DWG to Excel Conversion

Business Case

Problem Statement

AutoCAD DWG files contain valuable project data locked in proprietary format:

• Layer structures with drawing organization
• Block references with attribute data
• Text annotations and dimensions
• Geometric entities (lines, polylines, arcs)
• External references (xrefs)

Extracting this data typically requires AutoCAD licenses or complex programming.

Solution

DwgExporter.exe converts DWG files to structured Excel databases offline, without Autodesk licenses.

Business Value

• Zero license cost - No AutoCAD license required
• Legacy support - Reads DWG files from 1983 to 2026
• Data extraction - Layers, blocks, attributes, text, geometry
• PDF export - Generate drawings from DWG layouts
• Batch processing - Convert thousands of DWG files

Technical Implementation

CLI Syntax

DwgExporter.exe <input_dwg> [options]

Output Formats

Supported Versions

Examples

# Basic conversion
DwgExporter.exe "C:\Projects\FloorPlan.dwg"

# Export with PDF drawings
DwgExporter.exe "C:\Projects\FloorPlan.dwg" sheets2pdf

# Batch processing all DWG in folder
for /R "C:\Projects" %f in (*.dwg) do DwgExporter.exe "%f"

# PowerShell batch conversion
Get-ChildItem "C:\Projects\*.dwg" -Recurse | ForEach-Object {
    & "C:\DDC\DwgExporter.exe" $_.FullName
}

Python Integration

import subprocess
import pandas as pd
from pathlib import Path
from typing import List, Optional, Dict, Any
from dataclasses import dataclass
from enum import Enum


class DWGEntityType(Enum):
    """DWG entity types."""
    LINE = "LINE"
    POLYLINE = "POLYLINE"
    LWPOLYLINE = "LWPOLYLINE"
    CIRCLE = "CIRCLE"
    ARC = "ARC"
    ELLIPSE = "ELLIPSE"
    SPLINE = "SPLINE"
    TEXT = "TEXT"
    MTEXT = "MTEXT"
    DIMENSION = "DIMENSION"
    INSERT = "INSERT"  # Block reference
    HATCH = "HATCH"
    SOLID = "SOLID"
    POINT = "POINT"
    ATTRIB = "ATTRIB"
    ATTDEF = "ATTDEF"


@dataclass
class DWGEntity:
    """Represents a DWG entity."""
    handle: str
    entity_type: str
    layer: str
    color: int
    linetype: str
    lineweight: float

    # Geometry (depends on entity type)
    start_x: Optional[float] = None
    start_y: Optional[float] = None
    end_x: Optional[float] = None
    end_y: Optional[float] = None

    # Block reference data
    block_name: Optional[str] = None
    rotation: Optional[float] = None
    scale_x: Optional[float] = None
    scale_y: Optional[float] = None

    # Text data
    text_content: Optional[str] = None
    text_height: Optional[float] = None


@dataclass
class DWGBlock:
    """Represents a DWG block definition."""
    name: str
    base_point_x: float
    base_point_y: float
    entity_count: int
    is_dynamic: bool
    attributes: List[str]


@dataclass
class DWGLayer:
    """Represents a DWG layer."""
    name: str
    color: int
    linetype: str
    is_on: bool
    is_frozen: bool
    is_locked: bool
    lineweight: float
    entity_count: int


class DWGExporter:
    """DWG to Excel converter using DDC DwgExporter CLI."""

    def __init__(self, exporter_path: str = "DwgExporter.exe"):
        self.exporter = Path(exporter_path)
        if not self.exporter.exists():
            raise FileNotFoundError(f"DwgExporter not found: {exporter_path}")

    def convert(self, dwg_file: str,
                export_pdf: bool = False) -> Path:
        """Convert DWG file to Excel."""
        dwg_path = Path(dwg_file)
        if not dwg_path.exists():
            raise FileNotFoundError(f"DWG file not found: {dwg_file}")

        cmd = [str(self.exporter), str(dwg_path)]
        if export_pdf:
            cmd.append("sheets2pdf")

        result = subprocess.run(cmd, capture_output=True, text=True)

        if result.returncode != 0:
            raise RuntimeError(f"Export failed: {result.stderr}")

        # Output file is same name with .xlsx extension
        return dwg_path.with_suffix('.xlsx')

    def batch_convert(self, folder: str,
                      include_subfolders: bool = True,
                      export_pdf: bool = False) -> List[Dict[str, Any]]:
        """Convert all DWG files in folder."""
        folder_path = Path(folder)
        pattern = "**/*.dwg" if include_subfolders else "*.dwg"

        results = []
        for dwg_file in folder_path.glob(pattern):
            try:
                output = self.convert(str(dwg_file), export_pdf)
                results.append({
                    'input': str(dwg_file),
                    'output': str(output),
                    'status': 'success'
                })
                print(f"✓ Converted: {dwg_file.name}")
            except Exception as e:
                results.append({
                    'input': str(dwg_file),
                    'output': None,
                    'status': 'failed',
                    'error': str(e)
                })
                print(f"✗ Failed: {dwg_file.name} - {e}")

        return results

    def read_entities(self, xlsx_file: str) -> pd.DataFrame:
        """Read converted Excel as DataFrame."""
        xlsx_path = Path(xlsx_file)
        if not xlsx_path.exists():
            raise FileNotFoundError(f"Excel file not found: {xlsx_file}")

        return pd.read_excel(xlsx_file, sheet_name="Elements")

    def get_layers(self, xlsx_file: str) -> pd.DataFrame:
        """Get layer summary from converted file."""
        df = self.read_entities(xlsx_file)

        if 'Layer' not in df.columns:
            raise ValueError("Layer column not found in data")

        summary = df.groupby('Layer').agg({
            'Handle': 'count'
        }).reset_index()
        summary.columns = ['Layer', 'Entity_Count']
        return summary.sort_values('Entity_Count', ascending=False)

    def get_blocks(self, xlsx_file: str) -> pd.DataFrame:
        """Get block reference summary."""
        df = self.read_entities(xlsx_file)

        # Filter to INSERT entities (block references)
        blocks = df[df['EntityType'] == 'INSERT']

        if blocks.empty:
            return pd.DataFrame(columns=['Block_Name', 'Count'])

        summary = blocks.groupby('BlockName').agg({
            'Handle': 'count'
        }).reset_index()
        summary.columns = ['Block_Name', 'Count']
        return summary.sort_values('Count', ascending=False)

    def get_text_content(self, xlsx_file: str) -> pd.DataFrame:
        """Extract all text content from DWG."""
        df = self.read_entities(xlsx_file)

        # Filter to text entities
        text_types = ['TEXT', 'MTEXT', 'ATTRIB']
        texts = df[df['EntityType'].isin(text_types)]

        if 'TextContent' in texts.columns:
            return texts[['Handle', 'EntityType', 'Layer', 'TextContent']].copy()
        return texts[['Handle', 'EntityType', 'Layer']].copy()

    def get_entity_statistics(self, xlsx_file: str) -> Dict[str, int]:
        """Get entity type statistics."""
        df = self.read_entities(xlsx_file)

        if 'EntityType' not in df.columns:
            return {}

        return df['EntityType'].value_counts().to_dict()

    def extract_block_attributes(self, xlsx_file: str,
                                  block_name: str) -> pd.DataFrame:
        """Extract attributes from specific block type."""
        df = self.read_entities(xlsx_file)

        # Find block references
        blocks = df[(df['EntityType'] == 'INSERT') &
                    (df['BlockName'] == block_name)]

        # Find as