Skip to content

Bulk asynchronous downloader for multiple file hosts

refactor: try embeds first (Fileditch)

NTFSvolume67646958caf2
diff --git a/cyberdrop_dl/crawlers/fileditch.py b/cyberdrop_dl/crawlers/fileditch.py
index af2d80c32..24abb45ec 100644
--- a/cyberdrop_dl/crawlers/fileditch.py
+++ b/cyberdrop_dl/crawlers/fileditch.py
@@ -6,9 +6,10 @@ from typing import TYPE_CHECKING, ClassVar, override
from cyberdrop_dl import env
from cyberdrop_dl.clients.http import HTTPConfig
+from cyberdrop_dl.constants import FileExt
from cyberdrop_dl.crawlers import Registry
from cyberdrop_dl.crawlers.crawler import Crawler, SupportedDomains, SupportedPaths
-from cyberdrop_dl.exceptions import DDOSGuardError, ScrapeError
+from cyberdrop_dl.exceptions import DDOSGuardError, DownloadError, ScrapeError
from cyberdrop_dl.url_objects import AbsoluteHttpURL
from cyberdrop_dl.utils import b64_pad, css, extr_text
from cyberdrop_dl.utils.errors import error_handling_wrapper
@@ -86,7 +87,15 @@ class FileditchCrawler(Crawler):
)
async def request_download(self, url: AbsoluteHttpURL) -> File:
- resp = await self.flaresolverr_request(url, wait=env.FILEDITCH_WAIT)
+ resp = None
+ if url.suffix.lower() in FileExt.VIDEO:
+ # Try embeds first, they have no CF turnstile
+ try:
+ resp = await self.flaresolverr_request(url.with_host("embedditch.st"), wait=env.FILEDITCH_WAIT)
+ except (DDOSGuardError, DownloadError):
+ pass
+
+ resp = resp or await self.flaresolverr_request(url, wait=env.FILEDITCH_WAIT)
soup = await resp.soup()
src = _extract_dl_url(soup)
return File(