Bulk asynchronous downloader for multiple file hosts
Python asynciobunkrcyberdropdownloaderdropboxfilestergofilegoogle-drivemediafiremegamega-nzonedrivepatreonpawchivepinterestpixeldraintransfer-ittwitchtwittervk
fix: send a valid Origin header (yandex disk) (#2136)
Michael Menannoe8afe4337a92
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 6438a60d1..7b4e185fd 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -44,6 +44,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0- Downloads failing with 404 when the file name contains "&" or "'" (Bunkr)- Downloads of embeded videos and direct URLs (Imagepond)- Thumbnails downloads always failing with 404 (Cyberdrop)+- Downloads failing with "DDoS-Guard" errors (Yandex Disk)## [10.8.0] - 2026-09-06diff --git a/cyberdrop_dl/crawlers/yandex_disk.py b/cyberdrop_dl/crawlers/yandex_disk.pyindex da0b31b2e..7e8ef5ee3 100644--- a/cyberdrop_dl/crawlers/yandex_disk.py+++ b/cyberdrop_dl/crawlers/yandex_disk.py@@ -123,14 +123,7 @@ class YandexDiskCrawler(Crawler):if await self.check_complete_from_referer(scrape_item.url):return None- referer = str(file.url)- headers = _DEFAULT_HEADERS | {- "Content-Type": "text/plain",- "X-Requested-With": "XMLHttpRequest",- "Origin": str(scrape_item.url.host),- "Referer": referer,- "X-Retpath-Y": referer,- }+ headers = _download_url_headers(scrape_item.url, file.url)api_url = _DOWNLOAD_API_ENTRYPOINT.with_host(scrape_item.url.host)with self._request_context():@@ -160,6 +153,16 @@ class YandexDiskCrawler(Crawler):await self.handle_file(file.url, scrape_item, filename, ext, debrid_link=link)+def _download_url_headers(url: AbsoluteHttpURL, referer: AbsoluteHttpURL) -> dict[str, str]:+ return _DEFAULT_HEADERS | {+ "Content-Type": "text/plain",+ "X-Requested-With": "XMLHttpRequest",+ "Origin": str(url.origin()),+ "Referer": str(referer),+ "X-Retpath-Y": str(referer),+ }++def _get_item_info(soup: BeautifulSoup) -> dict[str, Any]:js_text: str = css.select_text(soup, "script#store-prefetch")info_json: dict[str, dict[str, Any]] = json.loads(js_text)diff --git a/tests/crawlers/test_yandex_disk.py b/tests/crawlers/test_yandex_disk.pynew file mode 100644index 000000000..3b851e4ae--- /dev/null+++ b/tests/crawlers/test_yandex_disk.py@@ -0,0 +1,19 @@+import pytest++from cyberdrop_dl.crawlers import yandex_disk+from cyberdrop_dl.url_objects import AbsoluteHttpURL+++ ("url", "expected"),+ [+ ("https://disk.yandex.com/i/AbCdEf123", "https://disk.yandex.com"),+ ("https://disk.yandex.com.tr/d/AbCdEf123/video.mp4", "https://disk.yandex.com.tr"),+ ("https://disk.yandex.ru/i/AbCdEf123", "https://disk.yandex.ru"),+ ],+)+def test_download_url_headers_origin(url: str, expected: str) -> None:+ referer = AbsoluteHttpURL("https://yadi.sk/i/AbCdEf123")+ headers = yandex_disk._download_url_headers(AbsoluteHttpURL(url), referer)+ assert headers["Origin"] == expected+ assert headers["Referer"] == headers["X-Retpath-Y"] == str(referer)