pdf-processor

PDF Processing Guide

Overview

This guide covers basic PDF processing operations using Python libraries and command-line tools.

Quick Start

from pypdf import PdfReader, PdfWriter

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

Extract Text

text = "" for page in reader.pages: text += page.extract_text()

## Python 库

### pypdf - 基本操作

#### 合并 PDF

```python
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)

Split 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)

Extract Metadata

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}")

Rotate Pages

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 - Text and Table Extraction

Extract Text (Preserve Layout)

import pdfplumber

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

Extract Tables

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} 页的表格 {j+1}:")
            for row in table:
                print(row)

Advanced Table Extraction

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:  # 检查表格非空
                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 - Create PDF

Basic PDF Creation

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, "这是一个使用 reportlab 创建的 PDF")

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

# 保存
c.save()

Create Multi-page 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("这是报告正文。 " * 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)

Command-line Tools

pdftotext (poppler-utils)

# 提取文本
pdftotext input.pdf output.txt

# 提取文本并保持布局
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

Common Tasks

Add Watermark

from pypdf import PdfReader, PdfWriter

# 创建水印（或加载现有水印）
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)

Password Protection

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)

Quick Reference

Task	Best Tool	Command/Code
Merge PDF	pypdf	writer.add_page(page)
Split PDF	pypdf	One file per page
Extract Text	pdfplumber	page.extract_text()
Extract Tables	pdfplumber	page.extract_tables()
Create PDF	reportlab	Canvas or Platypus
Command-line Merge	qpdf	qpdf --empty --pages ...

Dependencies

• pypdf: pip install pypdf
• pdfplumber: pip install pdfplumber
• reportlab: pip install reportlab
• pandas: pip install pandas (for table export)

Command-line tools:

• poppler-utils: sudo apt-get install poppler-utils (Linux)
• qpdf: sudo apt-get install qpdf (Linux)