面
pdftotext -f 1 -l 5 input.pdf output.txt  # 第 1-5 页

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
qpdf input.pdf --pages . 6-10 -- pages6-10.pdf

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

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

pdftk（如可用）

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

# 拆分
pdftk input.pdf burst

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

常见任务

从扫描 PDF 提取文本

# 依赖：pip install pytesseract pdf2image
import pytesseract
from pdf2image import convert_from_path

# 将 PDF 转换为图像
images = convert_from_path('scanned.pdf')

# 对每页进行 OCR
text = ""
for i, image in enumerate(images):
    text += f"第 {i+1} 页：\n"
    text += pytesseract.image_to_string(image)
    text += "\n\n"

print(text)

添加水印

from pypdf import PdfReader, PdfWriter

# 创建水印（或加载现有的）
watermark = PdfReader("watermark.pdf").pages[0]

# 应用到所有页面
reader = PdfReader("document.pdf")
writer = PdfWriter()

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

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

提取图像

# 使用 pdfimages（poppler-utils）
pdfimages -j input.pdf output_prefix

# 这会提取所有图像为 output_prefix-000.jpg、output_prefix-001.jpg 等

密码保护

from pypdf import PdfReader, PdfWriter

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

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

# 添加密码
writer.encrypt("userpassword", "ownerpassword")

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

快速参考

后续步骤

• 高级 pypdfium2 用法，参见 reference.md
• JavaScript 库（pdf-lib），参见 reference.md
• 如需填写 PDF 表单，遵循 forms.md 中的说明
• 故障排除指南，参见 reference.md