获取pdf中的文字

getTextFromPDF.go

package main

import (
	"fmt"
	"os"

	"github.com/ledongthuc/pdf"
)

func main() {
	content, err := readPdf(os.Args[1]) // Read local pdf file
	if err != nil {
		panic(err)
	}
	fmt.Println(content)
	return
}

func readPdf(path string) (text string, err error) {
	f, r, err := pdf.Open(path)
	r.GetPlainText()
	if err != nil {
		return
	}
	defer f.Close()
	totalPage := r.NumPage()

	for pageIndex := 1; pageIndex <= totalPage; pageIndex++ {
		p := r.Page(pageIndex)
		if p.V.IsNull() {
			continue
		}

		rows, err := p.GetTextByRow()
		if err != nil {
			continue
		}
		for _, row := range rows {
			for _, word := range row.Content {
				text += word.S
			}
		}
	}
	return
}