1
0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-22 02:32:33 +01:00

[bunkr] update domain (#3391)

and improve bunkr/app.bunkr handling
This commit is contained in:
Mike Fährmann 2022-12-11 17:34:34 +01:00
parent eb94568e1f
commit 6b6f886dcf
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88
5 changed files with 35 additions and 53 deletions

View File

@ -971,7 +971,7 @@ extractor.cyberdrop.domain
Type
``string``
Default
``"auto"``
``null``
Example
``"cyberdrop.to"``
Description
@ -1717,7 +1717,7 @@ extractor.lolisafe.domain
Type
``string``
Default
``"auto"``
``null``
Description
Specifies the domain used by a ``lolisafe`` extractor
regardless of input URL.

View File

@ -55,7 +55,7 @@
},
"cyberdrop":
{
"domain": "auto"
"domain": null
},
"danbooru":
{

View File

@ -111,7 +111,7 @@ Consider all sites to be NSFW unless otherwise known.
</tr>
<tr>
<td>Bunkr</td>
<td>https://bunkr.is/</td>
<td>https://bunkr.ru/</td>
<td>Albums</td>
<td></td>
</tr>

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://bunkr.is/"""
"""Extractors for https://bunkr.ru/"""
from .lolisafe import LolisafeAlbumExtractor
from .. import text
@ -14,13 +14,13 @@ import json
class BunkrAlbumExtractor(LolisafeAlbumExtractor):
"""Extractor for bunkr.is albums"""
"""Extractor for bunkr.ru albums"""
category = "bunkr"
root = "https://bunkr.is"
pattern = r"(?:https?://)?(?:app\.)?bunkr\.(?:is|to)/a/([^/?#]+)"
root = "https://bunkr.ru"
pattern = r"(?:https?://)?(?:app\.)?bunkr\.(?:ru|is|to)/a/([^/?#]+)"
test = (
("https://bunkr.is/a/Lktg9Keq", {
"pattern": r"https://cdn\.bunkr\.is/test-テスト-\"&>-QjgneIQv\.png",
("https://bunkr.ru/a/Lktg9Keq", {
"pattern": r"https://cdn\.bunkr\.ru/test-テスト-\"&>-QjgneIQv\.png",
"content": "0c8768055e4e20e7c7259608b67799171b691140",
"keyword": {
"album_id": "Lktg9Keq",
@ -34,64 +34,46 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor):
}),
# mp4 (#2239)
("https://app.bunkr.is/a/ptRHaCn2", {
"pattern": r"https://media-files\.bunkr\.is/_-RnHoW69L\.mp4",
"pattern": r"https://media-files\.bunkr\.ru/_-RnHoW69L\.mp4",
"content": "80e61d1dbc5896ae7ef9a28734c747b28b320471",
}),
# cdn4
("https://bunkr.is/a/iXTTc1o2", {
"pattern": r"https://(cdn|media-files)4\.bunkr\.is/",
"pattern": r"https://(cdn|media-files)4\.bunkr\.ru/",
"content": "da29aae371b7adc8c5ef8e6991b66b69823791e8",
}),
("https://bunkr.to/a/Lktg9Keq"),
)
def fetch_album(self, album_id):
if "//app." in self.root:
return self._fetch_album_api(album_id)
else:
return self._fetch_album_site(album_id)
def _fetch_album_api(self, album_id):
files, data = LolisafeAlbumExtractor.fetch_album(self, album_id)
for file in files:
url = file["file"]
if url.endswith(".mp4"):
file["file"] = url.replace(
"//cdn.bunkr.is/", "//media-files.bunkr.is/", 1)
else:
file["_fallback"] = (url.replace("//cdn.", "//cdn3.", 1),)
return files, data
def _fetch_album_site(self, album_id):
url = self.root + "/a/" + self.album_id
root = self.root
try:
data = json.loads(text.extr(
self.request(url).text,
self.request(root + "/a/" + self.album_id).text,
'id="__NEXT_DATA__" type="application/json">', '<'))
album = data["props"]["pageProps"]["album"]
files = album["files"]
except Exception as exc:
self.log.debug(exc.__class__.__name__, exc)
self.root = self.root.replace("bunkr", "app.bunkr", 1)
return self._fetch_album_api(album_id)
headers = {"Referer": "https://stream.bunkr.is/"}
self.log.debug("%s: %s", exc.__class__.__name__, exc)
self.root = root.replace("://", "://app.", 1)
files, data = LolisafeAlbumExtractor.fetch_album(self, album_id)
else:
for file in files:
file["file"] = file["cdn"] + "/" + file["name"]
data = {
"album_id" : self.album_id,
"album_name" : text.unescape(album["name"]),
"description": text.unescape(album["description"]),
"count" : len(files),
}
headers = {"Referer": root.replace("://", "://stream.", 1)}
for file in files:
name = file["name"]
cdn = file["cdn"]
if name.endswith((".mp4", ".m4v", ".mov", ".webm",
".zip", ".rar", ".7z")):
cdn = cdn.replace("//cdn", "//media-files", 1)
if file["file"].endswith(
(".mp4", ".m4v", ".mov", ".webm", ".zip", ".rar", ".7z")):
file["_http_headers"] = headers
file["file"] = cdn + "/" + name
file["file"] = file["file"].replace(
"//cdn", "//media-files", 1)
return files, {
"album_id" : self.album_id,
"album_name" : text.unescape(album["name"]),
"description": text.unescape(album["description"]),
"count" : len(files),
}
return files, data

View File

@ -23,7 +23,7 @@ BASE_PATTERN = LolisafeExtractor.update({
"xbunkr": {
"root": "https://xbunkr.com",
"pattern": r"xbunkr\.com",
}
},
})
@ -47,9 +47,9 @@ class LolisafeAlbumExtractor(LolisafeExtractor):
self.album_id = match.group(match.lastindex)
domain = self.config("domain")
if domain is None or domain == "auto":
if domain == "auto":
self.root = text.root_from_url(match.group(0))
else:
elif domain:
self.root = text.ensure_http_scheme(domain)
def items(self):