Back to Details

pdf

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

PDF Processing Guide

PDF处理指南

Overview

概述

This guide covers essential PDF processing operations using Python libraries and command-line tools. For advanced features, JavaScript libraries, and detailed examples, see REFERENCE.md. If you need to fill out a PDF form, read FORMS.md and follow its instructions.
本指南涵盖了使用Python库和命令行工具进行的基本PDF处理操作。如需高级功能、JavaScript库和详细示例，请参阅REFERENCE.md。如果您需要填写PDF表单，请阅读FORMS.md并遵循其说明。

Quick Start

快速开始

python
from pypdf import PdfReader, PdfWriter
python
from pypdf import PdfReader, PdfWriter

Read a PDF

读取PDF

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

Extract text

提取文本

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

Python Libraries

Python库

pypdf - Basic Operations

pypdf - 基础操作

Merge PDFs

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)
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

拆分PDF

python
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)
python
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

提取元数据

python
reader = PdfReader("document.pdf")
meta = reader.metadata
print(f"Title: {meta.title}")
print(f"Author: {meta.author}")
print(f"Subject: {meta.subject}")
print(f"Creator: {meta.creator}")
python
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

旋转页面

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

page = reader.pages[0]
page.rotate(90)  # Rotate 90 degrees clockwise
writer.add_page(page)

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

pdfplumber - 文本与表格提取

Extract Text with Layout

提取带布局的文本

python
import pdfplumber

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

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

Extract Tables

提取表格

python
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"Table {j+1} on page {i+1}:")
            for row in table:
                print(row)
python
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}页的第{j+1}个表格:")
            for row in table:
                print(row)

Advanced Table Extraction

高级表格提取

python
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:  # Check if table is not empty
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)
python
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:  # 检查表格是否非空
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)

Combine all tables

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)
undefined
if all_tables: combined_df = pd.concat(all_tables, ignore_index=True) combined_df.to_excel("extracted_tables.xlsx", index=False)
undefined

reportlab - Create PDFs

reportlab - 创建PDF

Basic PDF Creation

基础PDF创建

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

c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter
python
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter

Add text

添加文本

c.drawString(100, height - 100, "Hello World!") c.drawString(100, height - 120, "This is a PDF created with reportlab")
c.drawString(100, height - 100, "Hello World!") c.drawString(100, height - 120, "这是使用reportlab创建的PDF")

Add a line

添加线条

c.line(100, height - 140, 400, height - 140)
c.line(100, height - 140, 400, height - 140)

Save

保存

c.save()
undefined
c.save()
undefined

Create PDF with Multiple Pages

创建多页PDF

python
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 = []
python
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 = []

Add content

添加内容

title = Paragraph("Report Title", styles['Title']) story.append(title) story.append(Spacer(1, 12))
body = Paragraph("This is the body of the report. " * 20, styles['Normal']) story.append(body) story.append(PageBreak())
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())

Page 2

第2页

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

Build PDF

生成PDF

doc.build(story)
undefined
doc.build(story)
undefined

Subscripts and Superscripts

下标与上标

IMPORTANT: Never use Unicode subscript/superscript characters (₀₁₂₃₄₅₆₇₈₉, ⁰¹²³⁴⁵⁶⁷⁸⁹) in ReportLab PDFs. The built-in fonts do not include these glyphs, causing them to render as solid black boxes.
Instead, use ReportLab's XML markup tags in Paragraph objects:
python
from reportlab.platypus import Paragraph
from reportlab.lib.styles import getSampleStyleSheet

styles = getSampleStyleSheet()
重要提示：切勿在ReportLab PDF中使用Unicode下标/上标字符（₀₁₂₃₄₅₆₇₈₉，⁰¹²³⁴⁵⁶⁷⁸⁹）。内置字体不包含这些字形，会导致它们渲染为实心黑框。
请改用Paragraph对象中的ReportLab XML标记标签：
python
from reportlab.platypus import Paragraph
from reportlab.lib.styles import getSampleStyleSheet

styles = getSampleStyleSheet()

Subscripts: use <sub> tag

下标：使用<sub>标签

chemical = Paragraph("H<sub>2</sub>O", styles['Normal'])
chemical = Paragraph("H<sub>2</sub>O", styles['Normal'])

Superscripts: use <super> tag

上标：使用<super>标签

squared = Paragraph("x<super>2</super> + y<super>2</super>", styles['Normal'])

For canvas-drawn text (not Paragraph objects), manually adjust font the size and position rather than using Unicode subscripts/superscripts.
squared = Paragraph("x<super>2</super> + y<super>2</super>", styles['Normal'])

对于用canvas绘制的文本（非Paragraph对象），请手动调整字体大小和位置，而非使用Unicode下标/上标。

Command-Line Tools

命令行工具

pdftotext (poppler-utils)

pdftotext (poppler-utils)

bash
undefined
bash
undefined

Extract text

提取文本

pdftotext input.pdf output.txt
pdftotext input.pdf output.txt

Extract text preserving layout

提取文本并保留布局

pdftotext -layout input.pdf output.txt
pdftotext -layout input.pdf output.txt

Extract specific pages

提取特定页面

pdftotext -f 1 -l 5 input.pdf output.txt # Pages 1-5
undefined
pdftotext -f 1 -l 5 input.pdf output.txt # 第1-5页
undefined

qpdf

qpdf

bash
undefined
bash
undefined

Merge PDFs

合并PDF

qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf
qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf

Split pages

拆分页面

qpdf input.pdf --pages . 1-5 -- pages1-5.pdf qpdf input.pdf --pages . 6-10 -- pages6-10.pdf
qpdf input.pdf --pages . 1-5 -- pages1-5.pdf qpdf input.pdf --pages . 6-10 -- pages6-10.pdf

Rotate pages

旋转页面

qpdf input.pdf output.pdf --rotate=+90:1 # Rotate page 1 by 90 degrees
qpdf input.pdf output.pdf --rotate=+90:1 # 将第1页旋转90度

Remove password

移除密码

qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf
undefined
qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf
undefined

pdftk (if available)

pdftk (若可用)

bash
undefined
bash
undefined

Merge

合并

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

Split

拆分

pdftk input.pdf burst
pdftk input.pdf burst

Rotate

旋转

pdftk input.pdf rotate 1east output rotated.pdf
undefined
pdftk input.pdf rotate 1east output rotated.pdf
undefined

Common Tasks

常见任务

Extract Text from Scanned PDFs

从扫描版PDF提取文本

python
undefined
python
undefined

Requires: pip install pytesseract pdf2image

需安装：pip install pytesseract pdf2image

import pytesseract from pdf2image import convert_from_path
import pytesseract from pdf2image import convert_from_path

Convert PDF to images

将PDF转换为图片

images = convert_from_path('scanned.pdf')
images = convert_from_path('scanned.pdf')

OCR each page

对每页进行OCR识别

text = "" for i, image in enumerate(images): text += f"Page {i+1}:\n" text += pytesseract.image_to_string(image) text += "\n\n"
print(text)
undefined
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)
undefined

Add Watermark

添加水印

python
from pypdf import PdfReader, PdfWriter
python
from pypdf import PdfReader, PdfWriter

Create watermark (or load existing)

创建水印（或加载现有水印）

watermark = PdfReader("watermark.pdf").pages[0]
watermark = PdfReader("watermark.pdf").pages[0]

Apply to all pages

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)
undefined
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)
undefined

Extract Images

提取图片

bash
undefined
bash
undefined

Using pdfimages (poppler-utils)

使用pdfimages (poppler-utils)

pdfimages -j input.pdf output_prefix
pdfimages -j input.pdf output_prefix

This extracts all images as output_prefix-000.jpg, output_prefix-001.jpg, etc.

此命令会将所有图片提取为output_prefix-000.jpg, output_prefix-001.jpg等格式

undefined
undefined

Password Protection

密码保护

python
from pypdf import PdfReader, PdfWriter

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

for page in reader.pages:
    writer.add_page(page)
python
from pypdf import PdfReader, PdfWriter

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

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

Add password

添加密码

writer.encrypt("userpassword", "ownerpassword")
with open("encrypted.pdf", "wb") as output: writer.write(output)
undefined
writer.encrypt("userpassword", "ownerpassword")
with open("encrypted.pdf", "wb") as output: writer.write(output)
undefined

Quick Reference

快速参考

TaskBest ToolCommand/Code
Merge PDFspypdf
writer.add_page(page)
Split PDFspypdfOne page per file
Extract textpdfplumber
page.extract_text()
Extract tablespdfplumber
page.extract_tables()
Create PDFsreportlabCanvas or Platypus
Command line mergeqpdf
qpdf --empty --pages ...
OCR scanned PDFspytesseractConvert to image first
Fill PDF formspdf-lib or pypdf (see FORMS.md)See FORMS.md
任务最佳工具命令/代码
合并PDFpypdf
writer.add_page(page)
拆分PDFpypdf单页存为单个文件
提取文本pdfplumber
page.extract_text()
提取表格pdfplumber
page.extract_tables()
创建PDFreportlabCanvas或Platypus
命令行合并qpdf
qpdf --empty --pages ...
OCR扫描版PDFpytesseract先转换为图片
填写PDF表单pdf-lib或pypdf（见FORMS.md）见FORMS.md

Next Steps

后续步骤

  • For advanced pypdfium2 usage, see REFERENCE.md
  • For JavaScript libraries (pdf-lib), see REFERENCE.md
  • If you need to fill out a PDF form, follow the instructions in FORMS.md
  • For troubleshooting guides, see REFERENCE.md
  • 如需了解pypdfium2的高级用法，请参阅REFERENCE.md
  • 如需JavaScript库（pdf-lib）相关内容，请参阅REFERENCE.md
  • 如果您需要填写PDF表单，请遵循FORMS.md中的说明
  • 如需故障排除指南，请参阅REFERENCE.md