Bulk asynchronous downloader for multiple file hosts
Python asynciobunkrcyberdropdownloaderdropboxfilestergofilegoogle-drivemediafiremegamega-nzonedrivepatreonpawchivepinterestpixeldraintransfer-ittwitchtwittervk
feat: add goonbox support (#2001)
NTFSvolume2e33395eab10
diff --git a/cyberdrop_dl/crawlers/goonbox.py b/cyberdrop_dl/crawlers/goonbox.pynew file mode 100644index 000000000..9e694567c--- /dev/null+++ b/cyberdrop_dl/crawlers/goonbox.py@@ -0,0 +1,182 @@+from __future__ import annotations++import dataclasses+import itertools+from typing import TYPE_CHECKING, Any, ClassVar, Self++from cyberdrop_dl.crawlers.crawler import API, Crawler, SupportedDomains, SupportedPaths+from cyberdrop_dl.url_objects import AbsoluteHttpURL+from cyberdrop_dl.utils import parse_url+from cyberdrop_dl.utils.dataclass import deserialize+from cyberdrop_dl.utils.errors import error_handling_wrapper++if TYPE_CHECKING:+ from collections.abc import AsyncGenerator, Iterable++ from cyberdrop_dl.url_objects import ScrapeItem++_CDN = "cuckcapital.cr"+++class GoonBoxCrawler(Crawler):+ SUPPORTED_DOMAINS: ClassVar[SupportedDomains] = "selti-delivery.ru", "goonbox", _CDN+ SUPPORTED_PATHS: ClassVar[SupportedPaths] = {+ "Image": "/img/<image_id>",+ "Album": "/a/<album_id>",+ "Direct links": "",+ }++ DOMAIN: ClassVar[str] = "goonbox"+ FOLDER_DOMAIN: ClassVar[str] = "GoonBox"+ OLD_DOMAINS: ClassVar[tuple[str, ...]] = (+ "host.church",+ "jpg.homes",+ "jpg.church",+ "jpg.fish",+ "jpg.fishing",+ "jpg.pet",+ "jpeg.pet",+ "jpg1.su",+ "jpg2.su",+ "jpg3.su",+ "jpg4.su",+ "jpg5.su",+ "jpg6.su",+ "jpg7.cr",+ )+ PRIMARY_URL: ClassVar[AbsoluteHttpURL] = AbsoluteHttpURL("https://goonbox.cr")++ def __post_init__(self) -> None:+ self.api: GoonBoxAPI = GoonBoxAPI.from_crawler(self)++ @classmethod+ def transform_url(cls, url: AbsoluteHttpURL) -> AbsoluteHttpURL:+ url = super().transform_url(url)+ if cls.is_subdomain(url):+ return _fix_cdn(_thumb_to_src(url))++ match url.parts[1:]:+ case ["a" | "img" as part, slug, *_]:+ return (url.origin() / part / _id(slug)).with_query(url.query)+ case _:+ return url++ async def fetch(self, scrape_item: ScrapeItem) -> None:+ if self.is_subdomain(scrape_item.url):+ return await self.direct_file(scrape_item)++ match scrape_item.url.parts[1:]:+ case ["img", file_id]:+ return await self.image(scrape_item, file_id)+ case ["a", album_id]:+ return await self.album(scrape_item, album_id)+ case _:+ raise ValueError++ @error_handling_wrapper+ async def image(self, scrape_item: ScrapeItem, image_id: str) -> None:+ if await self.check_complete_from_referer(scrape_item.url):+ return++ image = await self.api.image(image_id)+ await self._image(scrape_item, image)++ @error_handling_wrapper+ async def _image(self, scrape_item: ScrapeItem, image: Image) -> None:+ scrape_item.uploaded_at = self.parse_iso_date(image.created_at)+ name = image.original_filename or image.src.name+ filename, ext = self.get_filename_and_ext(name, mime_type=image.mime, assume_ext=".jpg")+ await self.handle_file(image.src, scrape_item, name, ext, custom_filename=filename)++ @error_handling_wrapper+ async def album(self, scrape_item: ScrapeItem, album_id: str) -> None:+ album = await self.api.album(album_id)+ title = self.create_title(album.title, album_id)+ scrape_item.setup_as_album(title, album_id=album_id)++ async for images in self._album_images(album):+ for img in images:+ url = self.PRIMARY_URL / "img" / img.encoded_id+ new_item = scrape_item.create_child(url)+ self.create_eager_task(self._image(new_item, img))+ scrape_item.add_children()++ async def _album_images(self, album: Album) -> AsyncGenerator[Iterable[Image]]:+ already_downloaded = await self.get_album_results(album.encoded_id)++ def filter_images(images: Iterable[Image]):+ for img in images:+ if not self.check_album_results(img.src, already_downloaded):+ yield img++ yield filter_images(album.images)+ if not album.has_more:+ return++ async for images in self.api.album_images(album.encoded_id, init_page=2):+ yield filter_images(images)++[email protected](slots=True)+class Image:+ encoded_id: str+ mime: str+ created_at: str+ original_filename: str | None+ src: AbsoluteHttpURL++ @classmethod+ def parse(cls, img: dict[str, Any]) -> Self:+ return deserialize(cls, img, src=parse_url(img["original_url"]))++[email protected](slots=True)+class Album:+ title: str+ description: str | None+ encoded_id: str+ images: map[Image]+ has_more: bool+++class GoonBoxAPI(API):+ async def image(self, image_id: str) -> Image:+ api_url = self.PRIMARY_URL / "api/images" / image_id+ resp = await self.request_json(api_url)+ return Image.parse(resp["image"])++ async def album(self, album_id: str) -> Album:+ api_url = self.PRIMARY_URL / "api/albums" / album_id+ resp = await self.request_json(api_url.with_query(per_page=100))+ return deserialize(+ Album,+ resp["album"],+ images=map(Image.parse, resp["images"]),+ has_more=resp["pagination"]["total"] > 1,+ )++ async def album_images(self, album_id: str, init_page: int = 1) -> AsyncGenerator[map[Image]]:+ api_url = self.PRIMARY_URL / "api/albums" / album_id / "images"+ for page in itertools.count(init_page):+ resp = await self.request_json(api_url.update_query(page=page, per_page=100))+ yield map(Image.parse, resp["images"])+ if page >= resp["pagination"]["last_page"]:+ break+++def _fix_cdn(url: AbsoluteHttpURL) -> AbsoluteHttpURL:+ if GoonBoxCrawler.is_subdomain(url) and not url.host.endswith(_CDN):+ server, *_ = url.host.rsplit(".", 2)+ return url.with_host(f"{server}.{_CDN}")+ return url+++def _id(slug: str) -> str:+ return slug.rsplit(".", maxsplit=1)[-1]+++def _thumb_to_src(url: AbsoluteHttpURL) -> AbsoluteHttpURL:+ new_name = url.name+ for trash in (".md.", ".th.", ".fr."):+ new_name = new_name.replace(trash, ".", 1)+ return url.with_name(new_name)diff --git a/cyberdrop_dl/crawlers/jpg5.py b/cyberdrop_dl/crawlers/jpg5.pydeleted file mode 100644index e908f6dab..000000000--- a/cyberdrop_dl/crawlers/jpg5.py+++ /dev/null@@ -1,79 +0,0 @@-from __future__ import annotations--import base64-from typing import TYPE_CHECKING, ClassVar, Final--from cyberdrop_dl.url_objects import AbsoluteHttpURL, ScrapeItem-from cyberdrop_dl.utils import xor_decrypt-from cyberdrop_dl.utils.errors import error_handling_wrapper--from ._chevereto import CheveretoCrawler--if TYPE_CHECKING:- import yarl-- from cyberdrop_dl.crawlers.crawler import RateLimit, SupportedDomains--_CDN: Final = "cuckcapital.cr"-_DECRYPTION_KEY: Final = b"seltilovessimpcity@simpcityhatesscrapers"---class JPG5Crawler(CheveretoCrawler):- SUPPORTED_DOMAINS: ClassVar[SupportedDomains] = "selti-delivery.ru", "jpg7.cr", "jpg6.su", _CDN- DOMAIN: ClassVar[str] = "jpg5.su"- FOLDER_DOMAIN: ClassVar[str] = "JPG5"- PRIMARY_URL: ClassVar[AbsoluteHttpURL] = AbsoluteHttpURL("https://jpg6.su")- CHEVERETO_SUPPORTS_VIDEO: ClassVar[bool] = False- OLD_DOMAINS: ClassVar[tuple[str, ...]] = (- "host.church",- "jpg.homes",- "jpg.church",- "jpg.fish",- "jpg.fishing",- "jpg.pet",- "jpeg.pet",- "jpg1.su",- "jpg2.su",- "jpg3.su",- "jpg4.su",- "jpg5.su",- )-- _RATE_LIMIT: ClassVar[RateLimit] = 2, 1-- @classmethod- def transform_url(cls, url: AbsoluteHttpURL) -> AbsoluteHttpURL:- url = super().transform_url(url)- if cls.is_subdomain(url):- # old jpg5 subdomains are still valid. ex: simp4.jpg5.su- return url.with_host(url.host.replace("jpg6.su", "jpg5.su"))- return url-- @error_handling_wrapper- async def direct_file(- self, scrape_item: ScrapeItem, /, url: AbsoluteHttpURL | None = None, assume_ext: str | None = None- ) -> None:- link = _fix_cdn(url or scrape_item.url)- await super().direct_file(scrape_item, link, assume_ext)-- @classmethod- def parse_url(- cls, link_str: yarl.URL | str, relative_to: AbsoluteHttpURL | None = None, *, trim: bool | None = None- ) -> AbsoluteHttpURL:- if type(link_str) is str:- link_str = _decode_url(link_str)- return _fix_cdn(super().parse_url(link_str, relative_to, trim=trim))---def _decode_url(url: str) -> str:- if url.startswith(("https:", "http:", "/")):- return url- encrypted_url = bytes.fromhex(base64.b64decode(url).decode())- return xor_decrypt(encrypted_url, _DECRYPTION_KEY)---def _fix_cdn(url: AbsoluteHttpURL) -> AbsoluteHttpURL:- if JPG5Crawler.is_subdomain(url) and not url.host.endswith(_CDN):- server, *_ = url.host.rsplit(".", 2)- return url.with_host(f"{server}.{_CDN}")- return urldiff --git a/cyberdrop_dl/database/history.py b/cyberdrop_dl/database/history.pyindex f47846ac5..118c5d861 100644--- a/cyberdrop_dl/database/history.py+++ b/cyberdrop_dl/database/history.py@@ -178,9 +178,10 @@ async def _fix_domains(db_conn: aiosqlite.Connection) -> None:f"UPDATE OR REPLACE media SET domain = '{current}' WHERE domain = '{old}';" # noqa: S608for current, old in [("bunkr", "bunkrr"),- ("jpg5.su", "sharex"),+ ("goonbox", "sharex"),("turbovid", "saint"),("nudostar.tv", "nudostartv"),+ ("goonbox", "jpg5.su"),])await db_conn.executescript(updates)@@ -188,7 +189,7 @@ async def _fix_domains(db_conn: aiosqlite.Connection) -> None:async def _fix_referers(db_conn: aiosqlite.Connection) -> None:- from cyberdrop_dl.crawlers import bunkr, cyberdrop, jpg5, redgifs, turbovid+ from cyberdrop_dl.crawlers import bunkr, cyberdrop, goonbox, redgifs, turboviddef try_wrap[T](fn: Callable[..., T]) -> Callable[..., T]:def call(*args: Any, **kwargs: Any) -> T:@@ -204,7 +205,7 @@ async def _fix_referers(db_conn: aiosqlite.Connection) -> None:with _timed_update("old database referers"):for fn_name, fn, domain in [("FIX_REDGIFS_REFERER", redgifs.fix_redgifs_referer, "redgifs"),- ("FIX_JPG5_REFERER", _generic_fix_referer(jpg5.JPG5Crawler), "jpg5.su"),+ ("FIX_GOONBOX_REFERER", _generic_fix_referer(goonbox.GoonBoxCrawler), "goonbox"),("FIX_CYBERDROP_REFERER", _generic_fix_referer(cyberdrop.CyberdropCrawler), "cyberdrop"),("FIX_TURBOVID_REFERER", turbovid.fix_turbovid_referer, "turbovid"),("FIX_BUNKR_REFERER", bunkr.fix_db_referer, "bunkr"),diff --git a/cyberdrop_dl/database/schema.py b/cyberdrop_dl/database/schema.pyindex e45b7b1d0..a14a940cf 100644--- a/cyberdrop_dl/database/schema.py+++ b/cyberdrop_dl/database/schema.py@@ -32,7 +32,7 @@ class Version(NamedTuple):return ".".join(map(str, self))-CURRENT_VERSION = Version(10, 0, 0)+CURRENT_VERSION = Version(10, 1, 0)REQUIRED_VERSION = Version(9, 15, 0)logger = logging.getLogger(__name__)diff --git a/tests/crawlers/test_cases/goonbox.py b/tests/crawlers/test_cases/goonbox.pynew file mode 100644index 000000000..4cf36a900--- /dev/null+++ b/tests/crawlers/test_cases/goonbox.py@@ -0,0 +1,119 @@+DOMAIN = "goonbox"+TEST_CASES = [+ {+ "url": "https://goonbox.cr/img/tgs7KfH",+ "results": [+ {+ "url": "https://simp6.cuckcapital.cr/images4/098c105b-0c36-4fc5-afc7-78279e3bb9e7.png",+ "filename": "098c105b-0c36-4fc5-afc7-78279e3bb9e7.png",+ "debrid_url": None,+ "original_filename": "098c105b-0c36-4fc5-afc7-78279e3bb9e7.png",+ "referer": "https://goonbox.cr/img/tgs7KfH",+ "album_id": None,+ "uploaded_at": 1782580570,+ "download_folder": "re:Loose Files (GoonBox)",+ }+ ],+ "count": 1,+ },+ {+ "url": "https://goonbox.cr/a/YVuDPn",+ "results": [+ {+ "url": "https://simp6.cuckcapital.cr/images3/Screenshot_20250419_222405_Adblock-Browser3ce42a12ed2e3edf.jpg",+ "filename": "Screenshot_20250419_222405_Adblock-Browser3ce42a12ed2e3edf.jpg",+ "debrid_url": None,+ "original_filename": "Screenshot_20250419_222405_Adblock-Browser3ce42a12ed2e3edf.jpg",+ "referer": "https://goonbox.cr/img/aySgGc6",+ "album_id": "YVuDPn",+ "uploaded_at": 1745080005,+ "download_folder": "re:cpiexo (GoonBox)",+ }+ ],+ "count": 1,+ },+ {+ "url": "https://jpg6.su/img/960x1280-90c58bc6682426b5ff88266b8ec5a647.N3gCSXD",+ "results": [+ {+ "url": "https://simp6.cuckcapital.cr/images3/960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",+ "filename": "960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",+ "referer": "https://goonbox.cr/img/N3gCSXD",+ "album_id": None,+ "uploaded_at": 1753505718,+ }+ ],+ },+ {+ "url": "https://jpg7.cr/img/960x1280-90c58bc6682426b5ff88266b8ec5a647.N3gCSXD",+ "results": [+ {+ "url": "https://simp6.cuckcapital.cr/images3/960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",+ "filename": "960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",+ "referer": "https://goonbox.cr/img/N3gCSXD",+ "album_id": None,+ "uploaded_at": 1753505718,+ }+ ],+ },+ {+ "url": "https://jpg6.su/img/2520x3360-ab219efe5d20f99740d58188edd20c440659035b8a5c979d.N3iJfxa",+ "results": [+ {+ "url": "https://simp6.cuckcapital.cr/images3/2520x3360_ab219efe5d20f99740d58188edd20c440659035b8a5c979d2f40a0e086780c7d.jpg",+ "filename": "2520x3360_ab219efe5d20f99740d58188edd20c440659035b8a5c979d2f40a0e086780c7d.jpg",+ "referer": "https://goonbox.cr/img/N3iJfxa",+ "uploaded_at": int,+ }+ ],+ },+ {+ "url": "https://jpg6.su/a/testalbum.YnfD4p",+ "results": [+ {+ "url": "https://simp6.cuckcapital.cr/images3/landscape-mountains-nature-5564166880341c46b7abbe.jpg",+ "filename": "landscape-mountains-nature-5564166880341c46b7abbe.jpg",+ "referer": "https://goonbox.cr/img/N3TGEr1",+ "uploaded_at": int,+ "album_id": "YnfD4p",+ },+ {+ "url": "https://simp6.cuckcapital.cr/images3/47749882ae05d0349d87f2d.jpg",+ "filename": "47749882ae05d0349d87f2d.jpg",+ "referer": "https://goonbox.cr/img/N3TGCdA",+ "uploaded_at": int,+ "album_id": "YnfD4p",+ },+ ],+ },+ {+ "url": "https://simp6.jpg5.su/images3/Screenshot-46d10ff096ae50f993.th.png",+ "results": [+ {+ "url": "https://simp6.cuckcapital.cr/images3/Screenshot-46d10ff096ae50f993.png",+ "filename": "Screenshot-46d10ff096ae50f993.png",+ "referer": "https://simp6.cuckcapital.cr/images3/Screenshot-46d10ff096ae50f993.png",+ }+ ],+ },+ {+ "url": "https://simp6.cuckcapital.cr/images3/rebeca-yellow-pic00910102ed45e07d539.md.jpg",+ "results": [+ {+ "url": "https://simp6.cuckcapital.cr/images3/rebeca-yellow-pic00910102ed45e07d539.jpg",+ "filename": "rebeca-yellow-pic00910102ed45e07d539.jpg",+ "referer": "https://simp6.cuckcapital.cr/images3/rebeca-yellow-pic00910102ed45e07d539.jpg",+ }+ ],+ },+ {+ "url": "https://jpg5.su/img/NK9wL8h",+ "results": [+ {+ "url": "https://simp6.cuckcapital.cr/images3/Palm-Desert-Resuscitation-Education-YourCPRMD.com4fc75181ec3d573e.png",+ "filename": "Palm-Desert-Resuscitation-Education-YourCPRMD.com4fc75181ec3d573e.png",+ "referer": "https://goonbox.cr/img/NK9wL8h",+ }+ ],+ },+]diff --git a/tests/crawlers/test_cases/jpg5_su.py b/tests/crawlers/test_cases/jpg5_su.pyindex ca5741336..30346c0e8 100644--- a/tests/crawlers/test_cases/jpg5_su.py+++ b/tests/crawlers/test_cases/jpg5_su.py@@ -1,79 +1,5 @@DOMAIN = "jpg5.su"TEST_CASES = [- {- "url": "https://jpg6.su/img/960x1280-90c58bc6682426b5ff88266b8ec5a647.N3gCSXD",- "results": [- {- "url": "https://simp6.cuckcapital.cr/images3/960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",- "filename": "960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",- "referer": "https://jpg6.su/img/N3gCSXD",- "album_id": None,- "uploaded_at": 1753538118,- }- ],- },- {- "url": "https://jpg7.cr/img/960x1280-90c58bc6682426b5ff88266b8ec5a647.N3gCSXD",- "results": [- {- "url": "https://simp6.cuckcapital.cr/images3/960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",- "filename": "960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",- "referer": "https://jpg7.cr/img/N3gCSXD",- "album_id": None,- "uploaded_at": 1753538118,- }- ],- },- {- "url": "https://jpg6.su/img/2520x3360-ab219efe5d20f99740d58188edd20c440659035b8a5c979d.N3iJfxa",- "results": [- {- "url": "https://simp6.cuckcapital.cr/images3/2520x3360_ab219efe5d20f99740d58188edd20c440659035b8a5c979d2f40a0e086780c7d.jpg",- "filename": "2520x3360_ab219efe5d20f99740d58188edd20c440659035b8a5c979d2f40a0e086780c7d.jpg",- "referer": "https://jpg6.su/img/N3iJfxa",- "uploaded_at": 1753502011,- }- ],- },- {- "url": "https://jpg6.su/a/testalbum.YnfD4p",- "results": [- {- "url": "https://simp6.cuckcapital.cr/images3/landscape-mountains-nature-5564166880341c46b7abbe.jpg",- "filename": "landscape-mountains-nature-5564166880341c46b7abbe.jpg",- "referer": "https://jpg6.su/img/N3TGEr1",- "uploaded_at": None,- "album_id": "YnfD4p",- },- {- "url": "https://simp6.cuckcapital.cr/images3/47749882ae05d0349d87f2d.jpg",- "filename": "47749882ae05d0349d87f2d.jpg",- "referer": "https://jpg6.su/img/N3TGCdA",- "uploaded_at": None,- "album_id": "YnfD4p",- },- ],- },- {- "url": "https://simp6.jpg5.su/images3/Screenshot-46d10ff096ae50f993.th.png",- "results": [- {- "url": "https://simp6.cuckcapital.cr/images3/Screenshot-46d10ff096ae50f993.png",- "filename": "Screenshot-46d10ff096ae50f993.png",- "referer": "https://simp6.jpg5.su/images3/Screenshot-46d10ff096ae50f993.th.png",- }- ],- },- {- "url": "https://simp6.cuckcapital.cr/images3/rebeca-yellow-pic00910102ed45e07d539.md.jpg",- "results": [- {- "url": "https://simp6.cuckcapital.cr/images3/rebeca-yellow-pic00910102ed45e07d539.jpg",- "filename": "rebeca-yellow-pic00910102ed45e07d539.jpg",- "referer": "https://simp6.cuckcapital.cr/images3/rebeca-yellow-pic00910102ed45e07d539.md.jpg",- }- ],- },{"url": "https://jpg6.su/a/rebeca-linares-bikiniriot.aYKmSi/sub","results": [@@ -113,14 +39,4 @@ TEST_CASES = [],"count": 1065,},- {- "url": "https://jpg5.su/img/NK9wL8h",- "results": [- {- "url": "https://simp6.cuckcapital.cr/images3/Palm-Desert-Resuscitation-Education-YourCPRMD.com4fc75181ec3d573e.png",- "filename": "Palm-Desert-Resuscitation-Education-YourCPRMD.com4fc75181ec3d573e.png",- "referer": "https://jpg6.su/img/NK9wL8h",- }- ],- },]diff --git a/tests/crawlers/test_goonbox.py b/tests/crawlers/test_goonbox.pynew file mode 100644index 000000000..be98d71f1--- /dev/null+++ b/tests/crawlers/test_goonbox.py@@ -0,0 +1,34 @@+import pytest++from cyberdrop_dl.crawlers import goonbox+from cyberdrop_dl.url_objects import AbsoluteHttpURL+++ ("url", "expected"),+ [+ (+ "https://jpg6.su/img/960x1280-90c58bc6682426b5ff88266b8ec5a647.N3gCSXD",+ "https://jpg6.su/img/960x1280-90c58bc6682426b5ff88266b8ec5a647.N3gCSXD",+ ),+ (+ "https://simp6.jpg5.cr/images3/960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",+ "https://simp6.cuckcapital.cr/images3/960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",+ ),+ (+ "https://simp4.jpg5.su/images3/Screenshot",+ "https://simp4.cuckcapital.cr/images3/Screenshot",+ ),+ (+ "http://simp4.jpg5.su/images3/Screenshot",+ "http://simp4.cuckcapital.cr/images3/Screenshot",+ ),+ (+ "http://simp4.jpg7.cr/images3/Screenshot",+ "http://simp4.cuckcapital.cr/images3/Screenshot",+ ),+ ],+)+def test_fix_cdn(url: str, expected: str) -> None:+ result = str(goonbox._fix_cdn(AbsoluteHttpURL(url)))+ assert result == expecteddiff --git a/tests/crawlers/test_jpg5.py b/tests/crawlers/test_jpg5.pydeleted file mode 100644index a63d48092..000000000--- a/tests/crawlers/test_jpg5.py+++ /dev/null@@ -1,90 +0,0 @@-import pytest--from cyberdrop_dl.crawlers import jpg5-from cyberdrop_dl.url_objects import AbsoluteHttpURL--- ("url", "expected"),- [- (- "MWIxMTE4MDQxYTU2NDA1OTE2MWExZTE5NWI1ZTAwMWMxNzEyMjMxMjE5MDQwNDAyMDU1YTFhMWE0ZTFkMDgxMjE0MDYwMTUyNWY1YzQ0NDMwYjU0NWU0YzU5MzM1NjQ2MDY0NjRiMGIwZTQ2NTU1MTQ2NGQ3MjQ1MGI1ODE2MDU1MTRjNGI1ZTU3MTY1ZDE2MTA1NjEzNTc0NDUyNDM0NzQxMDY1ZjQ1MGE1YjVkNDQ1NTQ1MTU1MDBjNDM0ZDAzMDQxZQ==",- "https://simp6.cuckcapital.cr/images3/960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",- ),- (- "MWIxMTE4MDQxYTU2NDA1OTE2MWExZTE5NWI1ZTAwMWMxNzEyMjMxMjE5MDQwNDAyMDU1YTFhMWE0ZTFkMDgxMjE0MDYwMTUyNWYxNzE3MTExNjA2MGQ1OTE5MDUwMTFkNDgwMzFhMGE1ZDQwNTIwZjQ1MWM3MDE2NWE1ZDQxMDcwZDQwMWQ1ZDU3MTIwNzVkMTkxMzE1",- "https://simp6.cuckcapital.cr/images3/rebeca-pink-pic001f1e0e301dd4d56fb.jpg",- ),- (- "http://simp4.jpg5.su/images3/Screenshot",- "http://simp4.jpg5.su/images3/Screenshot",- ),- ],-)-def test_decode_url(url: str, expected: str) -> None:- result = str(jpg5._decode_url(url))- assert result == expected--- ("url", "expected"),- [- (- "https://jpg6.su/img/960x1280-90c58bc6682426b5ff88266b8ec5a647.N3gCSXD",- "https://jpg6.su/img/960x1280-90c58bc6682426b5ff88266b8ec5a647.N3gCSXD",- ),- (- "https://simp6.jpg5.cr/images3/960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",- "https://simp6.cuckcapital.cr/images3/960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",- ),- (- "https://simp4.jpg5.su/images3/Screenshot",- "https://simp4.cuckcapital.cr/images3/Screenshot",- ),- (- "http://simp4.jpg5.su/images3/Screenshot",- "http://simp4.cuckcapital.cr/images3/Screenshot",- ),- ],-)-def test_fix_cdn(url: str, expected: str) -> None:- result = str(jpg5._fix_cdn(AbsoluteHttpURL(url)))- assert result == expected--- ("url", "expected"),- [- (- "MWIxMTE4MDQxYTU2NDA1OTE2MWExZTE5NWI1ZTAwMWMxNzEyMjMxMjE5MDQwNDAyMDU1YTFhMWE0ZTFkMDgxMjE0MDYwMTUyNWY1YzQ0NDMwYjU0NWU0YzU5MzM1NjQ2MDY0NjRiMGIwZTQ2NTU1MTQ2NGQ3MjQ1MGI1ODE2MDU1MTRjNGI1ZTU3MTY1ZDE2MTA1NjEzNTc0NDUyNDM0NzQxMDY1ZjQ1MGE1YjVkNDQ1NTQ1MTU1MDBjNDM0ZDAzMDQxZQ==",- "https://simp6.cuckcapital.cr/images3/960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",- ),- (- "MWIxMTE4MDQxYTU2NDA1OTE2MWExZTE5NWI1ZTAwMWMxNzEyMjMxMjE5MDQwNDAyMDU1YTFhMWE0ZTFkMDgxMjE0MDYwMTUyNWYxNzE3MTExNjA2MGQ1OTE5MDUwMTFkNDgwMzFhMGE1ZDQwNTIwZjQ1MWM3MDE2NWE1ZDQxMDcwZDQwMWQ1ZDU3MTIwNzVkMTkxMzE1",- "https://simp6.cuckcapital.cr/images3/rebeca-pink-pic001f1e0e301dd4d56fb.jpg",- ),- (- "http://simp4.jpg5.su/images3/Screenshot",- "http://simp4.cuckcapital.cr/images3/Screenshot",- ),- (- "https://jpg6.su/img/Nv7ZaLE",- "https://jpg6.su/img/Nv7ZaLE",- ),- (- "https://jpg6.su/img/960x1280-90c58bc6682426b5ff88266b8ec5a647.N3gCSXD",- "https://jpg6.su/img/960x1280-90c58bc6682426b5ff88266b8ec5a647.N3gCSXD",- ),- (- "https://simp6.jpg5.cr/images3/960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",- "https://simp6.cuckcapital.cr/images3/960x1280_90c58bc6682426b5ff88266b8ec5a647142c31c72206f9a3.jpg",- ),- (- "https://simp4.jpg5.su/images3/Screenshot",- "https://simp4.cuckcapital.cr/images3/Screenshot",- ),- ],-)-def test_parse_url(url: str, expected: str) -> None:- result = str(jpg5.JPG5Crawler.parse_url(url))- assert result == expected