Bulk asynchronous downloader for multiple file hosts
Python asynciobunkrcyberdropdownloaderdropboxfilestergofilegoogle-drivemediafiremegamega-nzonedrivepatreonpawchivepinterestpixeldraintransfer-ittwitchtwittervk
fix: download URL extraction (FuckingFast)
NTFSvolume996bd354caae
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 22cb2d47c..8a45ada49 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -45,6 +45,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0- Some URLs being wrongly skipped as duplicates when using any of the `retry` options if they came from the same collection/folder/album.This affected sites where multiple files may share identical URL path and query, with the fragment being what uniquely identifies each file (Mega.nz, Koofr, Transfer.it)- Download URL extraction (BuzzHeavier)+- Download URL extraction (FuckingFast)- Download of files with no hash information (Filester)- Parsing of `$EDITOR` for paths with spacesdiff --git a/cyberdrop_dl/crawlers/fucking_fast.py b/cyberdrop_dl/crawlers/fucking_fast.pyindex 508750a2e..4eee4fa6d 100644--- a/cyberdrop_dl/crawlers/fucking_fast.py+++ b/cyberdrop_dl/crawlers/fucking_fast.py@@ -4,7 +4,7 @@ from typing import TYPE_CHECKING, ClassVarfrom cyberdrop_dl.crawlers.crawler import Crawler, SupportedPathsfrom cyberdrop_dl.url_objects import AbsoluteHttpURL-from cyberdrop_dl.utils import css, extr_text+from cyberdrop_dl.utils import cssfrom cyberdrop_dl.utils.errors import error_handling_wrapperif TYPE_CHECKING:@@ -33,9 +33,18 @@ class FuckingFastCrawler(Crawler):if await self.check_complete_from_referer(scrape_item.url):return- soup = await self.request_soup(scrape_item.url)+ soup = await self.request_soup(scrape_item.url, impersonate=True)name = css.page_title(soup)- dl_link = extr_text(str(soup), 'window.open("https:', ")").strip('"')- link = self.parse_url(f"https:{dl_link}")- filename, ext = self.get_filename_and_ext(name)- await self.handle_file(scrape_item.url, scrape_item, name, ext, debrid_link=link, custom_filename=filename)+ hx_url = self.parse_url(css.select(soup, ".link-button", "hx-post"))+ async with self.request(+ hx_url,+ method="POST",+ headers={+ "HX-Current-URL": str(scrape_item.url),+ "HX-Request": "true",+ },+ ) as resp:+ src = self.parse_url(resp.headers["hx-redirect"])++ filename, ext = self.get_filename_and_ext(name, assume_ext=".zip")+ await self.handle_file(scrape_item.url, scrape_item, name, ext, debrid_link=src, custom_filename=filename)