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

[bunkr] fix extraction (#5088, #5151, #5153)

Browse Source 
- remove legacy code
- map legacy domains to bunkr.sk
- use input URL domain for newer domains
- update tests (some files got slightly modified or deleted)
This commit is contained in:
Mike Fährmann
2024-02-11 22:36:03 +01:00
parent dcc6e3f65c
commit 06cb518d97
2 changed files with 87 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

70
gallery_dl/extractor/bunkr.py
View File

@@ -10,24 +10,22 @@
from .lolisafe import LolisafeAlbumExtractor from .lolisafe import LolisafeAlbumExtractor
from .. import text from .. import text
from urllib.parse import urlsplit, urlunsplit
BASE_PATTERN = ( BASE_PATTERN = (
r"(?:https?://)?(?:app\.)?bunkr+" r"(?:https?://)?(?:app\.)?(bunkr+"
r"\.(?:sk|[rs]u|la|is|to|si|ac|black|cat|media|red|site|ws)" r"\.(?:s[kiu]|ru|la|is|to|ac|black|cat|media|red|site|ws))"
) )
MEDIA_DOMAIN_OVERRIDES = { LEGACY_DOMAINS = {
"cdn9.bunkr.ru" : "c9.bunkr.ru", "bunkr.ru",
"cdn12.bunkr.ru": "media-files12.bunkr.la", "bunkrr.ru",
"cdn-pizza.bunkr.ru": "pizza.bunkr.ru", "bunkr.su",
"bunkrr.su",
"bunkr.la",
"bunkr.is",
"bunkr.to",
} }
CDN_HOSTED_EXTENSIONS = (
".mp4", ".m4v", ".mov", ".webm", ".mkv", ".ts", ".wmv",
".zip", ".rar", ".7z",
)
class BunkrAlbumExtractor(LolisafeAlbumExtractor): class BunkrAlbumExtractor(LolisafeAlbumExtractor):
"""Extractor for bunkr.sk albums""" """Extractor for bunkr.sk albums"""
@@ -36,6 +34,12 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor):
pattern = BASE_PATTERN + r"/a/([^/?#]+)" pattern = BASE_PATTERN + r"/a/([^/?#]+)"
example = "https://bunkr.sk/a/ID" example = "https://bunkr.sk/a/ID"
def __init__(self, match):
LolisafeAlbumExtractor.__init__(self, match)
domain = match.group(match.lastindex-1)
if domain not in LEGACY_DOMAINS:
self.root = "https://" + domain
def fetch_album(self, album_id): def fetch_album(self, album_id):
# album metadata # album metadata
page = self.request(self.root + "/a/" + self.album_id).text page = self.request(self.root + "/a/" + self.album_id).text
@@ -56,46 +60,32 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor):
def _extract_files(self, urls): def _extract_files(self, urls):
for url in urls: for url in urls:
if url.startswith("/"): try:
try: url = self._extract_file(text.unescape(url))
url = self._extract_file(text.unescape(url)) except Exception as exc:
except Exception as exc: self.log.error("%s: %s", exc.__class__.__name__, exc)
self.log.error("%s: %s", exc.__class__.__name__, exc) continue
continue
else:
if url.lower().endswith(CDN_HOSTED_EXTENSIONS):
scheme, domain, path, query, fragment = urlsplit(url)
if domain in MEDIA_DOMAIN_OVERRIDES:
domain = MEDIA_DOMAIN_OVERRIDES[domain]
else:
domain = domain.replace("cdn", "media-files", 1)
url = urlunsplit((scheme, domain, path, query, fragment))
yield {"file": text.unescape(url)} yield {"file": text.unescape(url)}
def _extract_file(self, path): def _extract_file(self, url):
page = self.request(self.root + path).text page = self.request(url).text
if path[1] == "v": return (
url = text.extr(page, '<source src="', '"') text.extr(page, '<source src="', '"') or
else: text.extr(page, '<img src="', '"') or
url = text.extr(page, '<img src="', '"') text.rextract(page, ' href="', '"', page.rindex("Download"))[0]
if not url: )
url = text.rextract(
page, ' href="', '"', page.rindex("Download"))[0]
return url
class BunkrMediaExtractor(BunkrAlbumExtractor): class BunkrMediaExtractor(BunkrAlbumExtractor):
"""Extractor for bunkr.sk media links""" """Extractor for bunkr.sk media links"""
subcategory = "media" subcategory = "media"
directory_fmt = ("{category}",) directory_fmt = ("{category}",)
pattern = BASE_PATTERN + r"/[vid]/([^/?#]+)" pattern = BASE_PATTERN + r"(/[vid]/[^/?#]+)"
example = "https://bunkr.sk/v/FILENAME" example = "https://bunkr.sk/v/FILENAME"
def fetch_album(self, album_id): def fetch_album(self, album_id):
try: try:
url = self._extract_file(urlsplit(self.url).path) url = self._extract_file(self.root + self.album_id)
except Exception as exc: except Exception as exc:
self.log.error("%s: %s", exc.__class__.__name__, exc) self.log.error("%s: %s", exc.__class__.__name__, exc)
return (), {} return (), {}

89
test/results/bunkr.py
View File

@@ -13,24 +13,19 @@ __tests__ = (
"#category": ("lolisafe", "bunkr", "album"), "#category": ("lolisafe", "bunkr", "album"),
"#class" : bunkr.BunkrAlbumExtractor, "#class" : bunkr.BunkrAlbumExtractor,
"#urls" : "https://i-burger.bunkr.ru/test-テスト-\"&>-QjgneIQv.png", "#urls" : "https://i-burger.bunkr.ru/test-テスト-\"&>-QjgneIQv.png",
"#sha1_content": "0c8768055e4e20e7c7259608b67799171b691140", "#sha1_content": "f38b54b17cd7462e687b58d83f00fca88b1b105a",
"album_id" : "Lktg9Keq", "album_id" : "Lktg9Keq",
"album_name": "test テスト \"&>", "album_name" : "test テスト \"&>",
"count" : 1, "album_size" : "182 B",
"filename" : "test-テスト-\"&>-QjgneIQv", "count" : 1,
"id" : "QjgneIQv", "description": "",
"name" : "test-テスト-\"&>", "extension" : "png",
"num" : int, "file" : "https://i-burger.bunkr.ru/test-テスト-\"&>-QjgneIQv.png",
}, "filename" : "test-テスト-\"&>-QjgneIQv",
"id" : "QjgneIQv",
{ "name" : "test-テスト-\"&>",
"#url" : "https://app.bunkr.ru/a/ptRHaCn2", "num" : 1,
"#comment" : "mp4 (#2239)",
"#category": ("lolisafe", "bunkr", "album"),
"#class" : bunkr.BunkrAlbumExtractor,
"#urls" : "https://burger.bunkr.ru/_-RnHoW69L.mp4",
"#sha1_content": "80e61d1dbc5896ae7ef9a28734c747b28b320471",
}, },
{ {
@@ -39,24 +34,24 @@ __tests__ = (
"#category": ("lolisafe", "bunkr", "album"), "#category": ("lolisafe", "bunkr", "album"),
"#class" : bunkr.BunkrAlbumExtractor, "#class" : bunkr.BunkrAlbumExtractor,
"#urls" : ( "#urls" : (
"https://milkshake.bunkr.ru/video-wFO9FtxG.mp4",
"https://i-milkshake.bunkr.ru/image-sZrQUeOx.jpg", "https://i-milkshake.bunkr.ru/image-sZrQUeOx.jpg",
"https://burger.bunkr.ru/video-gLn1hgpw.mp4",
), ),
"#sha1_content": "da29aae371b7adc8c5ef8e6991b66b69823791e8", "#sha1_content": "80914b8190ad001662f64e3b0b9c02ea3872c584",
"album_id" : "iXTTc1o2", "album_id" : "iXTTc1o2",
"album_name" : "test2", "album_name" : "test2",
"album_size" : "691.1 KB", "album_size" : "561.6 KB",
"count" : 2, "count" : 2,
"description": "", "description": "",
"filename" : r"re:video-wFO9FtxG|image-sZrQUeOx", "filename" : r"re:video-gLn1hgpw|image-sZrQUeOx",
"id" : r"re:wFO9FtxG|sZrQUeOx", "id" : r"re:gLn1hgpw|sZrQUeOx",
"name" : r"re:video|image", "name" : r"re:video|image",
"num" : int, "num" : range(1, 2),
}, },
{ {
"#url" : "https://bunkrr.su/a/j1G29CnD", "#url" : "https://bunkr.cat/a/j1G29CnD",
"#comment" : "cdn12 .ru TLD (#4147)", "#comment" : "cdn12 .ru TLD (#4147)",
"#category": ("lolisafe", "bunkr", "album"), "#category": ("lolisafe", "bunkr", "album"),
"#class" : bunkr.BunkrAlbumExtractor, "#class" : bunkr.BunkrAlbumExtractor,
@@ -64,6 +59,36 @@ __tests__ = (
"#count" : 9, "#count" : 9,
}, },
{
"#url" : "https://bunkr.si/a/Lktg9Keq",
"#category": ("lolisafe", "bunkr", "album"),
"#class" : bunkr.BunkrAlbumExtractor,
},
{
"#url" : "https://bunkr.ac/a/Lktg9Keq",
"#category": ("lolisafe", "bunkr", "album"),
"#class" : bunkr.BunkrAlbumExtractor,
},
{
"#url" : "https://bunkr.media/a/Lktg9Keq",
"#category": ("lolisafe", "bunkr", "album"),
"#class" : bunkr.BunkrAlbumExtractor,
},
{
"#url" : "https://bunkr.site/a/Lktg9Keq",
"#category": ("lolisafe", "bunkr", "album"),
"#class" : bunkr.BunkrAlbumExtractor,
},
{
"#url" : "https://bunkr.ws/a/Lktg9Keq",
"#category": ("lolisafe", "bunkr", "album"),
"#class" : bunkr.BunkrAlbumExtractor,
},
{ {
"#url" : "https://bunkrr.ru/a/Lktg9Keq", "#url" : "https://bunkrr.ru/a/Lktg9Keq",
"#category": ("lolisafe", "bunkr", "album"), "#category": ("lolisafe", "bunkr", "album"),
@@ -107,11 +132,11 @@ __tests__ = (
}, },
{ {
"#url" : "https://bunkrr.su/i/image-sZrQUeOx.jpg", "#url" : "https://bunkr.black/i/image-sZrQUeOx.jpg",
"#category": ("lolisafe", "bunkr", "media"), "#category": ("lolisafe", "bunkr", "media"),
"#class" : bunkr.BunkrMediaExtractor, "#class" : bunkr.BunkrMediaExtractor,
"#urls" : "https://i-milkshake.bunkr.ru/image-sZrQUeOx.jpg", "#urls" : "https://i-milkshake.bunkr.ru/image-sZrQUeOx.jpg",
"#sha1_content": "caf7c3d3439d94e83b3c24ddaf5a3a48aa057519", "#sha1_content": "55998743751dfe008d0e95605114fcbfa7dc4de8",
"count" : 1, "count" : 1,
"extension": "jpg", "extension": "jpg",
@@ -122,17 +147,17 @@ __tests__ = (
}, },
{ {
"#url" : "https://bunkrr.su/v/video-wFO9FtxG.mp4", "#url" : "https://bunkr.red/v/MY5aa4cLO7jN5",
"#category": ("lolisafe", "bunkr", "media"), "#category": ("lolisafe", "bunkr", "media"),
"#class" : bunkr.BunkrMediaExtractor, "#class" : bunkr.BunkrMediaExtractor,
"#urls" : "https://milkshake.bunkr.ru/video-wFO9FtxG.mp4", "#urls" : "https://burger.bunkr.ru/video-gLn1hgpw.mp4",
"#sha1_content": "a8cba735ae533507b1810b88d11df7028286dd8a", "#sha1_content": "f7a2ab24766a15ceffff1b07bada432b13ff8e5b",
"count" : 1, "count" : 1,
"extension": "mp4", "extension": "mp4",
"file" : "https://milkshake.bunkr.ru/video-wFO9FtxG.mp4", "file" : "https://burger.bunkr.ru/video-gLn1hgpw.mp4",
"filename" : "video-wFO9FtxG", "filename" : "video-gLn1hgpw",
"id" : "wFO9FtxG", "id" : "gLn1hgpw",
"name" : "video", "name" : "video",
}, },