This commit is contained in:
Simon
2026-04-03 17:20:11 +00:00
parent 4b017fafdf
commit 067ff3d1da
4 changed files with 6033 additions and 0 deletions

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

1
prompts/new-channel.md Normal file
View File

@@ -0,0 +1 @@
write a provider for the site "vjav.com". use playwright-mcp to get the index site and get the layout of videos from this. also figure out how searches work and if it has a different layout then. also find out how more videos get loaded/more pages urls. also find if it has video sites like recommended,most views etc and include them. try to find as much information about a video on the site as possible and build the video items with all the information. put tags and uploader into lists so they can be utilized later. on query check if the search already exists in these FilterObject arrays and use them for the url instead (similar to omgxxx). after coding this, test that all provided urls work, yt-dlp can download the video.url, the thumbnails work, searches, tag-/uploader- searches work, more pages work. analzye the provider too and set the channel tags and put it in a group that matches this provider or create a new group where it fits in. do not include the embed field in the videoitems responses. when parsing uploaders, make sure that the uploaders. if unsure about the endpoints, check with the docs dir.