pdf

Holo00 的头像作者 Holo00

全面的PDF操作工具包,用于提取文本和表格、创建新PDF、合并/拆分文档和处理表单。当Claude需要填写PDF表单或以编程方式大规模处理、生成或分析PDF文档时。

📖 中文导读:全面的PDF操作工具包,用于提取文本和表格、创建新PDF、合并/拆分文档和处理表单。当Claude需要填写PDF表单或以编程方式大规模处理、生成或分析PDF文档时。 以下正文为该技能的原始 SKILL.md 内容(英文),上方安装命令可直接使用。

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.

PDF Processing

Overview

Work with PDF documents for text extraction, creation, manipulation, and form handling.

Python Libraries

pypdf - Basic Operations

from pypdf import PdfReader, PdfWriter

# Read PDF
reader = PdfReader("input.pdf")
text = reader.pages[0].extract_text()

# Merge PDFs
writer = PdfWriter()
writer.append("file1.pdf")
writer.append("file2.pdf")
writer.write("merged.pdf")

# Split PDF
writer = PdfWriter()
writer.add_page(reader.pages[0])
writer.write("page1.pdf")

pdfplumber - Text and Tables

import pdfplumber

with pdfplumber.open("document.pdf") as pdf:
    page = pdf.pages[0]

    # Extract text with layout
    text = page.extract_text()

    # Extract tables
    tables = page.extract_tables()

reportlab - PDF Creation

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

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

Command-Line Tools

Text Extraction (poppler-utils)

pdftotext document.pdf output.txt
pdftotext -layout document.pdf output.txt  # Preserve layout

Page Manipulation (qpdf)

qpdf input.pdf --pages . 1-5 -- output.pdf  # Extract pages
qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf

pdftk Operations

pdftk input.pdf output output.pdf user_pw password  # Add password
pdftk input.pdf cat 1-5 output first5.pdf  # Extract pages

Advanced Operations

OCR for Scanned Documents

import pytesseract
from pdf2image import convert_from_path

images = convert_from_path('scanned.pdf')
text = pytesseract.image_to_string(images[0])

Table to DataFrame

import pandas as pd
import pdfplumber

with pdfplumber.open("document.pdf") as pdf:
    table = pdf.pages[0].extract_tables()[0]
    df = pd.DataFrame(table[1:], columns=table[0])
    df.to_excel("output.xlsx", index=False)

Tool Selection Guide

Task Tool
Simple text extraction pypdf
Layout-aware extraction pdfplumber
Table extraction pdfplumber
PDF creation reportlab
Merge/split pypdf or qpdf
Form filling pypdf
OCR pytesseract + pdf2image