[mangadex] add 'covers' extractor (#4994)

docs/supportedsites.md

@@ -592,7 +592,7 @@ Consider all listed sites to potentially be NSFW.
 <tr id="mangadex" title="mangadex">
     <td>MangaDex</td>
     <td>https://mangadex.org/</td>
-    <td>Authors, Chapters, Updates Feed, Library, MDLists, Manga</td>
+    <td>Authors, Chapters, Covers, Updates Feed, Library, MDLists, Manga</td>
     <td>Supported</td>
 </tr>
 <tr id="mangapark" title="mangapark">

gallery_dl/extractor/mangadex.py

@@ -96,6 +96,57 @@ class MangadexExtractor(Extractor):
         return data
 
 
+class MangadexCoversExtractor(MangadexExtractor):
+    """Extractor for mangadex manga covers"""
+    subcategory = "covers"
+    directory_fmt = ("{category}", "{manga}", "Covers")
+    filename_fmt = "{volume:>02}_{lang}.{extension}"
+    archive_fmt = "c_{cover_id}"
+    pattern = (rf"{BASE_PATTERN}/(?:title|manga)/(?!follows|feed$)([0-9a-f-]+)"
+               r"(?:/[^/?#]+)?\?tab=art")
+    example = ("https://mangadex.org/title"
+               "/01234567-89ab-cdef-0123-456789abcdef?tab=art")
+
+    def items(self):
+        base = f"{self.root}/covers/{self.uuid}/"
+        for cover in self.api.covers_manga(self.uuid):
+            data = self._transform_cover(cover)
+            name = data["cover"]
+            text.nameext_from_url(name, data)
+            data["cover_id"] = data["filename"]
+            yield Message.Directory, data
+            yield Message.Url, f"{base}{name}", data
+
+    def _transform_cover(self, cover):
+        relationships = defaultdict(list)
+        for item in cover["relationships"]:
+            relationships[item["type"]].append(item)
+        manga = self.api.manga(relationships["manga"][0]["id"])
+        for item in manga["relationships"]:
+            relationships[item["type"]].append(item)
+
+        cattributes = cover["attributes"]
+        mattributes = manga["attributes"]
+
+        return {
+            "manga"   : (mattributes["title"].get("en") or
+                         next(iter(mattributes["title"].values()))),
+            "manga_id": manga["id"],
+            "status"  : mattributes["status"],
+            "author"  : [author["attributes"]["name"]
+                         for author in relationships["author"]],
+            "artist"  : [artist["attributes"]["name"]
+                         for artist in relationships["artist"]],
+            "tags"    : [tag["attributes"]["name"]["en"]
+                         for tag in mattributes["tags"]],
+            "cover"   : cattributes["fileName"],
+            "lang"    : cattributes.get("locale"),
+            "volume"  : text.parse_int(cattributes["volume"]),
+            "date"    : text.parse_datetime(cattributes["createdAt"]),
+            "date_updated": text.parse_datetime(cattributes["updatedAt"]),
+        }
+
+
 class MangadexChapterExtractor(MangadexExtractor):
     """Extractor for manga-chapters from mangadex.org"""
     subcategory = "chapter"
@@ -239,6 +290,10 @@ class MangadexAPI():
         params = {"includes[]": ("scanlation_group",)}
         return self._call("/chapter/" + uuid, params)["data"]
 
+    def covers_manga(self, uuid):
+        params = {"manga[]": uuid}
+        return self._pagination_covers("/cover", params)
+
     def list(self, uuid):
         return self._call("/list/" + uuid, None, True)["data"]
 
@@ -374,6 +429,20 @@ class MangadexAPI():
 
         return self._pagination(endpoint, params, auth)
 
+    def _pagination_covers(self, endpoint, params=None, auth=False):
+        if params is None:
+            params = {}
+
+        lang = self.extractor.config("lang")
+        if isinstance(lang, str) and "," in lang:
+            lang = lang.split(",")
+        params["locales"] = lang
+        params["contentRating"] = None
+        params["order[volume]"] = \
+            "desc" if self.extractor.config("chapter-reverse") else "asc"
+
+        return self._pagination(endpoint, params, auth)
+
     def _pagination(self, endpoint, params, auth=False):
         config = self.extractor.config
 

test/results/mangadex.py

@@ -167,4 +167,63 @@ __tests__ = (
     "#count"   : ">= 15",
 },
 
+{
+    "#url"     : "https://mangadex.org/title/f90c4398-8aad-4f51-8a1f-024ca09fdcbc?tab=art",
+    "#class"   : mangadex.MangadexCoversExtractor,
+    "#results" : "https://mangadex.org/covers/f90c4398-8aad-4f51-8a1f-024ca09fdcbc/af3c1690-1e06-4432-909e-3e0f9ee01f68.jpg",
+
+    "artist"      : ["Arakawa Hiromu"],
+    "author"      : ["Arakawa Hiromu"],
+    "cover"       : "af3c1690-1e06-4432-909e-3e0f9ee01f68.jpg",
+    "cover_id"    : "af3c1690-1e06-4432-909e-3e0f9ee01f68",
+    "date"        : "dt:2021-05-24 17:19:13",
+    "date_updated": "dt:2021-05-24 17:19:13",
+    "extension"   : "jpg",
+    "filename"    : "af3c1690-1e06-4432-909e-3e0f9ee01f68",
+    "lang"        : "ja",
+    "manga"       : "Souten no Koumori",
+    "manga_id"    : "f90c4398-8aad-4f51-8a1f-024ca09fdcbc",
+    "status"      : "completed",
+    "volume"      : 0,
+    "tags"        : [
+        "Oneshot",
+        "Historical",
+        "Action",
+        "Martial Arts",
+        "Drama",
+        "Tragedy",
+    ],
+},
+
+{
+    "#url"     : "https://mangadex.org/title/192aa767-2479-42c1-9780-8d65a2efd36a/gachiakuta?tab=art",
+    "#class"   : mangadex.MangadexCoversExtractor,
+    "#pattern" : r"https://mangadex\.org/covers/192aa767-2479-42c1-9780-8d65a2efd36a/[\w-]+\.jpg",
+    "#count"   : 19,
+
+    "artist"      : ["Urana Kei"],
+    "author"      : ["Urana Kei"],
+    "cover_id"    : "iso:uuid",
+    "date"        : "type:datetime",
+    "date_updated": "type:datetime",
+    "extension"   : "jpg",
+    "filename"    : str,
+    "lang"        : {"ja", "fa"},
+    "manga"       : "Gachiakuta",
+    "manga_id"    : "192aa767-2479-42c1-9780-8d65a2efd36a",
+    "status"      : "ongoing",
+    "volume"      : range(1, 16),
+    "tags"        : [
+        "Monsters",
+        "Action",
+        "Comedy",
+        "Survival",
+        "Drama",
+        "Fantasy",
+        "Delinquents",
+        "Supernatural",
+        "Tragedy",
+    ],
+},
+
 )