finish bunkr downloads

bunker.go

@@ -0,0 +1,139 @@
+package main
+
+import (
+	"bufio"
+	"fmt"
+	"io"
+	"net/http"
+	"os"
+	"path/filepath"
+	"strings"
+
+	"github.com/anaskhan96/soup"
+)
+
+type BunkrAlbum struct {
+	AlbumName string
+	AlbumURL  string
+	ImageUrls []string
+	VideoUrls []string
+}
+
+// Read the "bunkrlinks.txt" file and return the links
+func ReadBunkrDownloadFile(fpath string) []string {
+	// Open the file
+	file, err := os.Open(fpath)
+	if err != nil {
+		panic(err)
+	}
+	defer file.Close()
+
+	// Read the file
+	links := []string{}
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		links = append(links, scanner.Text())
+	}
+	return links
+}
+
+// Get all images and videos from a Bunkr album
+// albumUrl: The URL of the album
+func GetBunkrAlbum(albumUrl string) BunkrAlbum {
+	// Make a GET request to the main page url
+	resp, err := http.Get(albumUrl)
+
+	if err != nil {
+		panic(err)
+	}
+
+	defer resp.Body.Close()
+
+	currentAlbum := BunkrAlbum{
+		AlbumURL: albumUrl,
+	}
+
+	// Read the response body
+	body, err := io.ReadAll(resp.Body)
+	if err != nil {
+		panic(err)
+	}
+
+	// Get all links from the page
+	medialinks := []string{}
+	doc := soup.HTMLParse(string(body))
+	links := doc.FindAll("a")
+	for _, link := range links {
+		// Save link if it contains a type of "https://bunkrrr.org/v" or "https://bunkrrr.org/i"
+		if strings.Contains(link.Attrs()["href"], "https://bunkrrr.org/v") ||
+			strings.Contains(link.Attrs()["href"], "https://bunkrrr.org/i") {
+			medialinks = append(medialinks, link.Attrs()["href"])
+		}
+	}
+
+	for _, link := range medialinks {
+		println("Found link ", link)
+	}
+
+	// Every of the links link to a page with the download link
+	for _, link := range medialinks {
+		resp, err := http.Get(link)
+		if err != nil {
+			panic(err)
+		}
+		defer resp.Body.Close()
+		body, err := io.ReadAll(resp.Body)
+		if err != nil {
+			panic(err)
+		}
+
+		// Get all video html tags
+		doc := soup.HTMLParse(string(body))
+		videos := doc.FindAll("video")
+		for _, video := range videos {
+			source := video.Find("source")
+			videourl := source.Attrs()["src"]
+			videotype := source.Attrs()["type"]
+			println("Adding video of type ", videotype, " with url ", videourl)
+			currentAlbum.VideoUrls = append(currentAlbum.VideoUrls, videourl)
+		}
+
+		// Find all image html tags with link of "*.bunkr.ru"
+		images := doc.FindAll("img")
+		for _, image := range images {
+			imageurl := image.Attrs()["src"]
+			if strings.Contains(imageurl, ".bunkr.ru") {
+				println("Adding image with url ", imageurl)
+				currentAlbum.ImageUrls = append(currentAlbum.ImageUrls, imageurl)
+			}
+		}
+
+	}
+	return currentAlbum
+}
+
+// Download a file from a URL and save it to a path
+// album: The album to download
+// path: The parent directory to save the album
+func DownloadBunkrAlbum(album BunkrAlbum, path string) {
+	println("Downloading album ", album.AlbumURL)
+	path = filepath.Join(path, strings.Split(album.AlbumURL, "/")[4])
+	// Create the directory for the album
+	os.MkdirAll(path, os.ModePerm)
+
+	downloadpath := "" // Temporary variable to store the download path
+	for i, image := range album.ImageUrls {
+		downloadpath = filepath.Join(path, fmt.Sprintf("%d.jpg", i))
+		println("Downloading image ", image)
+		downloadFile(image, downloadpath)
+	}
+	for i, video := range album.VideoUrls {
+		// Get the format of the video
+		// The format is the last part of the URL
+		// Example: https://bunkrrr.org/v/1234.mp4
+		format := strings.Split(video, ".")
+		downloadpath = filepath.Join(path, fmt.Sprintf("%d.%s", i, format[len(format)-1]))
+		println("Downloading video ", video)
+		downloadFile(video, downloadpath)
+	}
+}

bunkrlinks.txt

@@ -0,0 +1,2 @@
+https://bunkr.si/a/Yyi82pb0
+https://bunkr.fi/a/kNfpAHc9

download.go

@@ -1,13 +1,9 @@
 package main
 
 import (
-	"fmt"
 	"io"
 	"net/http"
 	"os"
-	"path/filepath"
-	"strconv"
-	"time"
 )
 
 // Download a file from a URL and save it to a path
@@ -32,27 +28,3 @@ func downloadFile(url string, path string) {
 		panic(err)
 	}
 }
-
-// Download a whole hentai
-// hentai: The hentai to download
-// path: The directory to save the hentai, will be populated with the cover and pages
-func DownloadHentai(hentai HentaiDict, path string) string {
-	path = filepath.Join(path, strconv.Itoa(hentai.ID))
-	// Check if the directory exists
-	if _, err := os.Stat(path); err == nil {
-		fmt.Println("Hentai already downloaded")
-		return path
-	}
-
-	println("Downloading hentai")
-	os.MkdirAll(path, os.ModePerm)
-	// Download the pages
-	for i, page := range hentai.Images.Pages {
-		downloadFile(page.Url, fmt.Sprintf("%s/%d.jpg", path, i))
-		// Sleep for a bit to avoid rate limiting
-		time.Sleep(time.Millisecond * 100)
-
-		println("Downloaded", i, "of", len(hentai.Images.Pages))
-	}
-	return path
-}

go.mod

@@ -3,7 +3,10 @@ module archivist_go
 go 1.23
 
 require (
+	github.com/anaskhan96/soup v1.2.5 // indirect
 	github.com/phpdave11/gofpdi v1.0.14-0.20211212211723-1f10f9844311 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
 	github.com/signintech/gopdf v0.27.0 // indirect
+	golang.org/x/net v0.0.0-20200114155413-6afb5195e5aa // indirect
+	golang.org/x/text v0.3.0 // indirect
 )

go.sum

@@ -1,7 +1,21 @@
+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/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/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/signintech/gopdf v0.27.0 h1:GEpWcZ2Gdk74+eHYINXWjs51j10r63/HxIFL9X5S7r0=
 github.com/signintech/gopdf v0.27.0/go.mod h1:d23eO35GpEliSrF22eJ4bsM3wVeQJTjXTHq5x5qGKjA=
+github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
+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=
+golang.org/x/net v0.0.0-20200114155413-6afb5195e5aa/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+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/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

main.go

@@ -2,16 +2,54 @@ package main
 
 import (
 	"os"
+	"strconv"
 )
 
+func setup() {
+	println("Setup...")
+	// Check if directories exist
+	if _, err := os.Stat("temp"); os.IsNotExist(err) {
+		os.Mkdir("temp", os.ModePerm)
+	}
+	if _, err := os.Stat("out"); os.IsNotExist(err) {
+		os.Mkdir("out", os.ModePerm)
+	}
+	if _, err := os.Stat("bunkr"); os.IsNotExist(err) {
+		os.Mkdir("bunkr", os.ModePerm)
+	}
+	print("Setup done.")
+}
+
 func main() {
-	if len(os.Args) < 2 {
-		println("Usage: go run main.go <id>")
-		os.Exit(1)
+	setup() // Create directories if not exist
+
+	if len(os.Args) == 2 {
+		println("Single argument mode: A single nhentai or bunkr album will be downloaded.")
+		arg := os.Args[1]
+		// decide if it is a nhentai or bunkr album, if its only numbers, its nhentai
+		if _, err := strconv.Atoi(arg); err == nil {
+			hentai := getByID(arg)
+			path := DownloadHentai(hentai, "temp")
+			CompilePdf(path, "out")
+		} else {
+			album := GetBunkrAlbum(arg)
+			DownloadBunkrAlbum(album, "bunkr")
+		}
+		return
+	}
+	println("Batch mode: nhentai and bunkr albums will be downloaded from the links in the files.")
+	// Download bunkr albums
+	links := ReadBunkrDownloadFile("bunkrlinks.txt")
+	for _, link := range links {
+		album := GetBunkrAlbum(link)
+		DownloadBunkrAlbum(album, "bunkr")
 	}
 
-	id := os.Args[1]
-	hentai := getByID(id)
-	path := DownloadHentai(hentai, "temp")
-	CompilePdf(path, "out")
+	// Download nhentai albums
+	links = ReadHentaiDownloadFile("hentailinks.txt")
+	for _, link := range links {
+		hentai := getByID(link)
+		path := DownloadHentai(hentai, "temp")
+		CompilePdf(path, "out")
+	}
 }

nhentai.go

@@ -1,10 +1,15 @@
 package main
 
 import (
+	"bufio"
 	"encoding/json"
 	"fmt"
 	"io"
 	"net/http"
+	"os"
+	"path/filepath"
+	"strconv"
+	"time"
 )
 
 type HentaiDict struct {
@@ -49,6 +54,23 @@ type HentaiDict struct {
 	NumFavorites int `json:"num_favorites"`
 }
 
+func ReadHentaiDownloadFile(fpath string) []string {
+	// Open the file
+	file, err := os.Open(fpath)
+	if err != nil {
+		panic(err)
+	}
+	defer file.Close()
+
+	// Read the file
+	links := []string{}
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		links = append(links, scanner.Text())
+	}
+	return links
+}
+
 func getByID(id string) HentaiDict {
 	// Perform a GET request
 	resp, err := http.Get("http://nhentai.net/api/gallery/" + id)
@@ -77,3 +99,27 @@ func getByID(id string) HentaiDict {
 	hentai.Images.Thumbnail.Url = fmt.Sprintf("https://t.nhentai.net/galleries/%s/thumb.jpg", hentai.MediaID)
 	return hentai
 }
+
+// Download a whole hentai
+// hentai: The hentai to download
+// path: The directory to save the hentai, will be populated with the cover and pages
+func DownloadHentai(hentai HentaiDict, path string) string {
+	path = filepath.Join(path, strconv.Itoa(hentai.ID))
+	// Check if the directory exists
+	if _, err := os.Stat(path); err == nil {
+		fmt.Println("Hentai already downloaded")
+		return path
+	}
+
+	println("Downloading hentai")
+	os.MkdirAll(path, os.ModePerm)
+	// Download the pages
+	for i, page := range hentai.Images.Pages {
+		downloadFile(page.Url, fmt.Sprintf("%s/%d.jpg", path, i))
+		// Sleep for a bit to avoid rate limiting
+		time.Sleep(time.Millisecond * 100)
+
+		println("Downloaded", i, "of", len(hentai.Images.Pages))
+	}
+	return path
+}

readme.md

@@ -1,15 +1,24 @@
 # archivist go
 [![Go](https://github.com/sam-k0/archivistgo/actions/workflows/go.yml/badge.svg)](https://github.com/sam-k0/archivistgo/actions/workflows/go.yml)
 
-nhentai.net downloader written in go.
+nhentai.net and bunkr.ru downloader and pdf compiler.
 
 ## Usage
 
+For the single album mode, pass an nhentaiID or bunkr-album link as an argument.
 ```sh
-./archivist_go <id>
+./archivistgo <id/bunkrlink>
 ```
 
-Will download <id> and compile to pdf.
+In case of an nhentai ID, the program will download the album and compile it into a pdf.
+In case of a bunkr link, the program will download the album's images and videos.
+
+For the batch mode, populate the files `hentainumbers.txt`and `bunkrlinks.txt` with the respective IDs and links
+and then run the progam without any arguments.
+* For bunkr links, please add the album link, and not the direct link to the image or videos.
+```sh
+./archivistgo
+```
 
 ## Build
 
@@ -19,4 +28,5 @@ go build
 
 ## Dependencies
 
-- github.com/signintech/gopdf
+- github.com/signintech/gopdf
+- github.com/anaskhan96/soup