PDF文档处理Skill pdf

---

name: pdf description: 全面的PDF操作工具包，用于提取文本和表格、创建新PDF、合并/拆分文档以及处理表单。当Claude需要填写PDF表单或大规模地编程处理、生成或分析PDF文档时使用。 license: 专有。LICENSE.txt包含完整条款

PDF处理指南

概述

本指南涵盖了使用Python库和命令行工具进行基本PDF处理操作。对于高级功能、JavaScript库和详细示例，请参阅reference.md。如果需要填写PDF表单，请阅读forms.md并按照其说明操作。

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 - 基本操作

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

提取文本并保留布局

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:  # 检查表格是否非空
                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 - 创建PDF

基本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, "This is a PDF created with reportlab")

# 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("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)

韩语字体支持 (한글 폰트 지원)

重要: reportlab默认不支持韩语。要使用韩语，必须查找并注册系统上的韩语字体。

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont
import platform
import os

def get_korean_font_path():
    """查找系统上的韩语字体路径。"""
    system = platform.system()

    if system == 'Darwin':  # macOS
        fonts = [
            '/System/Library/Fonts/Supplemental/AppleGothic.ttf',
            '/System/Library/Fonts/Supplemental/AppleMyungjo.ttf',
            '/Library/Fonts/NanumGothic.ttf'
        ]
    elif system == 'Windows':
        fonts = [
            'C:\\Windows\\Fonts\\malgun.ttf',  # 맑은 고딕
            'C:\\Windows\\Fonts\\gulim.ttc',   # 굴림
            'C:\\Windows\\Fonts\\batang.ttc'   # 바탕
        ]
    else:  # Linux
        fonts = [
            '/usr/share/fonts/truetype/nanum/NanumGothic.ttf',
            '/usr/share/fonts/truetype/nanum/NanumMyeongjo.ttf',
            '/usr/share/fonts/opentype/noto/NotoSansCJK-Regular.ttc'
        ]

    # 返回找到的第一个字体
    for font_path in fonts:
        if os.path.exists(font_path):
            return font_path

    raise FileNotFoundError("找不到韩语字体。请安装韩语字体。")

# 注册韩语字体
korean_font_path = get_korean_font_path()
pdfmetrics.registerFont(TTFont('KoreanFont', korean_font_path))

# 创建PDF
c = canvas.Canvas("korean.pdf", pagesize=letter)
width, height = letter

# 设置韩语字体
c.setFont('KoreanFont', 12)

# 添加韩语文本
c.drawString(100, height - 100, "안녕하세요! 한글 PDF 생성 테스트입니다.")
c.drawString(100, height - 120, "시스템의 한글 폰트를 자동으로 찾아서 사용합니다.")

c.save()

Platypus (高级布局) 中使用韩语:

from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont
import platform
import os

def get_korean_font_path():
    """查找系统上的韩语字体路径。"""
    system = platform.system()

    if system == 'Darwin':  # macOS
        fonts = [
            '/System/Library/Fonts/Supplemental/AppleGothic.ttf',
            '/System/Library/Fonts/Supplemental/AppleMyungjo.ttf',
            '/Library/Fonts/NanumGothic.ttf'
        ]
    elif system == 'Windows':
        fonts = [
            'C:\\Windows\\Fonts\\malgun.ttf',  # 맑은 고딕
            'C:\\Windows\\Fonts\\gulim.ttc',   # 굴림
            'C:\\Windows\\Fonts\\batang.ttc'   # 바탕
        ]
    else:  # Linux
        fonts = [
            '/usr/share/fonts/truetype/nanum/NanumGothic.ttf',
            '/usr/share/fonts/truetype/nanum/NanumMyeongjo.ttf',
            '/usr/share/fonts/opentype/noto/NotoSansCJK-Regular.ttc'
        ]

    for font_path in fonts:
        if os.path.exists(font_path):
            return font_path

    raise FileNotFoundError("找不到韩语字体。")

# 注册韩语字体
korean_font_path = get_korean_font_path()
pdfmetrics.registerFont(TTFont('KoreanFont', korean_font_path))

# 创建韩语样式
styles = getSampleStyleSheet()
korean_style = ParagraphStyle(
    'Korean',
    parent=styles['Normal'],
    fontName='KoreanFont',
    fontSize=12,
    leading=18
)

korean_title = ParagraphStyle(
    'KoreanTitle',
    parent=styles['Title'],
    fontName='KoreanFont',
    fontSize=24,
    leading=30
)

# 创建PDF
doc = SimpleDocTemplate("korean_report.pdf", pagesize=letter)
story = []

# 添加韩语内容
title = Paragraph("한글 리포트 제목", korean_title)
story.append(title)
story.append(Spacer(1, 12))

body = Paragraph("이것은 한글로 작성된 본문입니다. 시스템의 한글 폰트를 자동으로 찾아서 사용합니다.", korean_style)
story.append(body)

doc.build(story)

重要:

• 创建包含韩语文本的PDF时，必须使用上述get_korean_font_path()函数注册韩语字体。
• 使用Canvas时：c.setFont('KoreanFont', font_size)
• 使用Platypus时：在ParagraphStyle中指定fontName='KoreanFont'

命令行工具

pdftotext (poppler-utils)

# 提取文本
pdftotext input.pdf output.txt

# 提取文本并保留布局
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  # 第1页旋转90度

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

pdftk (如果可用)

# 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

# 需要：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')

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

"

print(text)

添加水印

from pypdf import PdfReader, PdfWriter

# 创建水印（或加载现有）
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

# 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

任务	最佳工具	命令/代码
合并PDF	pypdf	writer.add_page(page)
拆分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PDF	pytesseract	先转换为图像
填写PDF表单	pdf-lib或pypdf (见forms.md)	见forms.md

下一步

• 高级pypdfium2使用，见reference.md
• JavaScript库（pdf-lib），见reference.md
• 如果需要填写PDF表单，遵循forms.md中的说明
• 故障排除指南，见reference.md