dwg-to-excel

name	dwg-to-excel
description	Convert AutoCAD DWG files (1983-2026) to Excel databases using DwgExporter CLI. Extract layers, blocks, attributes, and geometry data without Autodesk licenses.

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

Output	Description
.xlsx	Excel database with all entities
.pdf	PDF drawings from layouts

Supported Versions

Version Range	Description
R12 (1992)	Legacy DWG
R14 (1997)	AutoCAD 14
2000-2002	DWG 2000 format
2004-2006	DWG 2004 format
2007-2009	DWG 2007 format
2010-2012	DWG 2010 format
2013-2017	DWG 2013 format
2018-2026	DWG 2018 format

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[] = 
    start_y: [] = 
    end_x: [] = 
    end_y: [] = 

    
    block_name: [] = 
    rotation: [] = 
    scale_x: [] = 
    scale_y: [] = 

    
    text_content: [] = 
    text_height: [] = 



 :
    
    name: 
    base_point_x: 
    base_point_y: 
    entity_count: 
    is_dynamic: 
    attributes: []



 :
    
    name: 
    color: 
    linetype: 
    is_on: 
    is_frozen: 
    is_locked: 
    lineweight: 
    entity_count: 


 :
    

     ():
        .exporter = Path(exporter_path)
          .exporter.exists():
             FileNotFoundError()

     () -> Path:
        
        dwg_path = Path(dwg_file)
          dwg_path.exists():
             FileNotFoundError()

        cmd = [(.exporter), (dwg_path)]
         export_pdf:
            cmd.append()

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

         result.returncode != :
             RuntimeError()

        
         dwg_path.with_suffix()

     () -> [[, ]]:
        
        folder_path = Path(folder)
        pattern =   include_subfolders  

        results = []
         dwg_file  folder_path.glob(pattern):
            :
                output = .convert((dwg_file), export_pdf)
                results.append({
                    : (dwg_file),
                    : (output),
                    : 
                })
                ()
             Exception  e:
                results.append({
                    : (dwg_file),
                    : ,
                    : ,
                    : (e)
                })
                ()

         results

     () -> pd.DataFrame:
        
        xlsx_path = Path(xlsx_file)
          xlsx_path.exists():
             FileNotFoundError()

         pd.read_excel(xlsx_file, sheet_name=)

     () -> pd.DataFrame:
        
        df = .read_entities(xlsx_file)

            df.columns:
             ValueError()

        summary = df.groupby().agg({
            : 
        }).reset_index()
        summary.columns = [, ]
         summary.sort_values(, ascending=)

     () -> pd.DataFrame:
        
        df = .read_entities(xlsx_file)

        
        blocks = df[df[] == ]

         blocks.empty:
             pd.DataFrame(columns=[, ])

        summary = blocks.groupby().agg({
            : 
        }).reset_index()
        summary.columns = [, ]
         summary.sort_values(, ascending=)

     () -> pd.DataFrame:
        
        df = .read_entities(xlsx_file)

        
        text_types = [, , ]
        texts = df[df[].isin(text_types)]

           texts.columns:
             texts[[, , , ]].copy()
         texts[[, , ]].copy()

     () -> [, ]:
        
        df = .read_entities(xlsx_file)

            df.columns:
             {}

         df[].value_counts().to_dict()

     () -> pd.DataFrame:
        
        df = .read_entities(xlsx_file)

        
        blocks = df[(df[] == ) &
                    (df[] == block_name)]

        
        
        result_data = []

         _, block  blocks.iterrows():
            block_handle = block[]
            block_data = {
                : block_handle,
                : block.get(, ),
                : block.get(, ),
                : block.get(, )
            }

            
             col  df.columns:
                 col.startswith():
                    block_data[col] = block.get(col)

            result_data.append(block_data)

         pd.DataFrame(result_data)


 :
    

     ():
        .exporter = exporter

     () -> [, ]:
        
        xlsx = .exporter.convert(dwg_file)
        df = .exporter.read_entities((xlsx))

        analysis = {
            : dwg_file,
            : (df),
            : .exporter.get_layers((xlsx)).to_dict(),
            : .exporter.get_entity_statistics((xlsx)),
            : .exporter.get_blocks((xlsx)).to_dict()
        }

        
           df.columns    df.columns:
            analysis[] = {
                : df[].(),
                : df[].(),
                : df[].(),
                : df[].()
            }

         analysis

     () -> [, ]:
        
        xlsx1 = .exporter.convert(dwg1)
        xlsx2 = .exporter.convert(dwg2)

        df1 = .exporter.read_entities((xlsx1))
        df2 = .exporter.read_entities((xlsx2))

        layers1 = (df1[].unique())    df1.columns  ()
        layers2 = (df2[].unique())    df2.columns  ()

         {
            : dwg1,
            : dwg2,
            : (df2) - (df1),
            : (layers2 - layers1),
            : (layers1 - layers2),
            : (layers1 & layers2)
        }

     () -> pd.DataFrame:
        
        df = .exporter.read_entities(xlsx_file)

            df.columns     df.columns:
             pd.DataFrame()

        
        df[] = (df[] / tolerance).() * tolerance
        df[] = (df[] / tolerance).() * tolerance

        
        duplicates = df[df.duplicated(
            subset=[, , , ],
            keep=
        )]

         duplicates.sort_values([, ])



 () -> :
    
    exporter = DWGExporter(exporter_path)
    output = exporter.convert(dwg_file)
     (output)


 () -> []:
    
    exporter = DWGExporter(exporter_path)
    results = exporter.batch_convert(folder, include_subfolders)
     [r[]  r  results  r[] == ]

Output Structure

Excel Sheets

Sheet	Content
Elements	All DWG entities with properties
Layers	Layer definitions
Blocks	Block definitions
Layouts	Drawing layouts/sheets

Entity Columns

Column	Type	Description
Handle	string	Unique entity handle
EntityType	string	LINE, CIRCLE, INSERT, etc.
Layer	string	Layer name
Color	int	Color index (0-256)
Linetype	string	Linetype name
Lineweight	float	Line weight in mm
X, Y, Z	float	Entity coordinates
BlockName	string	For INSERT entities
TextContent	string	For TEXT/MTEXT

Quick Start

# Initialize exporter
exporter = DWGExporter("C:/DDC/DwgExporter.exe")

# Convert single file
xlsx = exporter.convert("C:/Projects/Plan.dwg")
print(f"Output: {xlsx}")

# Read and analyze
df = exporter.read_entities(str(xlsx))
print(f"Total entities: {len(df)}")

# Get layer statistics
layers = exporter.get_layers(str(xlsx))
print(layers)

# Get block usage
blocks = exporter.get_blocks(str(xlsx))
print(blocks)

# Extract text annotations
texts = exporter.get_text_content(str(xlsx))
for _, row in texts.iterrows():
    print(f"{row['Layer']}: {row.get('TextContent', 'N/A')}")

Common Use Cases

1. Layer Audit

exporter = DWGExporter()
xlsx = exporter.convert("drawing.dwg")
layers = exporter.get_layers(str(xlsx))

# Check for non-standard layers
standard_layers = ['0', 'WALLS', 'DOORS', 'WINDOWS', 'DIMENSIONS']
non_standard = layers[~layers['Layer'].isin(standard_layers)]
print("Non-standard layers:", non_standard['Layer'].tolist())

2. Block Schedule

# Extract all door blocks with attributes
doors = exporter.extract_block_attributes(str(xlsx), "DOOR")
print(doors[['Block_Handle', 'Attr_DOOR_TYPE', 'Attr_DOOR_SIZE']])

3. Drawing Comparison

analyzer = DWGAnalyzer(exporter)
diff = analyzer.compare_drawings("rev1.dwg", "rev2.dwg")
print(f"Entities added: {diff['entity_count_diff']}")
print(f"New layers: {diff['layers_added']}")

Integration with DDC Pipeline

# Full pipeline: DWG → Excel → Analysis → Report
from dwg_exporter import DWGExporter, DWGAnalyzer

# 1. Convert DWG
exporter = DWGExporter("C:/DDC/DwgExporter.exe")
xlsx = exporter.convert("project.dwg")

# 2. Analyze structure
analyzer = DWGAnalyzer(exporter)
analysis = analyzer.analyze_drawing_structure("project.dwg")

# 3. Generate report
print(f"Drawing: {analysis['file']}")
print(f"Entities: {analysis['total_entities']}")
print(f"Layers: {len(analysis['layers'])}")
print(f"Blocks: {len(analysis['blocks'])}")

Best Practices

1. Check DWG version - Older files may have limited data
2. Validate layer structure - Clean up before processing
3. Handle external references - Bind xrefs if needed
4. Batch overnight - Large files take time
5. Verify entity counts - Compare with AutoCAD if possible

Resources

• GitHub: cad2data Pipeline
• Video Tutorial: DWG to Excel Pipeline
• DDC Book: Chapter 2.4 - CAD Data Extraction