[yiffverse] add support (#6611)

docs/supportedsites.md

@@ -1081,6 +1081,12 @@ Consider all listed sites to potentially be NSFW.
     <td>Galleries, User Profiles</td>
     <td></td>
 </tr>
+<tr>
+    <td>Yiff verse</td>
+    <td>https://yiffverse.com/</td>
+    <td>Playlists, Posts, Tag Searches</td>
+    <td></td>
+</tr>
 <tr>
     <td>Zerochan</td>
     <td>https://www.zerochan.net/</td>

gallery_dl/extractor/__init__.py

@@ -195,6 +195,7 @@ modules = [
     "wikimedia",
     "xhamster",
     "xvideos",
+    "yiffverse",
     "zerochan",
     "zzup",
     "booru",

gallery_dl/extractor/yiffverse.py

@@ -0,0 +1,157 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2024 Mike Fährmann
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+
+"""Extractors for https://yiffverse.com/"""
+
+from .booru import BooruExtractor
+from .. import text
+import collections
+
+BASE_PATTERN = r"(?:https?://)?(?:www\.)?yiffverse\.com"
+
+
+class YiffverseExtractor(BooruExtractor):
+    category = "yiffverse"
+    root = "https://yiffverse.com"
+    root_cdn = "https://furry34com.b-cdn.net"
+    filename_fmt = "{category}_{id}.{extension}"
+    per_page = 30
+
+    TAG_TYPES = {
+        None: "general",
+        1   : "general",
+        2   : "copyright",
+        4   : "character",
+        8   : "artist",
+    }
+    FORMATS = (
+        ("100", "mov.mp4"),
+        ("101", "mov720.mp4"),
+        ("102", "mov480.mp4"),
+        ("10" , "pic.jpg"),
+    )
+
+    def _file_url(self, post):
+        files = post["files"]
+        for fmt, extension in self.FORMATS:
+            if fmt in files:
+                break
+        else:
+            fmt = next(iter(files))
+
+        post_id = post["id"]
+        root = self.root_cdn if files[fmt][0] else self.root
+        post["file_url"] = url = "{}/posts/{}/{}/{}.{}".format(
+            root, post_id // 1000, post_id, post_id, extension)
+        post["format_id"] = fmt
+        post["format"] = extension.partition(".")[0]
+
+        return url
+
+    def _prepare(self, post):
+        post.pop("files", None)
+        post["date"] = text.parse_datetime(
+            post["created"], "%Y-%m-%dT%H:%M:%S.%fZ")
+        post["filename"], _, post["format"] = post["filename"].rpartition(".")
+        if "tags" in post:
+            post["tags"] = [t["value"] for t in post["tags"]]
+
+    def _tags(self, post, _):
+        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()
+
+    def _pagination(self, endpoint, params=None):
+        url = "{}/api{}".format(self.root, endpoint)
+
+        if params is None:
+            params = {}
+        params["sortOrder"] = 1
+        params["status"] = 2
+        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 len(data["items"]) < threshold:
+                return
+            params["cursor"] = data.get("cursor")
+
+
+class YiffversePostExtractor(YiffverseExtractor):
+    subcategory = "post"
+    archive_fmt = "{id}"
+    pattern = BASE_PATTERN + r"/post/(\d+)"
+    example = "https://yiffverse.com/post/12345"
+
+    def posts(self):
+        return (self._fetch_post(self.groups[0]),)
+
+
+class YiffversePlaylistExtractor(YiffverseExtractor):
+    subcategory = "playlist"
+    directory_fmt = ("{category}", "{playlist_id}")
+    archive_fmt = "p_{playlist_id}_{id}"
+    pattern = BASE_PATTERN + r"/playlist/(\d+)"
+    example = "https://yiffverse.com/playlist/12345"
+
+    def metadata(self):
+        return {"playlist_id": self.groups[0]}
+
+    def posts(self):
+        endpoint = "/v2/post/search/playlist/" + self.groups[0]
+        return self._pagination(endpoint)
+
+
+class YiffverseTagExtractor(YiffverseExtractor):
+    subcategory = "tag"
+    directory_fmt = ("{category}", "{search_tags}")
+    archive_fmt = "t_{search_tags}_{id}"
+    pattern = BASE_PATTERN + r"/(?:tag/([^/?#]+))?(?:/?\?([^#]+))?(?:$|#)"
+    example = "https://yiffverse.com/tag/TAG"
+
+    def _init(self):
+        tag, query = self.groups
+        params = text.parse_query(query)
+
+        self.tags = tags = []
+        if tag:
+            tags.append(text.unquote(tag))
+        if "tags" in params:
+            tags.extend(params["tags"].split("|"))
+
+        type = params.get("type")
+        if type == "video":
+            self.type = 1
+        elif type == "image":
+            self.type = 0
+        else:
+            self.type = None
+
+    def metadata(self):
+        return {"search_tags": " ".join(self.tags)}
+
+    def posts(self):
+        endpoint = "/v2/post/search/root"
+        params = {"includeTags": [t.replace("_", " ") for t in self.tags]}
+        if self.type is not None:
+            params["type"] = self.type
+        return self._pagination(endpoint, params)

scripts/supportedsites.py

@@ -160,6 +160,7 @@ CATEGORY_MAP = {
     "xhamster"       : "xHamster",
     "xvideos"        : "XVideos",
     "yandere"        : "yande.re",
+    "yiffverse"      : "Yiff verse",
 }
 
 SUBCATEGORY_MAP = {

test/results/yiffverse.py

@@ -0,0 +1,78 @@
+# -*- coding: utf-8 -*-
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+
+from gallery_dl.extractor import yiffverse
+
+
+__tests__ = (
+{
+    "#url"    : "https://yiffverse.com/post/574342",
+    "#comment": "image",
+    "#class"  : yiffverse.YiffversePostExtractor,
+    "#options"     : {"tags": True},
+    "#urls"        : "https://yiffverse.com/posts/574/574342/574342.pic.jpg",
+    "#sha1_content": "0f169fddbd320eae904508f83a722bb3633ad507",
+
+    "created"  : "2024-12-06T13:55:24.483002Z",
+    "date"     : "dt:2024-12-06 13:55:24",
+    "extension": "jpg",
+    "file_url" : "https://yiffverse.com/posts/574/574342/574342.pic.jpg",
+    "filename" : "574342",
+    "format"   : "pic",
+    "format_id": "10",
+    "height"   : 862,
+    "id"       : 574342,
+    "likes"    : range(5, 100),
+    "posted"   : "2024-12-06T13:55:55.299953Z",
+    "status"   : 2,
+    "type"     : 0,
+    "tags"        : list,
+    "tags_general": list,
+    "tags_artist" : ["imanika"],
+    "uploaderId"  : 2,
+    "width"       : 950,
+    "data"        : {
+        "sources": [
+            "https://www.furaffinity.net/view/59071676/",
+            "https://www.furaffinity.net/user/imanika/",
+            "https://d.furaffinity.net/art/imanika/1733430246/1733430246.imanika_dream_girl_ych_slot1_web.jpg",
+        ],
+    },
+    "uploader"    : {
+        "created"      : "2021-07-04T15:01:03.110916Z",
+        "data"         : None,
+        "displayName"  : "agent.e621-uploader",
+        "emailVerified": False,
+        "id"           : 2,
+        "role"         : 3,
+        "userName"     : "agent.e621-uploader",
+    },
+},
+
+{
+    "#url"    : "https://yiffverse.com/post/575680",
+    "#comment": "video",
+    "#class"  : yiffverse.YiffversePostExtractor,
+    "#urls"        : "https://yiffverse.com/posts/575/575680/575680.mov.mp4",
+    "#sha1_content": "8952fc794e58c531b4e3b01cfe9e14b1c59ad9ef",
+},
+
+{
+    "#url"  : "https://yiffverse.com/tag/tree",
+    "#class": yiffverse.YiffverseTagExtractor,
+    "#pattern": r"https://yiffverse\.com/posts/\d+/\d+/\d+\.(pic\.jpg|mov\d*\.mp4)",
+    "#range"  : "1-10",
+    "#count"  : 10,
+},
+
+{
+    "#url"  : "https://yiffverse.com/playlist/6842",
+    "#class": yiffverse.YiffversePlaylistExtractor,
+    "#pattern": r"https://(yiffverse\.com|furry34com\.b-cdn\.net)/posts/\d+/\d+/\d+\.mov(720)?\.mp4",
+    "#count"  : 25,
+},
+
+)