Skip to content

fix: handle more redirects (bunkr) #23

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
NTFSvolume merged 1 commit into from
Mar 9, 2026
Merged

fix: handle more redirects (bunkr) #23

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 10 additions & 4 deletions cyberdrop_dl/crawlers/bunkrr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,11 @@ class Selector:

VIDEO_AND_IMAGE_EXTS: set[str] = FILE_FORMATS["Images"] | FILE_FORMATS["Videos"]
HOST_OPTIONS: set[str] = {"bunkr.site", "bunkr.cr", "bunkr.ph"}
DEEP_SCRAPE_CDNS: set[str] = {"burger", "milkshake"} # CDNs under maintanance, ignore them and try to get a cached URL
DEEP_SCRAPE_CDNS: set[str] = {
"burger",
"milkshake",
"static.scdn.st",
} # CDNs under maintanance, ignore them and try to get a cached URL
FILE_KEYS = "id", "name", "original", "slug", "type", "extension", "size", "timestamp", "thumbnail", "cdnEndpoint"
known_bad_hosts: set[str] = set()

Expand Down Expand Up @@ -133,7 +137,7 @@ async def fetch(self, scrape_item: ScrapeItem) -> None:
return await self.reinforced_file(scrape_item, file_id)
case ["a", album_id]:
return await self.album(scrape_item, album_id)
case ["v", _]:
case ["v" | "d", _]:
return await self.follow_redirect(scrape_item)
case ["f", _]:
return await self.file(scrape_item)
Expand Down Expand Up @@ -173,14 +177,16 @@ async def _album_file(self, scrape_item: ScrapeItem, file: File, results: dict[s
try:
src = file.src()
except ValueError:
deep_scrape = True
self.create_task(self.run(scrape_item))
return

deep_scrape = deep_scrape or (
deep_scrape = (
src.suffix.lower() not in VIDEO_AND_IMAGE_EXTS
or "no-image" in src.name
or self.deep_scrape
or any(cdn in src.host for cdn in DEEP_SCRAPE_CDNS)
)

if deep_scrape:
self.create_task(self.run(scrape_item))
return
Expand Down