A Go library for reading and converting legacy Microsoft Office binary file formats (XLS, DOC, PPT) to modern Office Open XML formats (XLSX, DOCX, PPTX).
English | 中文
- XLS Reader: Parse Excel 97-2003 binary files (.xls)
- DOC Reader: Parse Word 97-2003 binary files (.doc)
- PPT Reader: Parse PowerPoint 97-2003 binary files (.ppt)
- Format Conversion: Convert legacy formats to modern Office Open XML formats
- XLS → XLSX
- DOC → DOCX
- PPT → PPTX
go get github.com/shakinm/xlsReaderpackage main
import (
"fmt"
"github.com/shakinm/xlsReader/xls"
"log"
)
func main() {
workbook, err := xls.OpenFile("spreadsheet.xls")
if err != nil {
log.Fatal(err)
}
// Get number of sheets
fmt.Printf("Sheets: %d\n", workbook.GetNumberSheets())
// Get first sheet
sheet, err := workbook.GetSheet(0)
if err != nil {
log.Fatal(err)
}
fmt.Printf("Sheet name: %s\n", sheet.GetName())
fmt.Printf("Rows: %d\n", sheet.GetNumberRows())
// Iterate through rows and columns
for i := 0; i <= sheet.GetNumberRows(); i++ {
if row, err := sheet.GetRow(i); err == nil {
for j := 0; j < len(row.GetCols()); j++ {
if cell, err := row.GetCol(j); err == nil {
fmt.Printf("Cell [%d,%d]: %s\n", i, j, cell.GetString())
}
}
}
}
}package main
import (
"fmt"
"github.com/shakinm/xlsReader/doc"
"log"
)
func main() {
document, err := doc.OpenFile("document.doc")
if err != nil {
log.Fatal(err)
}
// Get plain text
fmt.Println(document.GetText())
// Get images
images := document.GetImages()
for i, img := range images {
fmt.Printf("Image %d: format=%s, size=%d bytes\n", i, img.Format, len(img.Data))
}
// Get formatted content (paragraphs, styles, etc.)
formatted := document.GetFormattedContent()
if formatted != nil {
for i, para := range formatted.Paragraphs {
fmt.Printf("Paragraph %d: %s\n", i, para.Text)
// Access character formatting
for _, run := range para.Runs {
if run.Bold {
fmt.Printf(" Bold text: %s\n", run.Text)
}
}
}
// Get headers and footers
for _, header := range formatted.Headers {
fmt.Printf("Header: %s\n", header.Text)
}
for _, footer := range formatted.Footers {
fmt.Printf("Footer: %s\n", footer.Text)
}
}
// Get fonts used in document
fonts := document.GetFonts()
fmt.Printf("Fonts: %v\n", fonts)
// Get styles
styles := document.GetStyles()
fmt.Printf("Styles: %v\n", styles)
}package main
import (
"fmt"
"github.com/shakinm/xlsReader/ppt"
"log"
)
func main() {
presentation, err := ppt.OpenFile("presentation.ppt")
if err != nil {
log.Fatal(err)
}
// Get number of slides
fmt.Printf("Total slides: %d\n", presentation.GetNumberSlides())
// Get slide dimensions (in EMU units)
width, height := presentation.GetSlideSize()
fmt.Printf("Slide size: %d x %d EMU\n", width, height)
// Iterate through slides
for i := 0; i < presentation.GetNumberSlides(); i++ {
slide, err := presentation.GetSlide(i)
if err != nil {
log.Fatal(err)
}
fmt.Printf("\n--- Slide %d ---\n", i+1)
// Get all text blocks
texts := slide.GetTexts()
for j, text := range texts {
fmt.Printf("Text %d: %s\n", j, text)
}
// Get shapes with formatting info
shapes := slide.GetShapes()
for j, shape := range shapes {
fmt.Printf("Shape %d: type=%d, left=%d, top=%d, width=%d, height=%d\n",
j, shape.ShapeType, shape.Left, shape.Top, shape.Width, shape.Height)
}
}
// Get all images from presentation
images := presentation.GetImages()
for i, img := range images {
fmt.Printf("Image %d: format=%s, size=%d bytes\n", i, img.Format, len(img.Data))
}
// Get fonts used in presentation
fonts := presentation.GetFonts()
fmt.Printf("Fonts: %v\n", fonts)
}package main
import (
"github.com/shakinm/xlsReader/convert/xlsconv"
"log"
)
func main() {
err := xlsconv.ConvertFile("input.xls", "output.xlsx")
if err != nil {
log.Fatal(err)
}
}package main
import (
"github.com/shakinm/xlsReader/convert/docconv"
"log"
)
func main() {
err := docconv.ConvertFile("input.doc", "output.docx")
if err != nil {
log.Fatal(err)
}
}package main
import (
"github.com/shakinm/xlsReader/convert/pptconv"
"log"
)
func main() {
err := pptconv.ConvertFile("input.ppt", "output.pptx")
if err != nil {
log.Fatal(err)
}
}LegacyOfficeReader/
├── cfb/ # Compound File Binary format parser
├── xls/ # XLS file parser
│ ├── record/ # BIFF record types
│ └── structure/ # Data structures
├── doc/ # DOC file parser
├── ppt/ # PPT file parser
├── common/ # Shared utilities (image handling)
├── helpers/ # Helper functions (date, encoding)
├── convert/ # Format converters
│ ├── xlsconv/ # XLS → XLSX conversion
│ ├── docconv/ # DOC → DOCX conversion
│ └── pptconv/ # PPT → PPTX conversion
└── cmd/ # Command-line tools
└── convert/ # Batch conversion tool
- Cell values (strings, numbers, formulas)
- Multiple sheets
- Cell formatting
- Date/number formatting
- Plain text extraction
- Paragraph formatting
- Image extraction
- Headers and footers
- Text boxes
- Slide text extraction
- Image extraction
- Slide content preservation
- github.com/metakeule/fmtdate - Date formatting
- golang.org/x/text - Text encoding support
This project is licensed under the GNU General Public License v3.0 - see the LICENSE file for details.
一个用于读取和转换旧版 Microsoft Office 二进制文件格式（XLS, DOC, PPT）到现代 Office Open XML 格式（XLSX, DOCX, PPTX）的 Go 语言库。
- XLS 读取器：解析 Excel 97-2003 二进制文件（.xls）
- DOC 读取器：解析 Word 97-2003 二进制文件（.doc）
- PPT 读取器：解析 PowerPoint 97-2003 二进制文件（.ppt）
- 格式转换：将旧格式转换为现代 Office Open XML 格式
- XLS → XLSX
- DOC → DOCX
- PPT → PPTX
go get github.com/shakinm/xlsReaderpackage main
import (
"fmt"
"github.com/shakinm/xlsReader/xls"
"log"
)
func main() {
workbook, err := xls.OpenFile("spreadsheet.xls")
if err != nil {
log.Fatal(err)
}
// 获取工作表数量
fmt.Printf("工作表数量: %d\n", workbook.GetNumberSheets())
// 获取第一个工作表
sheet, err := workbook.GetSheet(0)
if err != nil {
log.Fatal(err)
}
fmt.Printf("工作表名称: %s\n", sheet.GetName())
fmt.Printf("行数: %d\n", sheet.GetNumberRows())
// 遍历行和列
for i := 0; i <= sheet.GetNumberRows(); i++ {
if row, err := sheet.GetRow(i); err == nil {
for j := 0; j < len(row.GetCols()); j++ {
if cell, err := row.GetCol(j); err == nil {
fmt.Printf("单元格 [%d,%d]: %s\n", i, j, cell.GetString())
}
}
}
}
}package main
import (
"fmt"
"github.com/shakinm/xlsReader/doc"
"log"
)
func main() {
document, err := doc.OpenFile("document.doc")
if err != nil {
log.Fatal(err)
}
// 获取纯文本内容
fmt.Println(document.GetText())
// 获取图片
images := document.GetImages()
for i, img := range images {
fmt.Printf("图片 %d: 格式=%s, 大小=%d 字节\n", i, img.Format, len(img.Data))
}
// 获取格式化内容（段落、样式等）
formatted := document.GetFormattedContent()
if formatted != nil {
for i, para := range formatted.Paragraphs {
fmt.Printf("段落 %d: %s\n", i, para.Text)
// 访问字符格式
for _, run := range para.Runs {
if run.Bold {
fmt.Printf(" 粗体文本: %s\n", run.Text)
}
}
}
// 获取页眉页脚
for _, header := range formatted.Headers {
fmt.Printf("页眉: %s\n", header.Text)
}
for _, footer := range formatted.Footers {
fmt.Printf("页脚: %s\n", footer.Text)
}
}
// 获取文档中使用的字体
fonts := document.GetFonts()
fmt.Printf("字体: %v\n", fonts)
// 获取样式
styles := document.GetStyles()
fmt.Printf("样式: %v\n", styles)
}package main
import (
"fmt"
"github.com/shakinm/xlsReader/ppt"
"log"
)
func main() {
presentation, err := ppt.OpenFile("presentation.ppt")
if err != nil {
log.Fatal(err)
}
// 获取幻灯片数量
fmt.Printf("幻灯片总数: %d\n", presentation.GetNumberSlides())
// 获取幻灯片尺寸（EMU单位）
width, height := presentation.GetSlideSize()
fmt.Printf("幻灯片尺寸: %d x %d EMU\n", width, height)
// 遍历幻灯片
for i := 0; i < presentation.GetNumberSlides(); i++ {
slide, err := presentation.GetSlide(i)
if err != nil {
log.Fatal(err)
}
fmt.Printf("\n--- 幻灯片 %d ---\n", i+1)
// 获取所有文本块
texts := slide.GetTexts()
for j, text := range texts {
fmt.Printf("文本 %d: %s\n", j, text)
}
// 获取形状及其格式信息
shapes := slide.GetShapes()
for j, shape := range shapes {
fmt.Printf("形状 %d: 类型=%d, 左=%d, 上=%d, 宽=%d, 高=%d\n",
j, shape.ShapeType, shape.Left, shape.Top, shape.Width, shape.Height)
}
}
// 获取演示文稿中的所有图片
images := presentation.GetImages()
for i, img := range images {
fmt.Printf("图片 %d: 格式=%s, 大小=%d 字节\n", i, img.Format, len(img.Data))
}
// 获取演示文稿中使用的字体
fonts := presentation.GetFonts()
fmt.Printf("字体: %v\n", fonts)
}// XLS 转 XLSX
xlsconv.ConvertFile("input.xls", "output.xlsx")
// DOC 转 DOCX
docconv.ConvertFile("input.doc", "output.docx")
// PPT 转 PPTX
pptconv.ConvertFile("input.ppt", "output.pptx")本项目采用 GNU General Public License v3.0 许可证 - 详见 LICENSE 文件。