Skip to content

Commit

Permalink
use go-epub to generate ebook
Browse files Browse the repository at this point in the history
  • Loading branch information
@Monirzadeh
Monirzadeh committed Aug 20, 2023
1 parent eb804bc commit 49e8ba8
Show file tree
Hide file tree
Showing 3 changed files with 17 additions and 176 deletions.
4 changes: 3 additions & 1 deletion go.mod
View file
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@ go 1.20

require (
github.com/PuerkitoBio/goquery v1.8.1
github.com/bmaupin/go-epub v1.1.1-0.20230816135150-45f45a4d57ba
github.com/disintegration/imaging v1.6.2
github.com/fatih/color v1.15.0
github.com/gin-contrib/gzip v0.0.6
Expand Down Expand Up @@ -33,7 +34,7 @@ require (
github.com/swaggo/swag v1.16.1
github.com/toorop/gin-logrus v0.0.0-20210225092905-2c785434f26f
golang.org/x/crypto v0.11.0
golang.org/x/net v0.12.0
golang.org/x/net v0.13.0
golang.org/x/term v0.10.0
modernc.org/sqlite v1.24.0
)
Expand Down Expand Up @@ -82,6 +83,7 @@ require (
github.com/tdewolff/parse v2.3.4+incompatible // indirect
github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
github.com/ugorji/go/codec v1.2.11 // indirect
github.com/vincent-petithory/dataurl v1.0.0 // indirect
go.etcd.io/bbolt v1.3.7 // indirect
go.uber.org/atomic v1.11.0 // indirect
golang.org/x/arch v0.3.0 // indirect
Expand Down
8 changes: 6 additions & 2 deletions go.sum
View file
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,8 @@ github.com/PuerkitoBio/urlesc v0.0.0-20170810143723-de5bf2ad4578/go.mod h1:uGdko
github.com/andybalholm/cascadia v1.3.1/go.mod h1:R4bJ1UQfqADjvDa4P6HZHLh/3OxWWEqc0Sk8XGwHqvA=
github.com/andybalholm/cascadia v1.3.2 h1:3Xi6Dw5lHF15JtdcmAHD3i1+T8plmv7BQ/nsViSLyss=
github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU=
github.com/bmaupin/go-epub v1.1.1-0.20230816135150-45f45a4d57ba h1:KsxwiuDsAixHe+PH0uVbRGs2EVVBxyfKF/Io67gV27A=
github.com/bmaupin/go-epub v1.1.1-0.20230816135150-45f45a4d57ba/go.mod h1:Wzh2rgIAWokCBSSF4C5/Z1LuufAGu/cETNd6O+2856E=
github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=
github.com/bytedance/sonic v1.9.2 h1:GDaNjuWSGu09guE9Oql0MSTNhNCLlWwO8y/xM5BzcbM=
github.com/bytedance/sonic v1.9.2/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZXU064P/U=
Expand Down Expand Up @@ -233,6 +235,8 @@ github.com/ugorji/go/codec v1.1.7/go.mod h1:Ax+UKWsSmolVDwsd+7N3ZtXu+yMGCf907BLY
github.com/ugorji/go/codec v1.2.7/go.mod h1:WGN1fab3R1fzQlVQTkfxVtIBhWDRqOviHU95kRgeqEY=
github.com/ugorji/go/codec v1.2.11 h1:BMaWp1Bb6fHwEtbplGBGJ498wD+LKlNSl25MjdZY4dU=
github.com/ugorji/go/codec v1.2.11/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
github.com/vincent-petithory/dataurl v1.0.0 h1:cXw+kPto8NLuJtlMsI152irrVw9fRDX8AbShPRpg2CI=
github.com/vincent-petithory/dataurl v1.0.0/go.mod h1:FHafX5vmDzyP+1CQATJn7WFKc9CvnvxyvZy6I1MrG/U=
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
go.etcd.io/bbolt v1.3.3/go.mod h1:IbVyRI1SCnLcuJnV2u8VeU0CEYM7e686BmAb1XKL+uU=
go.etcd.io/bbolt v1.3.7 h1:j+zJOnnEjF/kyHlDDgGnVL/AIqIJPq8UoB2GSNfkUfQ=
Expand Down Expand Up @@ -263,8 +267,8 @@ golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug
golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
golang.org/x/net v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
golang.org/x/net v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns=
golang.org/x/net v0.12.0 h1:cfawfvKITfUsFCeJIHJrbSxpeu/E81khclypR0GVT50=
golang.org/x/net v0.12.0/go.mod h1:zEVYFnQC7m/vmpQFELhcD1EWkZlX69l4oqgmer6hfKA=
golang.org/x/net v0.13.0 h1:Nvo8UFsZ8X3BhAC9699Z1j7XQ3rsZnUUm7jfBEk1ueY=
golang.org/x/net v0.13.0/go.mod h1:zEVYFnQC7m/vmpQFELhcD1EWkZlX69l4oqgmer6hfKA=
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
Expand Down
181 changes: 8 additions & 173 deletions internal/core/ebook.go
View file
Original file line number Diff line number Diff line change
@@ -1,17 +1,14 @@
package core

import (
"archive/zip"
"fmt"
"io"
"log"
"net/http"
"os"
fp "path/filepath"
"regexp"
"strconv"
"strings"

epub "github.com/bmaupin/go-epub"
"github.com/go-shiori/shiori/internal/model"
"github.com/pkg/errors"
)
Expand All @@ -21,7 +18,7 @@ import (
// The bookmark model will be used to update the UI based on whether this function is successful or not.
func GenerateEbook(req ProcessRequest, dstPath string) (book model.Bookmark, err error) {
// variable for store generated html code
var html string
//var html string

book = req.Bookmark

Expand Down Expand Up @@ -60,175 +57,13 @@ func GenerateEbook(req ProcessRequest, dstPath string) (book model.Bookmark, err
defer os.Remove(tmpFile.Name())

// Create zip archive
epubWriter := zip.NewWriter(tmpFile)
//epubWriter := zip.NewWriter(tmpFile)
ebook := epub.NewEpub(book.Title)
ebook.SetTitle(book.Title)
ebook.AddSection(string(book.HTML), book.Title, "", "")

Check failure on line 63 in internal/core/ebook.go

View workflow job for this annotation

GitHub Actions / call-lint / golangci 

unnecessary conversion (unconvert)
ebook.EmbedImages()
ebook.Write(tmpFile.Name())

// Create the mimetype file
mimetypeWriter, err := epubWriter.Create("mimetype")
if err != nil {
return book, errors.Wrap(err, "can't create mimetype")
}
_, err = mimetypeWriter.Write([]byte("application/epub+zip"))
if err != nil {
return book, errors.Wrap(err, "can't write into mimetype file")
}

// Create the container.xml file
containerWriter, err := epubWriter.Create("META-INF/container.xml")
if err != nil {
return book, errors.Wrap(err, "can't create container.xml")
}

_, err = containerWriter.Write([]byte(`<?xml version="1.0" encoding="UTF-8"?>
<container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
<rootfiles>
<rootfile full-path="OEBPS/content.opf" media-type="application/oebps-package+xml"/>
</rootfiles>
</container>`))
if err != nil {
return book, errors.Wrap(err, "can't write into container.xml file")
}

contentOpfWriter, err := epubWriter.Create("OEBPS/content.opf")
if err != nil {
return book, errors.Wrap(err, "can't create content.opf")
}
_, err = contentOpfWriter.Write([]byte(`<?xml version="1.0" encoding="UTF-8"?>
<package xmlns="http://www.idpf.org/2007/opf" version="2.0" unique-identifier="BookId">
<metadata>
<dc:title>` + book.Title + `</dc:title>
</metadata>
<manifest>
<item id="ncx" href="toc.ncx" media-type="application/x-dtbncx+xml"/>
<item id="content" href="content.html" media-type="application/xhtml+xml"/>
<item id="id" href="../style.css" media-type="text/css"/>
</manifest>
<spine toc="ncx">
<itemref idref="content"/>
</spine>
</package>`))
if err != nil {
return book, errors.Wrap(err, "can't write into container.opf file")
}

// Create the style.css file
styleWriter, err := epubWriter.Create("style.css")
if err != nil {
return book, errors.Wrap(err, "can't create content.xml")
}
_, err = styleWriter.Write([]byte(`content {
display: block;
font-size: 1em;
line-height: 1.2;
padding-left: 0;
padding-right: 0;
text-align: justify;
margin: 0 5pt
}
img {
margin: auto;
display: block;
}`))
if err != nil {
return book, errors.Wrap(err, "can't write into style.css file")
}
// Create the toc.ncx file
tocNcxWriter, err := epubWriter.Create("OEBPS/toc.ncx")
if err != nil {
return book, errors.Wrap(err, "can't create toc.ncx")
}
_, err = tocNcxWriter.Write([]byte(`<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE ncx PUBLIC "-//NISO//DTD ncx 2005-1//EN"
"http://www.daisy.org/z3986/2005/ncx-2005-1.dtd">
<ncx xmlns="http://www.daisy.org/z3986/2005/ncx/" version="2005-1">
<head>
<meta name="dtb:uid" content="urn:uuid:12345678-1234-5678-1234-567812345678"/>
<meta name="dtb:depth" content="1"/>
<meta name="dtb:totalPageCount" content="0"/>
<meta name="dtb:maxPageNumber" content="0"/>
</head>
<docTitle>
<text>` + book.Title + `</text>
</docTitle>
<navMap>
<navPoint id="navPoint-1" playOrder="1">
<navLabel>
<text >` + book.Title + `</text>
</navLabel>
<content src="content.html"/>
</navPoint>
</navMap>
</ncx>`))
if err != nil {
return book, errors.Wrap(err, "can't write into toc.ncx file")
}

// get list of images tag in html
imageList, _ := GetImages(book.HTML)
imgRegex := regexp.MustCompile(`<img.*?src="([^"]*)".*?>`)

// Create a set to store unique image URLs
imageSet := make(map[string]bool)

// Download image in html file and generate new html
html = book.HTML
for _, match := range imgRegex.FindAllStringSubmatch(book.HTML, -1) {
imageURL := match[1]
if _, ok := imageList[imageURL]; ok && !imageSet[imageURL] {
// Add the image URL to the set
imageSet[imageURL] = true

// Download the image
resp, err := http.Get(imageURL)
if err != nil {
log.Fatal(err)
}
defer resp.Body.Close()

// Get the image data
imageData, err := io.ReadAll(resp.Body)
if err != nil {
return book, errors.Wrap(err, "can't get image from the internet")
}

fileName := fp.Base(imageURL)
filePath := "images/" + fileName
imageWriter, err := epubWriter.Create(filePath)
if err != nil {
log.Fatal(err)
}

// Write the image to the file
_, err = imageWriter.Write(imageData)
if err != nil {
return book, errors.Wrap(err, "can't create image file")
}
// Replace the image tag with the new downloaded image
html = strings.ReplaceAll(html, match[0], fmt.Sprintf(`<img src="../%s"/>`, filePath))
}
}
// Create the content.html file
contentHtmlWriter, err := epubWriter.Create("OEBPS/content.html")
if err != nil {
return book, errors.Wrap(err, "can't create content.xml")
}
_, err = contentHtmlWriter.Write([]byte("<?xml version='1.0' encoding='utf-8'?>\n<html xmlns=\"http://www.w3.org/1999/xhtml\">\n<head>\n\t<title>" + book.Title + "</title>\n\t<link href=\"../style.css\" rel=\"stylesheet\" type=\"text/css\"/>\n</head>\n<body>\n\t<h1 dir=\"auto\">" + book.Title + "</h1>" + "\n<content dir=\"auto\">\n" + html + "\n</content>" + "\n</body></html>"))
if err != nil {
return book, errors.Wrap(err, "can't write into content.html")
}
// close epub and tmpFile
err = epubWriter.Close()
if err != nil {
return book, errors.Wrap(err, "failed to close EPUB writer")
}
err = tmpFile.Close()
if err != nil {
return book, errors.Wrap(err, "failed to close temporary EPUB file")
}
// open temporary file again
tmpFile, err = os.Open(tmpFile.Name())
if err != nil {
return book, errors.Wrap(err, "can't open temporary EPUB file")
}
defer tmpFile.Close()
// if everitings go well we start move ebook to dstPath
err = MoveFileToDestination(dstPath, tmpFile)
Expand Down

0 comments on commit 49e8ba8

Please sign in to comment.