Merge pull request #9 from vt-idiot/r18d

R18d
vt-idiot · Oct 17, 2023 · 883a0fb · 883a0fb
2 parents 760376a + fdceef2
commit 883a0fb
Show file tree

Hide file tree

Showing 4 changed files with 108 additions and 114 deletions.
diff --git a/pkg/scrape/javbus.go b/pkg/scrape/javbus.go
diff --git a/pkg/scrape/r18d.go b/pkg/scrape/r18d.go
@@ -0,0 +1,102 @@
+package scrape
+
+import (
+	"html"
+	"strconv"
+	"strings"
+
+	"github.com/tidwall/gjson"
+	"github.com/xbapps/xbvr/pkg/models"
+	"github.com/go-resty/resty/v2"
+)
+
+func ScrapeR18D(out *[]models.ScrapedScene, queryString string) error {
+	scenes := strings.Split(queryString, ",")
+	for _, v := range scenes {
+		sc := models.ScrapedScene{}
+		sc.SceneType = "VR"
+
+		r, _ := resty.New().R().Get("https://r18.dev/videos/vod/movies/detail/-/combined=" + v + "/json")
+		JsonMetadata := r.String()
+
+		content_id := gjson.Get(JsonMetadata, "content_id").String()
+		sc.HomepageURL = "https://www.dmm.co.jp/en/digital/videoa/-/detail/=/cid=" + content_id + "/"
+
+		// Title
+		if gjson.Get(JsonMetadata, "title_en_is_machine_translation").String() == "false" {
+			sc.Title = strings.Replace(strings.TrimSpace(html.UnescapeString(gjson.Get(JsonMetadata, "title_en").String())), "[VR] ", "", -1)
+		} else {
+			sc.Title = gjson.Get(JsonMetadata, "content_id").String()
+		}
+
+		// Studio
+		sc.Studio = gjson.Get(JsonMetadata, "maker_name_en").String()
+
+		// Date
+		sc.Released = gjson.Get(JsonMetadata, "release_date").String()
+
+		// Time
+		tmpDuration, err := strconv.Atoi(gjson.Get(JsonMetadata, "runtime_mins").String())
+		if err == nil {
+			sc.Duration = tmpDuration
+		}
+
+		// Covers
+		coverimgs := gjson.Get(JsonMetadata, "jacket_full_url")
+		sc.Covers = append(sc.Covers, strings.TrimSpace(html.UnescapeString(coverimgs.String())))
+
+		// Gallery
+		galleryimgs := gjson.Get(JsonMetadata, "gallery.#.image_full")
+		for _, name := range galleryimgs.Array() {
+			sc.Gallery = append(sc.Gallery, strings.TrimSpace(html.UnescapeString(name.String())))
+		}
+
+		// Cast
+		actornames := gjson.Get(JsonMetadata, "actresses.#.name_romaji")
+		for _, name := range actornames.Array() {
+			sc.Cast = append(sc.Cast, strings.TrimSpace(html.UnescapeString(name.String())))
+		}
+
+		// Tags
+		// Skipping some very generic and useless tags
+		skiptags := map[string]bool{
+			"Featured Actress":       true,
+			"VR Exclusive":           true,
+			"High-Quality VR":        true,
+			"Exclusive Distribution": true,
+		}
+
+		// JSON dump from R18's final days shows "女子校生" replaced with "Academy Uniform" instead of "Schoolgirl" - r18.dev seems to follow the same mapping for FANZA category 1018 - get your credit card compliance puritanism out of my porn, I don't need "Academy Uniform" and "Uniform" tagged together lmao
+		joshikosei := "Academy Uniform"
+
+		taglist := gjson.Get(JsonMetadata, "categories.#.name_en")
+		for _, name := range taglist.Array() {
+			if !skiptags[name.Str] {
+				if name.Str == joshikosei {
+					sc.Tags = append(sc.Tags, "schoolgirl")
+				} else {
+					sc.Tags = append(sc.Tags, strings.TrimSpace(html.UnescapeString(name.String())))
+				}
+			}
+		}
+		sc.Tags = append(sc.Tags, "JAVR")
+		sc.Tags = append(sc.Tags, "R18.dev")
+
+		// Scene ID and Site
+		dvdID := gjson.Get(JsonMetadata, "dvd_id").String()
+		if dvdID == "----" || dvdID == "" {
+			sc.SceneID = content_id
+			sc.SiteID = content_id
+			sc.Site = gjson.Get(JsonMetadata, "label_name_en").String()
+		} else {
+			sc.SceneID = dvdID
+			sc.SiteID = dvdID
+			sc.Site = strings.Split(dvdID, "-")[0]
+		}
+
+		if sc.SceneID != "" {
+			*out = append(*out, sc)
+		}
+	}
+	return nil
+}
diff --git a/pkg/tasks/content.go b/pkg/tasks/content.go
@@ -347,9 +347,9 @@ func ScrapeJAVR(queryString string, scraper string) {
 		if scraper == "javlibrary" {
 			tlog.Infof("Scraping JavLibrary")
 			scrape.ScrapeJavLibrary(&collectedScenes, queryString)
-		} else if scraper == "javbus" {
-			tlog.Infof("Scraping JavBus")
-			scrape.ScrapeJavBus(&collectedScenes, queryString)
+		} else if scraper == "r18d" {
+			tlog.Infof("Scraping R18.dev")
+			scrape.ScrapeR18D(&collectedScenes, queryString)
 		} else if scraper == "javland" {
 			tlog.Infof("Scraping JavLand")
 			scrape.ScrapeJavLand(&collectedScenes, queryString)

diff --git a/ui/src/views/options/sections/OptionsSceneCreate.vue b/ui/src/views/options/sections/OptionsSceneCreate.vue
@@ -6,13 +6,15 @@
         <b-field grouped>
           <b-select placeholder="Select scraper" v-model="javrScraper">
             <option value="javdatabase">javdatabase.com</option>
+            <option value="r18d">r18.dev</option>
             <option value="javlibrary">javlibrary.com</option>
-            <option value="javbus">javbus.com</option>
             <option value="javland">jav.land</option>
           </b-select>
           <b-input v-model="javrQuery" placeholder="ID (xxxx-001)" type="search"></b-input>
           <b-button class="button is-primary" v-on:click="scrapeJAVR()">{{$t('Go')}}</b-button>
         </b-field>
+        <br>
+        <span>R18.dev scraper requires FANZA content ID, e.g. 84vrkm00139</span>
       </div>
     </div>