Skip to content

Bulk asynchronous downloader for multiple file hosts

feat: Adding support to hashtags (TWPornstars) (#2063)

Barbarella66666668a21fca2c650
diff --git a/cyberdrop_dl/crawlers/twpornstars.py b/cyberdrop_dl/crawlers/twpornstars.py
index 12edf1288..86915c9ea 100644
--- a/cyberdrop_dl/crawlers/twpornstars.py
+++ b/cyberdrop_dl/crawlers/twpornstars.py
@@ -9,7 +9,7 @@ from cyberdrop_dl.utils import css
from cyberdrop_dl.utils.errors import error_handling_wrapper
if TYPE_CHECKING:
- from cyberdrop_dl.crawlers.crawler import SupportedDomains
+ from cyberdrop_dl.crawlers.crawler import SupportedDomains, SupportedPaths
from cyberdrop_dl.url_objects import ScrapeItem
@@ -34,6 +34,11 @@ class TwPornstarsCrawler(TwimgCrawler):
"www.indiantw.com",
"www.twpornstars.com",
)
+ SUPPORTED_PATHS: ClassVar[SupportedPaths] = {
+ "Post": "/p/<post_id>",
+ "Hashtag": "/hashtag/<hashtags>",
+ "Collection/User": "/<name>",
+ }
PRIMARY_URL: ClassVar[AbsoluteHttpURL] = AbsoluteHttpURL("https://www.twpornstars.com")
NEXT_PAGE_SELECTOR: ClassVar[str] = Selector.NEXT_PAGE
DOMAIN: ClassVar[str] = "twpornstars"
@@ -43,6 +48,8 @@ class TwPornstarsCrawler(TwimgCrawler):
match scrape_item.url.parts[1:]:
case ["p", _post_id]:
return await self.media(scrape_item)
+ case ["hashtag", _slug]:
+ return await self.collection(scrape_item)
case [_]:
return await self.collection(scrape_item)
case _:
diff --git a/tests/crawlers/test_cases/twpornstars.py b/tests/crawlers/test_cases/twpornstars.py
index 8bb8b1c99..77d2f7ca8 100644
--- a/tests/crawlers/test_cases/twpornstars.py
+++ b/tests/crawlers/test_cases/twpornstars.py
@@ -30,4 +30,18 @@ TEST_CASES = [
],
"count": range(49, 60),
},
+ {
+ "url": "https://www.twpornstars.com/hashtag/exhib-asswednesday",
+ "results": [
+ {
+ "url": "ANY",
+ "debrid_url": None,
+ "referer": "re:https://www.twpornstars.com/p/",
+ "album_id": None,
+ "uploaded_at": None,
+ "download_folder": "re:#exhib, #asswednesday (TWPornStars)",
+ },
+ ],
+ "count": range(5, 60),
+ },
]