Bulk asynchronous downloader for multiple file hosts
Python asynciobunkrcyberdropdownloaderdropboxfilestergofilegoogle-drivemediafiremegamega-nzonedrivepatreonpawchivepinterestpixeldraintransfer-ittwitchtwittervk
fix: do not try to parse upload date (YouJizz) (#1842)
NTFSvolumeba77f422d445
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 46c975c21..a8532990b 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -22,6 +22,13 @@ All notable changes to this project will be documented here. For more details, vThe format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).+## UNRELEASED++### Fixed++- Do not try to parse upload date (YouJizz)+- Video extraction from embed URLs (YouJizz)+## [9.10.1] - 2026-05-16### Changeddiff --git a/cyberdrop_dl/crawlers/youjizz.py b/cyberdrop_dl/crawlers/youjizz.pyindex 5964786a2..1fe8b1d5b 100644--- a/cyberdrop_dl/crawlers/youjizz.py+++ b/cyberdrop_dl/crawlers/youjizz.py@@ -2,34 +2,26 @@ from __future__ import annotationsimport dataclassesimport json-from typing import TYPE_CHECKING, Any, ClassVar, NamedTuple+from typing import TYPE_CHECKING, Any, ClassVarfrom cyberdrop_dl.crawlers.crawler import Crawler, SupportedPaths+from cyberdrop_dl.mediaprops import Resolutionfrom cyberdrop_dl.url_objects import AbsoluteHttpURL-from cyberdrop_dl.utils import css, error_handling_wrapper, extr_text, open_graph+from cyberdrop_dl.utils import css, error_handling_wrapper, extr_text, open_graph, parse_urlif TYPE_CHECKING:- from collections.abc import Iterable+ from collections.abc import Generatorfrom bs4 import BeautifulSoupfrom cyberdrop_dl.url_objects import ScrapeItem-PRIMARY_URL = AbsoluteHttpURL("https://www.youjizz.com/")-JS_SELECTOR = "div#content > script:-soup-contains('var dataEncodings')"-DATE_SELECTOR = "span.pretty-date"---class VideoSource(NamedTuple):- resolution: int- url: str-@dataclasses.dataclass(frozen=True, slots=True)class Video:- date: str # Human datetitle: str- best_src: VideoSource+ resolution: Resolution+ src: AbsoluteHttpURLclass YouJizzCrawler(Crawler):@@ -39,7 +31,7 @@ class YouJizzCrawler(Crawler):"/videos/<video_name>",)}- PRIMARY_URL: ClassVar[AbsoluteHttpURL] = PRIMARY_URL+ PRIMARY_URL: ClassVar[AbsoluteHttpURL] = AbsoluteHttpURL("https://www.youjizz.com/")DOMAIN: ClassVar[str] = "youjizz"FOLDER_DOMAIN: ClassVar[str] = "YouJizz"@@ -55,44 +47,46 @@ class YouJizzCrawler(Crawler):@error_handling_wrapperasync def video(self, scrape_item: ScrapeItem, video_id: str) -> None:- canonical_url = PRIMARY_URL / "videos" / "embed" / video_id+ canonical_url = self.PRIMARY_URL / "videos" / "embed" / video_idif await self.check_complete_from_referer(canonical_url):returnsoup = await self.request_soup(scrape_item.url)-scrape_item.url = canonical_urlvideo = _parse_video(soup)- link = self.parse_url(video.best_src.url)- scrape_item.uploaded_at = self.parse_date(video.date)- filename, ext = self.get_filename_and_ext(link.name)+ filename, ext = self.get_filename_and_ext(video.src.name)custom_filename = self.create_custom_filename(- video.title, ext, file_id=video_id, resolution=video.best_src.resolution+ video.title,+ ext,+ file_id=video_id,+ resolution=video.resolution,)await self.handle_file(- scrape_item.url, scrape_item, filename, ext, custom_filename=custom_filename, debrid_link=link+ scrape_item.url,+ scrape_item,+ filename,+ ext,+ custom_filename=custom_filename,+ debrid_link=video.src,)def _parse_video(soup: BeautifulSoup) -> Video:- js_text = css.select_text(soup, JS_SELECTOR)- encodings_text = extr_text(js_text, "var dataEncodings =", "var encodings").strip().removesuffix(";")+ js_text = css.select_text(soup, "script:-soup-contains('var dataEncodings')")+ encodings_text = extr_text(js_text, "var dataEncodings =", "var encodings").removesuffix(";")data_encodings = json.loads(encodings_text)- return Video(- title=open_graph.title(soup),- date=css.select_text(soup, DATE_SELECTOR),- best_src=_get_best_src(data_encodings),- )---def _get_best_src(data_encodings: list[dict[str, Any]]) -> VideoSource:- def parse() -> Iterable[VideoSource]:- for format_info in data_encodings:- try:- res = int(format_info["quality"])- except ValueError:- continue- if "/_hls/" not in (link_str := format_info["filename"]):- yield VideoSource(res, link_str)-- return max(parse())+ res, src = max(_parse_formats(data_encodings))+ return Video(resolution=res, src=src, title=open_graph.title(soup))+++def _parse_formats(data_encodings: list[dict[str, Any]]) -> Generator[tuple[Resolution, AbsoluteHttpURL]]:+ for fmt in data_encodings:+ if "/_hls/" in fmt["filename"]:+ continue++ url = parse_url(fmt["filename"])+ if url.suffix == ".m3u8":+ continue++ res = Resolution.parse(int(fmt["quality"]))+ yield res, urldiff --git a/tests/crawlers/test_cases/youjizz.py b/tests/crawlers/test_cases/youjizz.pynew file mode 100644index 000000000..219460584--- /dev/null+++ b/tests/crawlers/test_cases/youjizz.py@@ -0,0 +1,30 @@+DOMAIN = "youjizz"+TEST_CASES = [+ {+ "url": "https://www.youjizz.com/videos/lets-dance-4094031.html",+ "results": [+ {+ "url": "https://www.youjizz.com/videos/embed/4094031",+ "filename": "Lets dance [4094031][360p].mp4",+ "debrid_link": "re:.mp4",+ "original_filename": "90feba7396207e61d62351afac674cda1352199723-450-360-474-h264.mp4",+ "referer": "https://www.youjizz.com/videos/embed/4094031",+ "album_id": None,+ "uploaded_at": None,+ "download_folder": "re:Loose Files (YouJizz)",+ }+ ],+ "count": 1,+ },+ {+ "url": "https://www.youjizz.com/videos/embed/4094031",+ "results": [+ {+ "url": "https://www.youjizz.com/videos/embed/4094031",+ "filename": "Lets dance [4094031][360p].mp4",+ "original_filename": "90feba7396207e61d62351afac674cda1352199723-450-360-474-h264.mp4",+ "referer": "https://www.youjizz.com/videos/embed/4094031",+ }+ ],+ },+]