PDF Skill 详解

PDF 文档的处理、创建和分析

基本信息

属性	值
名称	pdf
类别	文档处理
输出格式	.pdf
许可证	专有（仅源码可见）

name: pdf
description: Comprehensive PDF manipulation toolkit for extracting text
and tables, creating new PDFs, merging/splitting documents, and handling
forms. When Claude needs to fill in a PDF form or programmatically process,
generate, or analyze PDF documents at scale.

---

1. Python 库概览

1.1 pypdf - 基本操作

适用场景：合并、分割、旋转、加密、水印

from pypdf import PdfReader, PdfWriter

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

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

1.2 pdfplumber - 文本和表格提取

适用场景：布局保留的文本提取、表格数据

import pdfplumber

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

1.3 reportlab - 创建 PDF

适用场景：从零创建新 PDF

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

c = canvas.Canvas("hello.pdf", pagesize=letter)
c.drawString(100, 750, "Hello World!")
c.save()

---

2. 常用操作

2.1 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)

2.2 分割 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)

2.3 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)

2.4 提取元数据

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}")

---

3. 表格提取

3.1 基本表格提取

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"Table {j+1} on page {i+1}:")
            for row in table:
                print(row)

3.2 高级表格提取（导出到 Excel）

import pandas as pd
import pdfplumber

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)

---

4. 创建复杂 PDF

4.1 多页文档

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("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())

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

# 构建 PDF
doc.build(story)

---

5. 命令行工具

5.1 pdftotext (poppler-utils)

# 提取文本
pdftotext input.pdf output.txt

# 保留布局
pdftotext -layout input.pdf output.txt

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

5.2 qpdf

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

# 分割页面
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  # 第 1 页旋转 90 度

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

5.3 pdftk

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

# 分割
pdftk input.pdf burst

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

---

6. 高级功能

6.1 OCR 扫描件

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

# PDF 转图片
images = convert_from_path('scanned.pdf')

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

print(text)

6.2 添加水印

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)

6.3 提取图片

# 使用 pdfimages (poppler-utils)
pdfimages -j input.pdf output_prefix
# 生成：output_prefix-000.jpg, output_prefix-001.jpg 等

6.4 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)

---

7. 快速参考表

任务	最佳工具	命令/代码
合并 PDF	pypdf	writer.add_page(page)
分割 PDF	pypdf	每页一个文件
提取文本	pdfplumber	page.extract_text()
提取表格	pdfplumber	page.extract_tables()
创建 PDF	reportlab	Canvas 或 Platypus
命令行合并	qpdf	qpdf --empty --pages ...
OCR 扫描件	pytesseract	先转图片
填写表单	pdf-lib/pypdf	见 forms.md

---

8. 表单处理

8.1 参考文档

如需填写 PDF 表单，请阅读 forms.md 文件获取完整指南。

8.2 基本流程

1. 识别表单字段
2. 提取字段名称和类型
3. 填入值
4. 保存修改后的 PDF

---

9. 使用示例

9.1 触发方式

"帮我提取这个 PDF 的文本"
"合并这些 PDF 文件"
"从 PDF 中提取表格数据"
"create a PDF report"
"fill in this PDF form"

9.2 依赖安装

# Python 库
pip install pypdf pdfplumber reportlab

# 命令行工具
sudo apt-get install poppler-utils  # pdftotext, pdfimages
sudo apt-get install qpdf           # qpdf

# OCR（可选）
pip install pytesseract pdf2image
sudo apt-get install tesseract-ocr

---

10. 本节小结

要点	说明
pypdf	基本操作：合并、分割、旋转、加密
pdfplumber	文本和表格提取，保留布局
reportlab	从零创建新 PDF
命令行工具	qpdf, pdftotext, pdftk
表单处理	见 forms.md

---

返回：Skills 目录