/pdf

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.
license: Proprietary. LICENSE.txt has complete terms

PDF Processing Guide

Overview

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.

Quick Start

from pypdf import PdfReader, PdfWriter

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

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

Python Libraries

pypdf - Basic Operations

Merge PDFs

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"Title: {meta.title}")
print(f"Author: {meta.author}")
print(f"Subject: {meta.subject}")
print(f"Creator: {meta.creator}")

Rotate Pages

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)

pdfplumber - Text and Table Extraction

Extract Text with 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"Table {j+1} on page {i+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:  # Check if table is not empty
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)

# Combine all tables
if all_tables:
    combined_df = pd.concat(all_tables, ignore_index=True)
    combined_df.to_excel("extracted_tables.xlsx", index=False)

reportlab - Create PDFs

Basic PDF Creation

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

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

# Add text
c.drawString(100, height - 100, "Hello World!")
c.drawString(100, height - 120, "This is a PDF created with reportlab")

# Add a line
c.line(100, height - 140, 400, height - 140)

# Save
c.save()

Create PDF with Multiple Pages

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
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())

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

# Build PDF
doc.build(story)

支持中文

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

# 尝试多个可能的字体路径
font_candidates = [
    '/System/Library/Fonts/PingFang.ttc',
    '/System/Library/Fonts/Supplemental/Songti.ttc',
    '/System/Library/Fonts/Supplemental/STSong.ttf',
    '/System/Library/Fonts/Supplemental/Kaiti.ttc',
    '/System/Library/Fonts/Supplemental/Arial Unicode.ttf',
    '/Library/Fonts/Arial Unicode.ttf',
]

font_registered = False
for font_path in font_candidates:
    if os.path.exists(font_path):
        try:
            pdfmetrics.registerFont(TTFont('ChineseFont', font_path))
            print(f"✓ 成功加载字体: {font_path}")
            font_registered = True
            break
        except Exception as e:
            print(f"✗ 尝试加载 {font_path} 失败: {e}")

if not font_registered:
    print("\n❌ 未找到可用字体，请运行字体查找代码")
    print("或手动指定字体路径")
    exit(1)

# Create PDF
doc = SimpleDocTemplate("红腹锦鸡保护报告.pdf", pagesize=letter)
styles = getSampleStyleSheet()

# 创建支持中文的样式
styles.add(ParagraphStyle(
    name='ChineseTitle', 
    fontName='ChineseFont', 
    fontSize=24, 
    leading=30,
    alignment=TA_LEFT
))

styles.add(ParagraphStyle(
    name='ChineseHeading', 
    fontName='ChineseFont', 
    fontSize=16, 
    leading=20
))

styles.add(ParagraphStyle(
    name='ChineseNormal', 
    fontName='ChineseFont', 
    fontSize=12, 
    leading=18
))

story = []

# Title
story.append(Paragraph("红腹锦鸡保护报告", styles['ChineseTitle']))
story.append(Spacer(1, 12))

# 1. 红腹锦鸡的基本介绍
story.append(Paragraph("1. 红腹锦鸡的基本介绍", styles['ChineseHeading']))
story.append(Parag