[webtoons] extract 'num_play' & 'num_stop' for background music (#8733 #8755)

* [webtoons] play_image and stop_image in background music
* [webtoons] add play_image and stop_image fields to test results
* [webtoons]: flake8
* [webtoons]: flake8 (2)

* update & improve
    - remove global 'images_urls'
    - move enumerate loop into images() extraction
* simplify 'play_image' etc extraction
* rename 'play_image' etc
    - num_play
    - num_stop
    - filename_play
    - filename_stop

---------

Co-authored-by: Mike Fährmann <mike_faehrmann@web.de>

gallery_dl/extractor/webtoons.py

@@ -52,6 +52,7 @@ class WebtoonsEpisodeExtractor(WebtoonsBase, GalleryExtractor):
                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
@@ -137,7 +148,7 @@ class WebtoonsEpisodeExtractor(WebtoonsBase, GalleryExtractor):
             url = _url(text.extr(active, 'data-url="', '"'))
             assets.append({"url": url, "type": "thumbnail"})
 
-        if self.config("bgm", True):
+        if self.bgm:
             if bgm := text.extr(page, "episodeBgmList:", ",\n"):
                 self._asset_bgm(assets, util.json_loads(bgm))
 
@@ -159,6 +170,7 @@ class WebtoonsEpisodeExtractor(WebtoonsBase, GalleryExtractor):
             "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"
@@ -168,10 +180,16 @@ class WebtoonsEpisodeExtractor(WebtoonsBase, GalleryExtractor):
             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(),

test/results/webtoons.py

@@ -160,6 +160,10 @@ __tests__ = (
     "lang"            : "en",
     "language"        : "English",
     "num"             : 0,
+    "num_play"        : 17,
+    "num_stop"        : 0,
+    "filename_play"   : "1475724249934679214",
+    "filename_stop"   : "",
     "objectType"      : "mp4a.40.2",
     "originalFileSize": 0,
     "playImageUrl"    : "/20161006_271/1475724249957QlGUF_JPEG/1475724249934679214.jpg",