merge #5061: [webtoons] extract more metadata

- author_name
- comic_name
- episode_name
- username

gallery_dl/extractor/webtoons.py

@@ -87,23 +87,31 @@ class WebtoonsEpisodeExtractor(WebtoonsBase, GalleryExtractor):
         self.episode_no = params.get("episode_no")
 
     def metadata(self, page):
-        keywords, pos = text.extract(
-            page, '<meta name="keywords" content="', '"')
-        title, pos = text.extract(
-            page, '<meta property="og:title" content="', '"', pos)
-        descr, pos = text.extract(
-            page, '<meta property="og:description" content="', '"', pos)
+        extr = text.extract_from(page)
+        keywords = extr('<meta name="keywords" content="', '"').split(", ")
+        title = extr('<meta property="og:title" content="', '"')
+        descr = extr('<meta property="og:description" content="', '"')
+
+        if extr('<div class="author_area"', '\n'):
+            username = extr('/creator/', '"')
+            author_name = extr('<span>', '</span>')
+        else:
+            username = author_name = ""
 
         return {
-            "genre"      : self.genre,
-            "comic"      : self.comic,
-            "title_no"   : self.title_no,
-            "episode_no" : self.episode_no,
-            "title"      : text.unescape(title),
-            "episode"    : keywords.split(", ")[1],
-            "description": text.unescape(descr),
-            "lang"       : self.lang,
-            "language"   : util.code_to_language(self.lang),
+            "genre"       : self.genre,
+            "comic"       : self.comic,
+            "title_no"    : self.title_no,
+            "episode_no"  : self.episode_no,
+            "title"       : text.unescape(title),
+            "episode"     : keywords[1],
+            "comic_name"  : text.unescape(keywords[0]),
+            "episode_name": text.unescape(keywords[2]),
+            "username"    : username,
+            "author_name" : text.unescape(author_name),
+            "description" : text.unescape(descr),
+            "lang"        : self.lang,
+            "language"    : util.code_to_language(self.lang),
         }
 
     @staticmethod

test/results/webtoons.py

@@ -20,6 +20,22 @@ __tests__ = (
         "42055e44659f6ffc410b3fb6557346dfbb993df3",
         "49e1f2def04c6f7a6a3dacf245a1cd9abe77a6a9",
     ],
+
+    "author_name" : "Chris McCoy",
+    "comic"       : "safely-endangered",
+    "comic_name"  : "Safely Endangered",
+    "count"       : 5,
+    "description" : "Silly comics for silly people.",
+    "episode"     : "572",
+    "episode_name": "Ep. 572 - Earth",
+    "episode_no"  : "572",
+    "genre"       : "comedy",
+    "lang"        : "en",
+    "language"    : "English",
+    "num"         : range(1, 5),
+    "title"       : "Safely Endangered - Ep. 572 - Earth",
+    "title_no"    : "352",
+    "username"    : "safelyendangered",
 },
 
 {
@@ -37,6 +53,18 @@ __tests__ = (
     "title_no"   : "312584",
 },
 
+{
+    "#url"     : "https://www.webtoons.com/en/canvas/i-want-to-be-a-cute-anime-girl/209-the-storys-story/viewer?title_no=349416&episode_no=214",
+    "#category": ("", "webtoons", "episode"),
+    "#class"   : webtoons.WebtoonsEpisodeExtractor,
+    "#count"   : 4,
+
+    "comic_name"  : "I want to be a cute anime girl",
+    "episode_name": "209 - The story's story",
+    "username"    : "m9huj",
+    "author_name" : "Azul Crescent",
+},
+
 {
     "#url"     : "https://www.webtoons.com/en/comedy/live-with-yourself/list?title_no=919",
     "#comment" : "english",