[luscious] support new album URLs + small fixes

gallery_dl/extractor/luscious.py

@@ -10,7 +10,6 @@
 
 from .common import Extractor, Message
 from .. import text, iso639_1
-from urllib.parse import urljoin
 import re
 
 class LusciousAlbumExtractor(Extractor):
@@ -19,17 +18,24 @@ class LusciousAlbumExtractor(Extractor):
     subcategory = "album"
     directory_fmt = ["{category}", "{gallery-id} {title}"]
     filename_fmt = "{category}_{gallery-id}_{num:>03}.{extension}"
-    pattern = [(r"(?:https?://)?(?:www\.)?luscious\.net/c/([^/]+)/"
-                r"(?:pictures/album|albums)/([^/]+_(\d+))")]
-    test = [("https://luscious.net/c/hentai_manga/albums/okinami-no-koigokoro_277031/view/", {
-        "url": "7e4984a271a1072ac6483e4228a045895aff86f3",
-        "keyword": "f3087f8e5c84e3f52fcd7d672cf0e6beae821837",
-        "content": "b3a747a6464509440bd0ff6d1267e6959f8d6ff3",
-    })]
+    pattern = [(r"(?:https?://)?(?:www\.)?luscious\.net/"
+                r"(?:c/[^/]+/)?(?:pictures/album|albums)/([^/]+_(\d+))")]
+    test = [
+        ("https://luscious.net/c/hentai_manga/albums/okinami-no-koigokoro_277031/view/", {
+            "url": "7e4984a271a1072ac6483e4228a045895aff86f3",
+            "keyword": "3b3d36b355fa6a1a6c24be374ae16e6e9b0c729e",
+            "content": "b3a747a6464509440bd0ff6d1267e6959f8d6ff3",
+        }),
+        ("https://luscious.net/albums/okinami-no-koigokoro_277031/", {
+            "url": "7e4984a271a1072ac6483e4228a045895aff86f3",
+            "keyword": "3b3d36b355fa6a1a6c24be374ae16e6e9b0c729e",
+        }),
+    ]
 
     def __init__(self, match):
         Extractor.__init__(self)
-        self.section, self.gpart, self.gid = match.groups()
+        self.gpart, self.gid = match.groups()
+        self.section = "x"
 
     def items(self):
         data = self.get_job_metadata()
@@ -41,24 +47,26 @@ class LusciousAlbumExtractor(Extractor):
 
     def get_job_metadata(self):
         """Collect metadata for extractor-job"""
-        url = "https://luscious.net/c/{}/albums/{}/view/".format(
-            self.section, self.gpart)
+        url = "https://luscious.net/albums/" + self.gpart + "/"
         page = self.request(url).text
-        data, pos = text.extract_all(page, (
+        data = text.extract_all(page, (
             ("title"   , '"og:title" content="', '"'),
+            ("tags"    , '<meta name="keywords" content="', '"'),
+            ("com"     , "'community': '", "'"),
             (None      , '<li class="user_info">', ''),
             ("count"   , '<p>', ' '),
             (None      , '<p>Section:', ''),
             ("section" , '>', '<'),
-            (None      , '<p>Language:', ''),
-            ("language", '', ' '),
-            ("artist"  , 'rtist:</strong>\n', '\n'),
-        ), values={"gallery-id": self.gid})
+            ("language", '<p>Language:', ' '),
+        ), values={"gallery-id": self.gid})[0]
         data["lang"] = iso639_1.language_to_code(data["language"])
-        data["artist"] = (data["artist"] or "").strip()
+        data["artist"] = text.extract(data["tags"], "rtist: ", ",")[0] or ""
+        self.section = data["com"]
+        del data["com"]
         return data
 
     def get_images(self):
+        """Collect image-urls and -metadata"""
         pnum = 1
         inum = 1
         apiurl = ("https://luscious.net/c/{}/pictures/album/{}/page/{{}}/.json"