README
¶
go-fitz
Go wrapper for MuPDF fitz library that can extract pages from PDF, EPUB, MOBI, DOCX, XLSX and PPTX documents as IMG, TXT, HTML or SVG.
Build tags
extlib- use external MuPDF librarystatic- build with static external MuPDF library (used withextlib)pkgconfig- enable pkg-config (used withextlib)musl- use musl compiled librarynocgo- experimental purego implementation (can also be used withCGO_ENABLED=0)
Notes
The bundled libraries are built without CJK fonts, if you need them you must use the external library.
Calling e.g. Image() or Text() methods concurrently for the same document is not supported.
Purego implementation requires libffi and libmupdf shared libraries on runtime.
You must set fitz.FzVersion in your code or set FZ_VERSION environment variable to exact version of the shared library.
Example
package main
import (
"fmt"
"image/jpeg"
"os"
"path/filepath"
"github.com/gen2brain/go-fitz"
)
func main() {
doc, err := fitz.New("test.pdf")
if err != nil {
panic(err)
}
defer doc.Close()
tmpDir, err := os.MkdirTemp(os.TempDir(), "fitz")
if err != nil {
panic(err)
}
// Extract pages as images
for n := 0; n < doc.NumPage(); n++ {
img, err := doc.Image(n)
if err != nil {
panic(err)
}
f, err := os.Create(filepath.Join(tmpDir, fmt.Sprintf("test%03d.jpg", n)))
if err != nil {
panic(err)
}
err = jpeg.Encode(f, img, &jpeg.Options{jpeg.DefaultQuality})
if err != nil {
panic(err)
}
f.Close()
}
}
Documentation
¶
Overview ¶
Package fitz provides wrapper for the [MuPDF](http://mupdf.com/) fitz library that can extract pages from PDF, EPUB, MOBI, DOCX, XLSX and PPTX documents as IMG, TXT, HTML or SVG.
Index ¶
- Variables
- type Document
- func (f *Document) Bound(pageNumber int) (image.Rectangle, error)
- func (f *Document) Close() error
- func (f *Document) HTML(pageNumber int, header bool) (string, error)
- func (f *Document) Image(pageNumber int) (*image.RGBA, error)
- func (f *Document) ImageDPI(pageNumber int, dpi float64) (*image.RGBA, error)
- func (f *Document) ImagePNG(pageNumber int, dpi float64) ([]byte, error)
- func (f *Document) Links(pageNumber int) ([]Link, error)
- func (f *Document) Metadata() map[string]string
- func (f *Document) NumPage() int
- func (f *Document) SVG(pageNumber int) (string, error)
- func (f *Document) Text(pageNumber int) (string, error)
- func (f *Document) ToC() ([]Outline, error)
- type Link
- type Outline
Examples ¶
Constants ¶
This section is empty.
Variables ¶
var ( ErrNoSuchFile = errors.New("fitz: no such file") ErrCreateContext = errors.New("fitz: cannot create context") ErrOpenDocument = errors.New("fitz: cannot open document") ErrEmptyBytes = errors.New("fitz: cannot send empty bytes") ErrOpenMemory = errors.New("fitz: cannot open memory") ErrLoadPage = errors.New("fitz: cannot load page") ErrRunPageContents = errors.New("fitz: cannot run page contents") ErrPageMissing = errors.New("fitz: page missing") ErrCreatePixmap = errors.New("fitz: cannot create pixmap") ErrPixmapSamples = errors.New("fitz: cannot get pixmap samples") ErrNeedsPassword = errors.New("fitz: document needs password") ErrLoadOutline = errors.New("fitz: cannot load outline") )
Errors.
var FzVersion = "1.24.9"
FzVersion is used for experimental purego implementation, it must be exactly the same as libmupdf shared library version. It is also possible to set `FZ_VERSION` environment variable.
var MaxStore = 256 << 20
MaxStore is maximum size in bytes of the resource store, before it will start evicting cached resources such as fonts and images.
Functions ¶
This section is empty.
Types ¶
type Document ¶
type Document struct {
// contains filtered or unexported fields
}
Document represents fitz document.
func New ¶
New returns new fitz document.
Example ¶
doc, err := fitz.New("test.pdf")
if err != nil {
panic(err)
}
defer doc.Close()
tmpDir, err := os.MkdirTemp(os.TempDir(), "fitz")
if err != nil {
panic(err)
}
// Extract pages as images
for n := 0; n < doc.NumPage(); n++ {
img, err := doc.Image(n)
if err != nil {
panic(err)
}
f, err := os.Create(filepath.Join(tmpDir, fmt.Sprintf("test%03d.jpg", n)))
if err != nil {
panic(err)
}
err = jpeg.Encode(f, img, &jpeg.Options{Quality: jpeg.DefaultQuality})
if err != nil {
panic(err)
}
f.Close()
}
// Extract pages as text
for n := 0; n < doc.NumPage(); n++ {
text, err := doc.Text(n)
if err != nil {
panic(err)
}
f, err := os.Create(filepath.Join(tmpDir, fmt.Sprintf("test%03d.txt", n)))
if err != nil {
panic(err)
}
_, err = f.WriteString(text)
if err != nil {
panic(err)
}
f.Close()
}
// Extract pages as html
for n := 0; n < doc.NumPage(); n++ {
html, err := doc.HTML(n, true)
if err != nil {
panic(err)
}
f, err := os.Create(filepath.Join(tmpDir, fmt.Sprintf("test%03d.html", n)))
if err != nil {
panic(err)
}
_, err = f.WriteString(html)
if err != nil {
panic(err)
}
f.Close()
}
// Extract pages as svg
for n := 0; n < doc.NumPage(); n++ {
svg, err := doc.SVG(n)
if err != nil {
panic(err)
}
f, err := os.Create(filepath.Join(tmpDir, fmt.Sprintf("test%03d.svg", n)))
if err != nil {
panic(err)
}
_, err = f.WriteString(svg)
if err != nil {
panic(err)
}
f.Close()
}
func NewFromMemory ¶
NewFromMemory returns new fitz document from byte slice.
func NewFromReader ¶
NewFromReader returns new fitz document from io.Reader.
type Outline ¶
type Outline struct {
// Hierarchy level of the entry (starting from 1).
Level int
// Title of outline item.
Title string
// Destination in the document to be displayed when this outline item is activated.
URI string
// The page number of an internal link.
Page int
// Top.
Top float64
}
Outline type.
Source Files
