browserSpider/program/spider/cli/rnext/main.go

package main

import (
	"errors"
	"flag"
	"io"
	"io/ioutil"
	"log"
	"os"
	"path/filepath"
	"strings"

	"github.com/gabriel-vasile/mimetype"
)

// FileSignature 定义了文件签名的结构
type FileSignature struct {
	Signature []byte
	Extension string
}

var (
	dir = flag.String("dir", "/Users/taozhang/Downloads/docs2", "要处理的文件目录")
)

// detectFileType 通过文件的签名来识别文件类型
func detectFileType(filePath string) (string, string, error) {
	f, err := os.Open(filePath)
	if err != nil {
		return "", "", err
	}
	defer f.Close()
	// 读取文件的前16字节，这应该足以检测大多数文件的类型
	signature := make([]byte, 64)
	if _, err := io.ReadFull(f, signature); err != nil {
		return "", "", err
	}
	// 查找匹配的签名
	mtype := mimetype.Detect(signature)
	// 如果没有匹配的签名，返回未知类型
	extension := mtype.Extension()
	mime := mtype.String()
	if extension == "" {
		return "", "", errors.New("unknow extension")
	} else {
		return extension, mime, nil
	}
}

// init
func init() {
	flag.Parse()
}

// main
func main() {
	fs, err := ioutil.ReadDir(*dir)
	if err != nil {
		log.Fatal(err)
	}
	for _, f := range fs {
		ext := strings.ToLower(filepath.Ext(f.Name()))
		newExt, mime, err := detectFileType(filepath.Join(*dir, f.Name()))
		if err == nil && ext != newExt {
			newFileName := f.Name()[:len(f.Name())-len(ext)] + newExt
			log.Println(f.Name(), mime, ext, newExt, newFileName)
			//os.Rename(filepath.Join(*dir, f.Name()), filepath.Join(*dir, newFileName))
		}
	}
}