From a0c22ded86dd4e7fa45449f4baeec8435b258eec Mon Sep 17 00:00:00 2001 From: Leo Robinovitch Date: Thu, 21 Dec 2023 08:38:48 -0800 Subject: [PATCH] working --- .gitignore | 3 +++ go.mod | 7 +++++- go.sum | 11 +++++++++ main.go | 70 ++++++++++++++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 88 insertions(+), 3 deletions(-) diff --git a/.gitignore b/.gitignore index 485dee6..4150d84 100644 --- a/.gitignore +++ b/.gitignore @@ -1 +1,4 @@ .idea +image* +img* +out* diff --git a/go.mod b/go.mod index 4975306..b51b9cc 100644 --- a/go.mod +++ b/go.mod @@ -2,9 +2,14 @@ module github.com/robinovitch61/webtoon-dl go 1.20 -require github.com/anaskhan96/soup v1.2.5 +require ( + github.com/anaskhan96/soup v1.2.5 + github.com/signintech/gopdf v0.20.0 +) require ( + github.com/phpdave11/gofpdi v1.0.14-0.20211212211723-1f10f9844311 // indirect + github.com/pkg/errors v0.9.1 // indirect golang.org/x/net v0.0.0-20200114155413-6afb5195e5aa // indirect golang.org/x/text v0.3.0 // indirect ) diff --git a/go.sum b/go.sum index c0a8e74..7177f97 100644 --- a/go.sum +++ b/go.sum @@ -1,8 +1,18 @@ github.com/anaskhan96/soup v1.2.5 h1:V/FHiusdTrPrdF4iA1YkVxsOpdNcgvqT1hG+YtcZ5hM= github.com/anaskhan96/soup v1.2.5/go.mod h1:6YnEp9A2yywlYdM4EgDz9NEHclocMepEtku7wg6Cq3s= +github.com/davecgh/go-spew v1.1.0 h1:ZDRjVQ15GmhC3fiQ8ni8+OwkZQO4DARzQgrnXU1Liz8= github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/phpdave11/gofpdi v1.0.14-0.20211212211723-1f10f9844311 h1:zyWXQ6vu27ETMpYsEMAsisQ+GqJ4e1TPvSNfdOPF0no= +github.com/phpdave11/gofpdi v1.0.14-0.20211212211723-1f10f9844311/go.mod h1:vBmVV0Do6hSBHC8uKUQ71JGW+ZGQq74llk/7bXwjDoI= +github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0= +github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4= +github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0= +github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= +github.com/signintech/gopdf v0.20.0 h1:a1rArIMmQCAFzjjCqXPgxynTPkytMccPuGZlUU8Jorw= +github.com/signintech/gopdf v0.20.0/go.mod h1:wrLtZoWaRNrS4hphED0oflFoa6IWkOu6M3nJjm4VbO4= github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= +github.com/stretchr/testify v1.6.1 h1:hDPOHmpOpP40lSULcqw7IrRb/u7w6RpDC9399XyoNd0= github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg= golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w= golang.org/x/net v0.0.0-20200114155413-6afb5195e5aa h1:F+8P+gmewFQYRk6JoLQLwjBCTu3mcIURZfNkVweuRKA= @@ -11,4 +21,5 @@ golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5h golang.org/x/text v0.3.0 h1:g61tztE5qeGQ89tm6NTjjM9VPIm088od1l6aSorWRWg= golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c h1:dUUwHk2QECo/6vqA44rthZ8ie2QXMNeKRTHCNY2nXvo= gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= diff --git a/main.go b/main.go index 2b0d8f5..05d407a 100644 --- a/main.go +++ b/main.go @@ -1,13 +1,45 @@ package main import ( + "bytes" "fmt" "github.com/anaskhan96/soup" + "github.com/signintech/gopdf" + "image" + "io" + "net/http" "os" ) +func fetchImage(imgLink string) []byte { + req, e := http.NewRequest("GET", imgLink, nil) + if e != nil { + fmt.Println(e) + os.Exit(1) + } + req.Header.Set("Referer", "http://www.webtoons.com") + + response, err := http.DefaultClient.Do(req) + if err != nil { + panic(err) + } + defer func(Body io.ReadCloser) { + err := Body.Close() + if err != nil { + panic(err) + } + }(response.Body) + + buff := new(bytes.Buffer) + _, err = buff.ReadFrom(response.Body) + if err != nil { + panic(err) + } + return buff.Bytes() +} + func main() { - resp, err := soup.Get("https://www.webtoons.com/en/thriller/bastard/ep-0/viewer?title_no=485&episode_no=1") + resp, err := soup.Get("https://www.webtoons.com/en/romance/down-to-earth/s2-episode-169/viewer?title_no=1817&episode_no=169") if err != nil { fmt.Println(fmt.Sprintf("Error fetching page: %v", err)) os.Exit(1) @@ -18,5 +50,39 @@ func main() { for _, img := range imgs { imgLinks = append(imgLinks, img.Attrs()["data-url"]) } - println(imgLinks[0]) + println(fmt.Sprintf("Found %d images", len(imgLinks))) + + pdf := gopdf.GoPdf{} + pdf.Start(gopdf.Config{Unit: gopdf.UnitPT, PageSize: *gopdf.PageSizeA4}) + for _, imgLink := range imgLinks { + fmt.Println(imgLink) + img := fetchImage(imgLink) + holder, err := gopdf.ImageHolderByBytes(img) + if err != nil { + panic(err) + } + + d, _, err := image.DecodeConfig(bytes.NewReader(img)) + if err != nil { + panic(err) + } + + // gopdf assumes dpi 128 https://github.com/signintech/gopdf/issues/168 + // W and H are in points, 1 point = 1/72 inch + // convert pixels (Width and Height) to ifrom nches, then to points + // subtract 1 to account for small margins + pdf.AddPageWithOption(gopdf.PageOption{PageSize: &gopdf.Rect{ + W: float64(d.Width)*72/128 - 1, + H: float64(d.Height)*72/128 - 1, + }}) + err = pdf.ImageByHolder(holder, 0, 0, nil) + if err != nil { + panic(err) + } + } + + err = pdf.WritePdf("out.pdf") + if err != nil { + panic(err) + } }