[patreon] add 'collection' extractor (#8286)

This commit is contained in:
Mike Fährmann
2025-09-24 21:21:56 +02:00
parent 303bb5b4d2
commit 4ad2596667
3 changed files with 79 additions and 1 deletions

View File

@@ -700,7 +700,7 @@ Consider all listed sites to potentially be NSFW.
<tr id="patreon" title="patreon">
<td>Patreon</td>
<td>https://www.patreon.com/</td>
<td>Creators, Posts, User Profiles</td>
<td>Collections, Creators, Posts, User Profiles</td>
<td><a href="https://github.com/mikf/gallery-dl#cookies">Cookies</a></td>
</tr>
<tr id="pexels" title="pexels">

View File

@@ -230,6 +230,16 @@ class PatreonExtractor(Extractor):
attr["created"], "%Y-%m-%dT%H:%M:%S.%f%z")
return attr
def _collection(self, collection_id):
url = f"{self.root}/api/collection/{collection_id}"
data = self.request_json(url)
coll = data["data"]
attr = coll["attributes"]
attr["id"] = coll["id"]
attr["date"] = text.parse_datetime(
attr["created_at"], "%Y-%m-%dT%H:%M:%S.%f%z")
return attr
def _filename(self, url):
"""Fetch filename from an URL's Content-Disposition header"""
response = self.request(url, method="HEAD", fatal=False)
@@ -333,6 +343,33 @@ class PatreonExtractor(Extractor):
raise exception.AbortExtraction("Unable to extract bootstrap data")
class PatreonCollectionExtractor(PatreonExtractor):
"""Extractor for a patreon collection"""
subcategory = "collection"
directory_fmt = ("{category}", "{creator[full_name]}",
"Collections", "{collection[title]} ({collection[id]})")
pattern = r"(?:https?://)?(?:www\.)?patreon\.com/collection/(\d+)"
example = "https://www.patreon.com/collection/12345"
def posts(self):
collection_id = self.groups[0]
self.kwdict["collection"] = collection = \
self._collection(collection_id)
campaign_id = text.extr(
collection["thumbnail"]["url"], "/campaign/", "/")
url = self._build_url("posts", (
# patreon returns '400 Bad Request' without campaign_id filter
f"&filter[campaign_id]={campaign_id}"
"&filter[contains_exclusive_posts]=true"
"&filter[is_draft]=false"
f"&filter[collection_id]={collection_id}"
"&filter[include_drops]=true"
"&sort=collection_order"
))
return self._pagination(url)
class PatreonCreatorExtractor(PatreonExtractor):
"""Extractor for a creator's works"""
subcategory = "creator"

View File

@@ -191,4 +191,45 @@ __tests__ = (
"#exception": exception.NotFoundError,
},
{
"#url" : "https://www.patreon.com/collection/15764",
"#class" : patreon.PatreonCollectionExtractor,
"#range" : "1-3",
"#pattern" : (
r"https://c10.patreonusercontent.com/4/patreon-media/p/post/32798362/957d49296e4f48ef80718d0de98c15a4/eyJhIjoxLCJwIjoxfQ%3D%3D/2.jpg\?token-hash=.+",
r"ytdl:https://stream.mux.com/h4DYqFU901qkkAwYmRWZPraVk5DvTJTlcSdhGV00006KBE.m3u8\?token=ey.+",
r"https://c10.patreonusercontent.com/4/patreon-media/p/post/32798374/357b0133a476427a99169b4400ee03d4/eyJhIjoxLCJwIjoxfQ%3D%3D/2.jpg\?token-hash=.+",
),
"campaign" : {
"currency" : "USD",
"is_monthly" : True,
"is_nsfw" : False,
"name" : "YaBoyRoshi",
},
"collection" : {
"created_at" : "2023-08-31T14:10:41.000+00:00",
"date" : "dt:2023-08-31 14:10:41",
"default_layout" : "grid",
"description" : "",
"edited_at" : "2025-07-16T22:58:10.834+00:00",
"id" : "15764",
"num_draft_posts": 0,
"num_posts" : 207,
"num_posts_visible_for_creation": 207,
"num_scheduled_posts": 8,
"post_sort_type" : "custom",
"title" : "JoJo's Bizarre Adventure",
"post_ids" : list,
"thumbnail" : dict,
},
"creator" : {
"date" : "dt:2018-10-17 05:45:19",
"first_name": "YaBoyRoshi",
"full_name" : "YaBoyRoshi",
"id" : "14264111",
"vanity" : "yaboyroshi",
},
},
)