[luscious] use new 'html' attribute in API responses

gallery_dl/extractor/luscious.py

@@ -23,7 +23,7 @@ class LusciousAlbumExtractor(Extractor):
                 r"(?:pictures/album|albums)/([^/]+_(\d+))")]
     test = [("https://luscious.net/c/hentai_manga/albums/okinami-no-koigokoro_277031/view/", {
         "url": "7e4984a271a1072ac6483e4228a045895aff86f3",
-        "keyword": "026f4dc2e17aa59f97c9b9d8e68fc52b7c900603",
+        "keyword": "f3087f8e5c84e3f52fcd7d672cf0e6beae821837",
         "content": "b3a747a6464509440bd0ff6d1267e6959f8d6ff3",
     })]
 
@@ -51,33 +51,35 @@ class LusciousAlbumExtractor(Extractor):
             (None      , '<p>Section:', ''),
             ("section" , '>', '<'),
             (None      , '<p>Language:', ''),
-            ("language", '\n                            ', ' '),
+            ("language", '', ' '),
-            ("artist"  , 'rtist: ', '\n'),
+            ("artist"  , 'rtist:</strong>\n', '\n'),
         ), values={"gallery-id": self.gid})
         data["lang"] = iso639_1.language_to_code(data["language"])
-        _, pos = text.extract(page, 'ic_container', '')
+        data["artist"] = (data["artist"] or "").strip()
-        self.imageurl = text.extract(page, '<a href="', '"', pos)[0]
         return data
 
     def get_images(self):
-        """Collect image-urls and -metadata"""
+        pnum = 1
-        url = self.imageurl
+        inum = 1
-        num = 1
+        apiurl = ("https://luscious.net/c/{}/pictures/album/{}/page/{{}}/.json"
+                  "/?style=default").format(self.section, self.gpart)
         while True:
-            page = self.request(urljoin("https://luscious.net", url)).text
+            data = self.request(apiurl.format(pnum)).json()
-            url, pos = text.extract(page, '<link rel="next" href="', '"')
+            page = data["html"]
-            data = text.extract_all(page, (
+            pos  = 0
-                (None    , '<img id="single_picture"', ''),
+            while True:
-                ("width" , 'width="', '"'),
+                imgid, pos = text.extract(page, 'container" id="', '"', pos)
-                ("height", 'height="', '"'),
+                if not imgid:
-                ("name"  , 'title="', '"'),
+                    break
-                (None    , 'image_option_icons', ''),
+                url  , pos = text.extract(page, 'data-src="', '"', pos)
-                (None    , '<a href="', '"'),
+                title, pos = text.extract(page, 'alt="', '"', pos)
-                ("image" , '<a href="', '"'),
+                yield re.sub(r"\.\d+x\d+(\.[a-z]+)$", r"\1", url), {
-            ), pos, values={"num": num})[0]
+                    "num": inum,
-            image = data["image"]
+                    "name": title,
-            data["extension"] = image[image.rfind(".")+1:]
+                    "extension": url[url.rfind(".")+1:],
-            yield urljoin("https:", image), data
+                    "image-id": imgid[8:]
-            if url.startswith("/c/-/"):
+                }
+                inum += 1
+            if data["paginator_complete"]:
                 return
-            num += 1
+            pnum += 1