[rule34vault] update

- implement 'tags' categorization
- don't use 'totalCount' for pagination end
- update tests

gallery_dl/extractor/rule34vault.py

@@ -8,6 +8,7 @@
 
 from .booru import BooruExtractor
 from .. import text
+import collections
 
 BASE_PATTERN = r"(?:https?://)?rule34vault\.com"
 
@@ -19,11 +20,19 @@ class Rule34vaultExtractor(BooruExtractor):
     filename_fmt = "{category}_{id}.{extension}"
     per_page = 100
 
+    TAG_TYPES = {
+        1: "general",
+        2: "copyright",
+        4: "character",
+        8: "artist",
+    }
+
     def _file_url(self, post):
         post_id = post["id"]
         extension = "jpg" if post["type"] == 0 else "mp4"
-        return "{}/posts/{}/{}/{}.{}".format(
+        post["file_url"] = url = "{}/posts/{}/{}/{}.{}".format(
             self.root_cdn, post_id // 1000, post_id, post_id, extension)
+        return url
 
     def _prepare(self, post):
         post.pop("files", None)
@@ -36,6 +45,13 @@ class Rule34vaultExtractor(BooruExtractor):
         if "tags" not in post:
             post.update(self._fetch_post(post["id"]))
 
+        tags = collections.defaultdict(list)
+        for tag in post["tags"]:
+            tags[tag["type"]].append(tag["value"])
+        types = self.TAG_TYPES
+        for type, values in tags.items():
+            post["tags_" + types[type]] = values
+
     def _fetch_post(self, post_id):
         url = "{}/api/v2/post/{}".format(self.root, post_id)
         return self.request(url).json()
@@ -45,19 +61,19 @@ class Rule34vaultExtractor(BooruExtractor):
 
         if params is None:
             params = {}
-        params["CountTotal"] = True
+        params["CountTotal"] = False
         params["Skip"] = self.page_start * self.per_page
         params["take"] = self.per_page
+        threshold = self.per_page
 
         while True:
             data = self.request(url, method="POST", json=params).json()
 
             yield from data["items"]
 
-            if params["Skip"] + params["take"] > data["totalCount"]:
+            if len(data["items"]) < threshold:
                 return
-            if "cursor" in data:
+            params["cursor"] = data.get("cursor")
-                params["cursor"] = data["cursor"]
             params["Skip"] += params["take"]
 
 
@@ -65,7 +81,7 @@ class Rule34vaultPostExtractor(Rule34vaultExtractor):
     subcategory = "post"
     archive_fmt = "{id}"
     pattern = BASE_PATTERN + r"/post/(\d+)"
-    example = "https://rule34vault.com/post/399437"
+    example = "https://rule34vault.com/post/12345"
 
     def posts(self):
         return (self._fetch_post(self.groups[0]),)
@@ -76,7 +92,7 @@ class Rule34vaultPlaylistExtractor(Rule34vaultExtractor):
     directory_fmt = ("{category}", "{playlist_id}")
     archive_fmt = "p_{playlist_id}_{id}"
     pattern = BASE_PATTERN + r"/playlists/view/(\d+)"
-    example = "https://rule34vault.com/playlists/view/2"
+    example = "https://rule34vault.com/playlists/view/12345"
 
     def metadata(self):
         return {"playlist_id": self.groups[0]}
@@ -90,7 +106,7 @@ class Rule34vaultTagExtractor(Rule34vaultExtractor):
     subcategory = "tag"
     directory_fmt = ("{category}", "{search_tags}")
     archive_fmt = "t_{search_tags}_{id}"
-    pattern = BASE_PATTERN + r"/([^/?#]+)$"
+    pattern = BASE_PATTERN + r"/(?!p(?:ost|laylists)/)([^/?#]+)"
     example = "https://rule34vault.com/TAG"
 
     def metadata(self):

test/results/rule34vault.py

@@ -16,21 +16,6 @@ __tests__ = (
     "#count"  : 10,
 },
 
-{
-    "#url"  : "https://rule34vault.com/post/486545",
-    "#class": rule34vault.Rule34vaultPostExtractor,
-    "#pattern"     : r"https://r34xyz\.b-cdn.net/posts/486/486545/486545\.jpg",
-    "#sha1_content": "8f53c4c9d049842d23b51fb3cf8ce11bcbe21f07",
-},
-
-{
-    "#url"    : "https://rule34vault.com/post/382937",
-    "#comment": "video",
-    "#class"  : rule34vault.Rule34vaultPostExtractor,
-    "#pattern"     : r"https://r34xyz\.b-cdn.net/posts/382/382937/382937\.mp4",
-    "#sha1_content": "b962e3e2304139767c3792508353e6e83a85a2af",
-},
-
 {
     "#url"  : "https://rule34vault.com/playlists/view/20164",
     "#class": rule34vault.Rule34vaultPlaylistExtractor,
@@ -38,4 +23,68 @@ __tests__ = (
     "#count"  : 55,
 },
 
+{
+    "#url"    : "https://rule34vault.com/post/280517",
+    "#comment": "image",
+    "#class"  : rule34vault.Rule34vaultPostExtractor,
+    "#options": {"tags": True},
+    "#pattern"     : "https://r34xyz.b-cdn.net/posts/280/280517/280517.jpg",
+    "#sha1_content": "1e19d601b4a79c06e6f885a83a5003e7e2a17057",
+
+    "created"   : "2023-09-01T11:57:57.317331Z",
+    "date"      : "dt:2023-09-01 11:57:57",
+    "extension" : "jpg",
+    "file_url"  : "https://r34xyz.b-cdn.net/posts/280/280517/280517.jpg",
+    "filename"  : "280517",
+    "height"    : 1152,
+    "id"        : 280517,
+    "likes"     : range(3, 100),
+    "posted"    : "2023-09-01T12:01:41.008547Z",
+    "status"    : 2,
+    "type"      : 0,
+    "uploaderId": 20678,
+    "views"     : range(90, 999),
+    "width"     : 768,
+    "data": {
+        "sources": [
+            "https://trynectar.ai/view/87c98fc8-e4f3-447c-a0d3-024b1890580a",
+        ],
+    },
+    "tags": [
+        "ai generated",
+        "demon slayer",
+        "kamado nezuko",
+        "school uniform",
+        "sfw",
+    ],
+    "tags_character": [
+        "kamado nezuko",
+    ],
+    "tags_copyright": [
+        "demon slayer",
+    ],
+    "tags_general": [
+        "ai generated",
+        "school uniform",
+        "sfw",
+    ],
+    "uploader": {
+        "created"      : "2023-07-24T04:33:36.734495Z",
+        "data"         : None,
+        "displayName"  : "quick1e",
+        "emailVerified": False,
+        "id"           : 20678,
+        "role"         : 1,
+        "userName"     : "quick1e",
+    },
+},
+
+{
+    "#url"    : "https://rule34vault.com/post/382937",
+    "#comment": "video",
+    "#class"  : rule34vault.Rule34vaultPostExtractor,
+    "#urls"        : "https://r34xyz.b-cdn.net/posts/382/382937/382937.mp4",
+    "#sha1_content": "b962e3e2304139767c3792508353e6e83a85a2af",
+},
+
 )