pdf-construction

建筑施工 PDF 处理

概述

改编自 Anthropic 的 PDF 技能，适用于建筑施工文档工作流。

建筑施工应用场景

1. RFI 处理

从信息请求文档中提取结构化数据。

from pypdf import PdfReader
import re

def extract_rfi_data(pdf_path: str) -> dict:
    """Extract RFI fields from PDF."""
    reader = PdfReader(pdf_path)
    text = ""
    for page in reader.pages:
        text += page.extract_text()

    # Parse common RFI fields
    rfi_data = {
        'rfi_number': re.search(r'RFI\s*#?\s*(\d+)', text),
        'subject': re.search(r'Subject:?\s*(.+?)(?:\n|$)', text),
        'from': re.search(r'From:?\s*(.+?)(?:\n|$)', text),
        'to': re.search(r'To:?\s*(.+?)(?:\n|$)', text),
        'date': re.search(r'Date:?\s*(\d{1,2}[/-]\d{1,2}[/-]\d{2,4})', text),
        'spec_section': re.search(r'Spec(?:ification)?\s*Section:?\s*(.+?)(?:\n|$)', text),
        'drawing_ref': re.search(r'Drawing\s*(?:Ref)?:?\s*(.+?)(?:\n|$)', text),
    }

    return {k: v.group(1) if v else None for k, v in rfi_data.items()}

2. 提交文件包创建

将多个 PDF 合并为整理好的提交文件包。

from pypdf import PdfWriter, PdfReader
from pathlib import Path

def create_submittal_package(
    cover_sheet: str,
    product_data: list,
    shop_drawings: list,
    output_path: str
) -> str:
    """Create organized submittal package."""
    writer = PdfWriter()

    # Add cover sheet
    writer.append(cover_sheet)

    # Add bookmarked sections
    page_num = len(PdfReader(cover_sheet).pages)

    # Product Data section
    writer.add_outline_item("Product Data", page_num)
    for pdf in product_data:
        writer.append(pdf)
        page_num += len(PdfReader(pdf).pages)

    # Shop Drawings section
    writer.add_outline_item("Shop Drawings", page_num)
    for pdf in shop_drawings:
        writer.append(pdf)
        page_num += len(PdfReader(pdf).pages)

    with open(output_path, "wb") as output:
        writer.write(output)

    return output_path

3. 规范提取

提取规范章节以供分析。

import pdfplumber

def extract_spec_sections(pdf_path: str) -> dict:
    """Extract specification sections by division."""
    sections = {}

    with pdfplumber.open(pdf_path) as pdf:
        current_section = None
        current_text = []

        for page in pdf.pages:
            text = page.extract_text()

            # Match CSI MasterFormat sections
            for line in text.split('\n'):
                # Match section headers like "03 30 00 - Cast-in-Place Concrete"
                match = re.match(r'^(\d{2}\s?\d{2}\s?\d{2})\s*[-–]\s*(.+)$', line)
                if match:
                    if current_section:
                        sections[current_section] = '\n'.join(current_text)
                    current_section = match.group(1).replace(' ', '')
                    current_text = [match.group(2)]
                elif current_section:
                    current_text.append(line)

        if current_section:
            sections[current_section] = '\n'.join(current_text)

    return sections

4. 图纸提取

按图纸拆分图纸包。

def split_drawing_package(pdf_path: str, output_dir: str) -> list:
    """Split drawing package into individual sheets."""
    reader = PdfReader(pdf_path)
    output_dir = Path(output_dir)
    output_dir.mkdir(exist_ok=True)

    sheets = []
    for i, page in enumerate(reader.pages):
        # Extract sheet number from page (if text-based)
        text = page.extract_text()
        sheet_match = re.search(r'([A-Z]+[-]?\d+)', text[:500])
        sheet_name = sheet_match.group(1) if sheet_match else f"Page_{i+1:03d}"

        writer = PdfWriter()
        writer.add_page(page)

        output_file = output_dir / f"{sheet_name}.pdf"
        with open(output_file, "wb") as f:
            writer.write(f)

        sheets.append(str(output_file))

    return sheets

与 DDC Pipeline 集成

# Example: Process RFI and add to tracking spreadsheet
import pandas as pd

# Extract RFI data
rfi_data = extract_rfi_data("RFI_045.pdf")

# Load existing tracker
tracker = pd.read_excel("RFI_Log.xlsx")

# Add new entry
new_row = pd.DataFrame([rfi_data])
tracker = pd.concat([tracker, new_row], ignore_index=True)

# Save updated tracker
tracker.to_excel("RFI_Log.xlsx", index=False)

依赖项

pip install pypdf pdfplumber reportlab

资源

• 原始内容：Anthropic PDF Skill
• PyPDF 文档：https://pypdf.readthedocs.io/
• PDFPlumber：https://github.com/jsvine/pdfplumber