github.com/stormvirux/pdf

PDF Reader

A simple Go library which enables reading PDF files. Forked from https://github.com/ledongthuc/pdf with changes from https://github.com/ledongthuc/pdf/pull/25

Features

• Get plain text content (without format)
• Get Content (including all font and formatting information)

Install:

go get -u github.com/ledongthuc/pdf

Read plain text

package main

import (
	"bytes"
	"fmt"

	"github.com/ledongthuc/pdf"
)

func main() {
	pdf.DebugOn = true
	content, err := readPdf("test.pdf") // Read local pdf file
	if err != nil {
		panic(err)
	}
	fmt.Println(content)
	return
}

func readPdf(path string) (string, error) {
	f, r, err := pdf.Open(path)
	// remember close file
    defer f.Close()
	if err != nil {
		return "", err
	}
	var buf bytes.Buffer
    b, err := r.GetPlainText()
    if err != nil {
        return "", err
    }
    buf.ReadFrom(b)
	return buf.String(), nil
}

Read all text with styles from PDF

func readPdf2(path string) (string, error) {
	f, r, err := pdf.Open(path)
	// remember close file
	defer f.Close()
	if err != nil {
		return "", err
	}
	totalPage := r.NumPage()

	for pageIndex := 1; pageIndex <= totalPage; pageIndex++ {
		p := r.Page(pageIndex)
		if p.V.IsNull() {
			continue
		}
		var lastTextStyle pdf.Text
		texts := p.Content().Text
		for _, text := range texts {
			if isSameSentence(text, lastTextStyle) {
				lastTextStyle.S = lastTextStyle.S + text.S
			} else {
				fmt.Printf("Font: %s, Font-size: %f, x: %f, y: %f, content: %s \n", lastTextStyle.Font, lastTextStyle.FontSize, lastTextStyle.X, lastTextStyle.Y, lastTextStyle.S)
				lastTextStyle = text
			}
		}
	}
	return "", nil
}

Read text grouped by rows

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

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

		rows, _ := p.GetTextByRow()
		for _, row := range rows {
		    println(">>>> row: ", row.Position)
		    for _, word := range row.Content {
		        fmt.Println(word.S)
		    }
		}
	}
	return "", nil
}

Extracting text with interword spaces

For more detailed explaination see detailed answer from . Something similar, has to be written for the spaces

func findWords(chars []pdf.Text) (words []pdf.Text) {
	// Sort by Y coordinate and normalize.
	const nudge = 1
	sort.Sort(pdf.TextVertical(chars))
	old := -100000.0
	for i, c := range chars {
		if c.Y != old && math.Abs(old-c.Y) < nudge {
			chars[i].Y = old
		} else {
			old = c.Y
		}
	}

	// Sort by Y coordinate, breaking ties with X.
	// This will bring letters in a single word together.
	sort.Sort(pdf.TextVertical(chars))

	// Loop over chars.
	for i := 0; i < len(chars); {
		// Find all chars on line.
		j := i + 1
		for j < len(chars) && chars[j].Y == chars[i].Y {
			j++
		}
		var end float64
		// Split line into words (really, phrases).
		for k := i; k < j; {
			ck := &chars[k]
			s := ck.S
			end = ck.X + ck.W
			charSpace := ck.FontSize / 6
			wordSpace := ck.FontSize * 2 / 3
			l := k + 1
			for l < j {
				// Grow word.
				cl := &chars[l]
				if sameFont(cl.Font, ck.Font) && math.Abs(cl.FontSize-ck.FontSize) < 0.1 && cl.X <= end+charSpace {
					s += cl.S
					end = cl.X + cl.W
					l++
					continue
				}
				// Add space to phrase before next word.
				if sameFont(cl.Font, ck.Font) && math.Abs(cl.FontSize-ck.FontSize) < 0.1 && cl.X <= end+wordSpace {
					s += " " + cl.S
					end = cl.X + cl.W
					l++
					continue
				}
				break
			}
			f := ck.Font
			f = strings.TrimSuffix(f, ",Italic")
			f = strings.TrimSuffix(f, "-Italic")
			words = append(words, pdf.Text{f, ck.FontSize, ck.X, ck.Y, end - ck.X, s})
			k = l
		}
		i = j
	}

	return words
}

func sameFont(f1, f2 string) bool {
	f1 = strings.TrimSuffix(f1, ",Italic")
	f1 = strings.TrimSuffix(f1, "-Italic")
	f2 = strings.TrimSuffix(f1, ",Italic")
	f2 = strings.TrimSuffix(f1, "-Italic")
	return strings.TrimSuffix(f1, ",Italic") == strings.TrimSuffix(f2, ",Italic") || f1 == "Symbol" || f2 == "Symbol" || f1 == "TimesNewRoman" || f2 == "TimesNewRoman"
}

Demo

References

List of useful references to how the PDF file format is structured:

• https://web.archive.org/web/20210128014024/https://www.adobe.com/content/dam/acom/en/devnet/pdf/PDF32000_2008.pdf
• https://www.oreilly.com/library/view/pdf-explained/9781449321581/ch04.html
• https://commandlinefanatic.com/cgi-bin/showarticle.cgi?article=art019