From 8a638013112a8213129aa5e3083fc6df92080919 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Sat, 17 Feb 2024 18:19:16 +0100
Subject: [PATCH] [vsco] add 'spaces' extractor (#5202)

for spaces listed on a user page
---
 gallery_dl/extractor/vsco.py | 34 ++++++++++++++++++++++++++++++++--
 scripts/supportedsites.py    |  3 +++
 test/results/vsco.py         | 11 +++++++++++
 3 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/gallery_dl/extractor/vsco.py b/gallery_dl/extractor/vsco.py
index c48a8b5b..41141c6f 100644
--- a/gallery_dl/extractor/vsco.py
+++ b/gallery_dl/extractor/vsco.py
@@ -139,8 +139,8 @@ class VscoCollectionExtractor(VscoExtractor):
     subcategory = "collection"
     directory_fmt = ("{category}", "{user}", "collection")
     archive_fmt = "c_{user}_{id}"
-    pattern = USER_PATTERN + r"/collection/"
-    example = "https://vsco.co/USER/collection/12345"
+    pattern = USER_PATTERN + r"/collection"
+    example = "https://vsco.co/USER/collection/1"
 
     def images(self):
         url = "{}/{}/collection/1".format(self.root, self.user)
@@ -208,6 +208,36 @@ class VscoSpaceExtractor(VscoExtractor):
             data = self.request(url, params=params, headers=headers).json()
 
 
+class VscoSpacesExtractor(VscoExtractor):
+    """Extractor for a vsco.co user's spaces"""
+    subcategory = "spaces"
+    pattern = USER_PATTERN + r"/spaces"
+    example = "https://vsco.co/USER/spaces"
+
+    def items(self):
+        url = "{}/{}/spaces".format(self.root, self.user)
+        data = self._extract_preload_state(url)
+
+        tkn = data["users"]["currentUser"]["tkn"]
+        uid = data["sites"]["siteByUsername"][self.user]["site"]["userId"]
+
+        headers = {
+            "Accept"       : "application/json",
+            "Referer"      : url,
+            "Content-Type" : "application/json",
+            "Authorization": "Bearer " + tkn,
+        }
+        # this would theoretically need to be paginated
+        url = "{}/grpc/spaces/user/{}".format(self.root, uid)
+        data = self.request(url, headers=headers).json()
+
+        for space in data["spacesWithRoleList"]:
+            space = space["space"]
+            url = "{}/spaces/{}".format(self.root, space["id"])
+            space["_extractor"] = VscoSpaceExtractor
+            yield Message.Queue, url, space
+
+
 class VscoImageExtractor(VscoExtractor):
     """Extractor for individual images on vsco.co"""
     subcategory = "image"
diff --git a/scripts/supportedsites.py b/scripts/supportedsites.py
index e12b65c2..2a5f24ed 100755
--- a/scripts/supportedsites.py
+++ b/scripts/supportedsites.py
@@ -290,6 +290,9 @@ SUBCATEGORY_MAP = {
     "vk": {
         "tagged": "Tagged Photos",
     },
+    "vsco": {
+        "spaces": "",
+    },
     "wallhaven": {
         "collections": "",
         "uploads"    : "",
diff --git a/test/results/vsco.py b/test/results/vsco.py
index 721ebd86..ed42f1fa 100644
--- a/test/results/vsco.py
+++ b/test/results/vsco.py
@@ -46,6 +46,17 @@ __tests__ = (
     "#count"   : range(100, 150),
 },
 
+{
+    "#url"     : "https://vsco.co/vscotest39/spaces",
+    "#category": ("", "vsco", "spaces"),
+    "#class"   : vsco.VscoSpacesExtractor,
+    "#urls"    : (
+        "https://vsco.co/spaces/62991a535a9ee215340fa2b0",
+        "https://vsco.co/spaces/62b35bfb54f97cbfbd5c1e62",
+        "https://vsco.co/spaces/629674a6875ebddb8f1320c1",
+    ),
+},
+
 {
     "#url"     : "https://vsco.co/erenyildiz/media/5d34b93ef632433030707ce2",
     "#category": ("", "vsco", "image"),