Mirrors/gallery-dl
1
0
Fork 0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-23 19:22:32 +01:00
Code Issues Releases Wiki Activity

[bunkr] fix extraction (#3636, #3655)

Browse Source
This commit is contained in:
Mike Fährmann 2023-02-15 15:42:32 +01:00
parent 9335d55bbc
commit ad96e70546
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88
1 changed files with 48 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

83
gallery_dl/extractor/bunkr.py
View File

@ -9,7 +9,7 @@
"""Extractors for https://bunkr.su/"""
from .lolisafe import LolisafeAlbumExtractor
from .. import text, util
from .. import text
class BunkrAlbumExtractor(LolisafeAlbumExtractor):
@ -19,7 +19,7 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor):
pattern = r"(?:https?://)?(?:app\.)?bunkr\.(?:[sr]u|is|to)/a/([^/?#]+)"
test = (
("https://bunkr.su/a/Lktg9Keq", {
"pattern": r"https://cdn\.bunkr\.su/test-テスト-\"&>-QjgneIQv\.png",
"pattern": r"https://cdn\.bunkr\.ru/test-テスト-\"&>-QjgneIQv\.png",
"content": "0c8768055e4e20e7c7259608b67799171b691140",
"keyword": {
"album_id": "Lktg9Keq",
@ -40,44 +40,57 @@ class BunkrAlbumExtractor(LolisafeAlbumExtractor):
("https://bunkr.is/a/iXTTc1o2", {
"pattern": r"https://(cdn|media-files)4\.bunkr\.ru/",
"content": "da29aae371b7adc8c5ef8e6991b66b69823791e8",
"keyword": {
"album_id": "iXTTc1o2",
"album_name": "test2",
"album_size": "691.1 KB",
"count": 2,
"description": "072022",
"filename": "re:video-wFO9FtxG|image-sZrQUeOx",
"id": "re:wFO9FtxG|sZrQUeOx",
"name": "re:video|image",
"num": int,
},
}),
("https://bunkr.to/a/Lktg9Keq"),
)
def fetch_album(self, album_id):
root = self.root
# album metadata
page = self.request(self.root + "/a/" + self.album_id).text
info = text.split_html(text.extr(
page, "<h1", "</div>").partition(">")[2])
count, _, size = info[1].split(None, 2)
try:
data = util.json_loads(text.extr(
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("%s: %s", exc.__class__.__name__, exc)
self.log.debug("Falling back to lolisafe API")
self.root = root.replace("://", "://app.", 1)
files, data = LolisafeAlbumExtractor.fetch_album(self, album_id)
# fix file URLs (bunkr..ru -> bunkr.ru) (#3481)
for file in files:
file["file"] = file["file"].replace("bunkr..", "bunkr.", 1)
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),
}
# files
cdn = None
files = []
append = files.append
headers = {"Referer": self.root.replace("://", "://stream.", 1) + "/"}
headers = {"Referer": root.replace("://", "://stream.", 1) + "/"}
for file in files:
if file["file"].endswith(
(".mp4", ".m4v", ".mov", ".webm", ".mkv", ".ts",
".zip", ".rar", ".7z")):
file["_http_headers"] = headers
file["file"] = file["file"].replace(
"://cdn", "://media-files", 1)
pos = page.index('class="grid-images')
for url in text.extract_iter(page, '<a href="', '"', pos):
if url.startswith("/"):
if not cdn:
# fetch cdn root from download page
durl = "{}/d/{}".format(self.root, url[3:])
cdn = text.extr(self.request(
durl).text, 'link.href = "', '"')
cdn = cdn[:cdn.index("/", 8)]
url = cdn + url[2:]
return files, data
url = text.unescape(url)
if url.endswith((".mp4", ".m4v", ".mov", ".webm", ".mkv", ".ts",
".zip", ".rar", ".7z")):
append({"file": url.replace("://cdn", "://media-files", 1),
"_http_headers": headers})
else:
append({"file": url})
return files, {
"album_id" : self.album_id,
"album_name" : text.unescape(info[0]),
"album_size" : size[1:-1],
"description": text.unescape(info[2]) if len(info) > 2 else "",
"count" : len(files),
}