Bulk asynchronous downloader for multiple file hosts
Python asynciobunkrcyberdropdownloaderdropboxfilestergofilegoogle-drivemediafiremegamega-nzonedrivepatreonpawchivepinterestpixeldraintransfer-ittwitchtwittervk
feat: add support for single file URLs (GoFile) (#1439)
NTFSvolumeaf0424f7d79e
diff --git a/cyberdrop_dl/crawlers/gofile.py b/cyberdrop_dl/crawlers/gofile.pyindex 62958baae..319932525 100644--- a/cyberdrop_dl/crawlers/gofile.py+++ b/cyberdrop_dl/crawlers/gofile.py@@ -86,6 +86,10 @@ class FolderResponse(Response):class GoFileCrawler(Crawler):SUPPORTED_PATHS: ClassVar[SupportedPaths] = {"Folder / File": "/d/<content_id>",+ "Direct link": (+ "/download/<content_id>/<filename>",+ "/download/web/<content_id>/<filename>",+ ),"**NOTE**": ("Use `password` as a query param to download password protected folders","ex: https://gofile.io/d/ABC654?password=1234",@@ -116,11 +120,22 @@ class GoFileCrawler(Crawler):match scrape_item.url.parts[1:]:case ["d", content_id]:return await self.folder(scrape_item, content_id)+ case ["download", "web", file_id, _]:+ return await self.single_file(scrape_item, file_id)+ case ["download", file_id, _]:+ return await self.single_file(scrape_item, file_id)case _:raise ValueError@error_handling_wrapper- async def folder(self, scrape_item: ScrapeItem, content_id: str) -> None:+ async def single_file(self, scrape_item: ScrapeItem, file_id: str) -> None:+ url = await self._get_redirect_url(scrape_item.url)+ scrape_item.url = url.with_fragment(file_id)+ assert "d" in url.parts+ return await self.folder(scrape_item, url.name, file_id)++ @error_handling_wrapper+ async def folder(self, scrape_item: ScrapeItem, content_id: str, single_file_id: str | None = None) -> None:is_first_page: bool = Trueasync for folder in self._folder_pager(content_id, scrape_item.url.query.get("password")):@@ -138,7 +153,15 @@ class GoFileCrawler(Crawler):scrape_item.url = scrape_item.url.with_query(None)is_first_page = False- self._handle_children(scrape_item, folder["children"])+ children = folder["children"]+ if single_file_id:+ file = children.get(single_file_id)+ if not file:+ continue++ children = {single_file_id: file}++ self._handle_children(scrape_item, children)def _handle_children(self, scrape_item: ScrapeItem, children: dict[str, Node]) -> None:def get_website_url(node: Node) -> AbsoluteHttpURL:diff --git a/tests/crawlers/test_cases/gofile.py b/tests/crawlers/test_cases/gofile.pyindex 8042d638b..10fb651ce 100644--- a/tests/crawlers/test_cases/gofile.py+++ b/tests/crawlers/test_cases/gofile.py@@ -23,15 +23,7 @@ TEST_CASES = ["referer": "https://gofile.io/d/0272Cc#386c2d54-548a-4fd1-abde-6f7c91b25a5d","album_id": "0272Cc","datetime": 1759603311,- },- {- "url": "ANY",- "filename": "Boeboe - Drift (Bass Boosted).mp4",- "download_folder": r"re:CDL_test \(GoFile\)/folder_B",- "referer": "https://gofile.io/d/OP2VyC#229e787c-22e2-4f77-90a5-eb9802788aad",- "album_id": "OP2VyC",- "datetime": 1759603323,- },+ }],),("https://gofile.io/d/tZeyhP?password=wrong_password", []),@@ -47,4 +39,17 @@ TEST_CASES = [},],),+ (+ "https://store6.gofile.io/download/69b4c1e4-a80a-45d5-ad76-061e48105bd0/MORE_IN90.mp4",+ [+ {+ "url": "https://store3.gofile.io/download/web/69b4c1e4-a80a-45d5-ad76-061e48105bd0/MORE_IN90.mp4",+ "filename": "MORE_IN90.mp4",+ "download_folder": r"re:01 \(GoFile\)",+ "referer": "https://gofile.io/d/9d83784e-2be6-472c-909f-0377704cfde3#69b4c1e4-a80a-45d5-ad76-061e48105bd0",+ "album_id": "9d83784e-2be6-472c-909f-0377704cfde3",+ "datetime": 1701541586,+ },+ ],+ ),]