New upstream version 1.31.2.upstream/1.31.2upstream

1 files changed, 66 insertions, 5 deletions

diff --git a/gallery_dl/extractor/webtoons.py b/gallery_dl/extractor/webtoons.py
index bed251b..92cf6b1 100644
--- a/gallery_dl/extractor/webtoons.py
+++ b/gallery_dl/extractor/webtoons.py
@@ -48,10 +48,11 @@ class WebtoonsBase():
 class WebtoonsEpisodeExtractor(WebtoonsBase, GalleryExtractor):
     """Extractor for an episode on webtoons.com"""
     subcategory = "episode"
-    pattern = (rf"{LANG_PATTERN}/([^/?#]+)/([^/?#]+)/[^/?#]+)"
+    pattern = (LANG_PATTERN + r"/([^/?#]+)/([^/?#]+)/[^/?#]+)"
                r"/viewer\?([^#'\"]+)")
     example = ("https://www.webtoons.com/en/GENRE/TITLE/NAME/viewer"
                "?title_no=123&episode_no=12345")
+    images_urls = []
 
     def _init(self):
         self.setup_agegate_cookies()
@@ -61,6 +62,7 @@ class WebtoonsEpisodeExtractor(WebtoonsBase, GalleryExtractor):
         self.title_no = params.get("title_no")
         self.episode_no = params.get("episode_no")
         self.page_url = f"{self.root}/{base}/viewer?{query}"
+        self.bgm = self.config("bgm", True)
 
     def metadata(self, page):
         extr = text.extract_from(page)
@@ -114,12 +116,21 @@ class WebtoonsEpisodeExtractor(WebtoonsBase, GalleryExtractor):
         elif not isinstance(quality, dict):
             quality = None
 
+        if self.bgm:
+            num = 0
+            self.paths = paths = {}
+        else:
+            num = None
+
         results = []
         for url in text.extract_iter(
                 page, 'class="_images" data-url="', '"'):
 
+            path, _, query = url.rpartition("?")
+            if num is not None:
+                num += 1
+                paths[path[path.find("/", 8):]] = num
             if quality is not None:
-                path, _, query = url.rpartition("?")
                 type = quality.get(path.rpartition(".")[2].lower())
                 if type is False:
                     url = path
@@ -130,10 +141,60 @@ class WebtoonsEpisodeExtractor(WebtoonsBase, GalleryExtractor):
         return results
 
     def assets(self, page):
+        assets = []
+
         if self.config("thumbnails", False):
             active = text.extr(page, 'class="on', '</a>')
             url = _url(text.extr(active, 'data-url="', '"'))
-            return ({"url": url, "type": "thumbnail"},)
+            assets.append({"url": url, "type": "thumbnail"})
+
+        if self.bgm:
+            if bgm := text.extr(page, "episodeBgmList:", ",\n"):
+                self._asset_bgm(assets, util.json_loads(bgm))
+
+        return assets
+
+    def _asset_bgm(self, assets, bgm_list):
+        import binascii
+        params = {
+            #  "quality"     : "MIDDLE",
+            "quality"     : "HIGH",  # no difference to 'MIDDLE'
+            "acceptCodecs": "AAC,MP3",
+        }
+        headers = {
+            "Accept"        : "application/json",
+            "Content-Type"  : "application/json",
+            "Origin"        : self.root,
+            "Referer"       : self.root + "/",
+            "Sec-Fetch-Dest": "empty",
+            "Sec-Fetch-Mode": "cors",
+            "Sec-Fetch-Site": "cross-site",
+        }
+        paths = self.paths
+
+        for bgm in bgm_list:
+            url = (f"https://apis.naver.com/audiocweb/audiocplayogwweb/play"
+                   f"/audio/{bgm['audioId']}/hls/token")
+            data = self.request_json(
+                url, params=params, headers=headers, interval=False)
+            token = data["result"]["playToken"]
+            data = util.json_loads(binascii.a2b_base64(token).decode())
+            audio = data["audioInfo"]
+            play = bgm.get("playImageUrl", "")
+            stop = bgm.get("stopImageUrl", "")
+
+            assets.append({
+                **bgm,
+                **audio,
+                "num_play": paths.get(play) or 0,
+                "num_stop": paths.get(stop) or 0,
+                "filename_play": play[play.rfind("/")+1:play.rfind(".")],
+                "filename_stop": stop[stop.rfind("/")+1:stop.rfind(".")],
+                "type": "bgm",
+                "url" : "ytdl:" + audio["url"],
+                "_ytdl_manifest": audio["type"].lower(),
+                "extension": "mp3",
+            })
 
 
 class WebtoonsComicExtractor(WebtoonsBase, Extractor):
@@ -142,7 +203,7 @@ class WebtoonsComicExtractor(WebtoonsBase, Extractor):
     categorytransfer = True
     filename_fmt = "{type}.{extension}"
     archive_fmt = "{title_no}_{type}"
-    pattern = rf"{LANG_PATTERN}/([^/?#]+)/([^/?#]+))/list\?([^#]+)"
+    pattern = LANG_PATTERN + r"/([^/?#]+)/([^/?#]+))/list\?([^#]+)"
     example = "https://www.webtoons.com/en/GENRE/TITLE/list?title_no=123"
 
     def items(self):
@@ -197,7 +258,7 @@ class WebtoonsComicExtractor(WebtoonsBase, Extractor):
 class WebtoonsArtistExtractor(WebtoonsBase, Extractor):
     """Extractor for webtoons.com artists"""
     subcategory = "artist"
-    pattern = rf"{BASE_PATTERN}/p/community/([^/?#]+)/u/([^/?#]+)"
+    pattern = BASE_PATTERN + r"/p/community/([^/?#]+)/u/([^/?#]+)"
     example = "https://www.webtoons.com/p/community/LANG/u/ARTIST"
 
     def items(self):