github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[kemono] update extractor to use new domains (#7902 #7907 #7904)

Browse Source 
* Update kemono.py
* Update coomer.py
* Update kemono.py
* Fixed TypeError
    - Fixed a regex mistake I made
* Make legacy domains resolve as current domains
* Update gallery_dl/extractor/kemono.py
* remove legacy .su domain support
* fixed accidental regex change
* update docs/supportedsites
* update test results
    - (re)add legacy domain URLs
    - update URL pattern TLDs
* restore support for '.su' TLDs

---------

Co-authored-by: Mike Fährmann <mike_faehrmann@web.de>
This commit is contained in:
CautiouslyKate
2025-07-27 04:10:35 -04:00
committed by GitHub
parent 8b6fffe866
commit ed2d07181a
5 changed files with 136 additions and 121 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
gallery_dl/extractor/kemono.py
View File

@@ -6,7 +6,7 @@
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
"""Extractors for https://kemono.su/"""
"""Extractors for https://kemono.cr/"""
from .common import Extractor, Message
from .. import text, util, exception
@@ -14,7 +14,8 @@ from ..cache import cache, memcache
import itertools
import json
BASE_PATTERN = r"(?:https?://)?(?:www\.|beta\.)?(kemono|coomer)\.(su|party)"
BASE_PATTERN = (r"(?:https?://)?(?:www\.|beta\.)?"
r"(kemono|coomer)\.(cr|s[tu]|party)")
USER_PATTERN = BASE_PATTERN + r"/([^/?#]+)/user/([^/?#]+)"
HASH_PATTERN = r"/[0-9a-f]{2}/[0-9a-f]{2}/([0-9a-f]{64})"
@@ -22,17 +23,17 @@ HASH_PATTERN = r"/[0-9a-f]{2}/[0-9a-f]{2}/([0-9a-f]{64})"
class KemonoExtractor(Extractor):
"""Base class for kemono extractors"""
category = "kemono"
root = "https://kemono.su"
root = "https://kemono.cr"
directory_fmt = ("{category}", "{service}", "{user}")
filename_fmt = "{id}_{title[:180]}_{num:>02}_{filename[:180]}.{extension}"
archive_fmt = "{service}_{user}_{id}_{num}"
cookies_domain = ".kemono.su"
cookies_domain = ".kemono.cr"
def __init__(self, match):
tld = match[2]
self.category = domain = match[1]
self.root = text.root_from_url(match[0])
self.cookies_domain = f".{domain}.{tld}"
if match[1] == "coomer":
self.category = "coomer"
self.root = "https://coomer.st"
self.cookies_domain = ".coomer.st"
Extractor.__init__(self, match)
def _init(self):
@@ -44,7 +45,7 @@ class KemonoExtractor(Extractor):
self.revisions_reverse = order[0] in ("r", "a") if order else False
self._find_inline = util.re(
r'src="(?:https?://(?:kemono|coomer)\.su)?(/inline/[^"]+'
r'src="(?:https?://(?:kemono\.cr|coomer\.st))?(/inline/[^"]+'
r'|/[0-9a-f]{2}/[0-9a-f]{2}/[0-9a-f]{64}\.[^"]+)').findall
self._json_dumps = json.JSONEncoder(
ensure_ascii=False, check_circular=False,
@@ -312,10 +313,10 @@ def _validate(response):
class KemonoUserExtractor(KemonoExtractor):
"""Extractor for all posts from a kemono.su user listing"""
"""Extractor for all posts from a kemono.cr user listing"""
subcategory = "user"
pattern = USER_PATTERN + r"/?(?:\?([^#]+))?(?:$|\?|#)"
example = "https://kemono.su/SERVICE/user/12345"
example = "https://kemono.cr/SERVICE/user/12345"
def __init__(self, match):
self.subcategory = match[3]
@@ -346,10 +347,10 @@ class KemonoUserExtractor(KemonoExtractor):
class KemonoPostsExtractor(KemonoExtractor):
"""Extractor for kemono.su post listings"""
"""Extractor for kemono.cr post listings"""
subcategory = "posts"
pattern = BASE_PATTERN + r"/posts()()(?:/?\?([^#]+))?"
example = "https://kemono.su/posts"
example = "https://kemono.cr/posts"
def posts(self):
params = text.parse_query(self.groups[4])
@@ -358,10 +359,10 @@ class KemonoPostsExtractor(KemonoExtractor):
class KemonoPostExtractor(KemonoExtractor):
"""Extractor for a single kemono.su post"""
"""Extractor for a single kemono.cr post"""
subcategory = "post"
pattern = USER_PATTERN + r"/post/([^/?#]+)(/revisions?(?:/(\d*))?)?"
example = "https://kemono.su/SERVICE/user/12345/post/12345"
example = "https://kemono.cr/SERVICE/user/12345/post/12345"
def __init__(self, match):
self.subcategory = match[3]
@@ -387,14 +388,14 @@ class KemonoPostExtractor(KemonoExtractor):
class KemonoDiscordExtractor(KemonoExtractor):
"""Extractor for kemono.su discord servers"""
"""Extractor for kemono.cr discord servers"""
subcategory = "discord"
directory_fmt = ("{category}", "discord",
"{server_id} {server}", "{channel_id} {channel}")
filename_fmt = "{id}_{num:>02}_{filename}.{extension}"
archive_fmt = "discord_{server_id}_{id}_{num}"
pattern = BASE_PATTERN + r"/discord/server/(\d+)[/#](?:channel/)?(\d+)"
example = "https://kemono.su/discord/server/12345/12345"
example = "https://kemono.cr/discord/server/12345/12345"
def items(self):
_, _, server_id, channel_id = self.groups
@@ -460,7 +461,7 @@ class KemonoDiscordExtractor(KemonoExtractor):
class KemonoDiscordServerExtractor(KemonoExtractor):
subcategory = "discord-server"
pattern = BASE_PATTERN + r"/discord/server/(\d+)$"
example = "https://kemono.su/discord/server/12345"
example = "https://kemono.cr/discord/server/12345"
def items(self):
server_id = self.groups[2]
@@ -485,10 +486,10 @@ def discord_server_info(extr, server_id):
class KemonoFavoriteExtractor(KemonoExtractor):
"""Extractor for kemono.su favorites"""
"""Extractor for kemono.cr favorites"""
subcategory = "favorite"
pattern = BASE_PATTERN + r"/(?:account/)?favorites()()(?:/?\?([^#]+))?"
example = "https://kemono.su/account/favorites/artists"
example = "https://kemono.cr/account/favorites/artists"
def items(self):
self.login()
@@ -536,7 +537,7 @@ class KemonoArtistsExtractor(KemonoExtractor):
"""Extractor for kemono artists"""
subcategory = "artists"
pattern = BASE_PATTERN + r"/artists(?:\?([^#]+))?"
example = "https://kemono.su/artists"
example = "https://kemono.cr/artists"
def items(self):
params = text.parse_query(self.groups[2])
@@ -571,7 +572,7 @@ class KemonoArtistsExtractor(KemonoExtractor):
class KemonoAPI():
"""Interface for the Kemono API v1.1.0
https://kemono.su/documentation/api
https://kemono.cr/documentation/api
"""
def __init__(self, extractor):