From 9f1e9dab21bbe651544c8f4663b0e615dc450e4d Mon Sep 17 00:00:00 2001 From: dasidiot <140998618+dasidiot@users.noreply.github.com> Date: Sat, 20 Jan 2024 21:46:53 -0500 Subject: [PATCH] [ie/motherless] Support uploader playlists (#8994) Authored by: dasidiot --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/motherless.py | 31 ++++++++++++++++++++++++++++--- 2 files changed, 29 insertions(+), 3 deletions(-) diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index c4f1ccb8e4..a273ae0d9c 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -1111,6 +1111,7 @@ MotherlessIE, MotherlessGroupIE, MotherlessGalleryIE, + MotherlessUploaderIE, ) from .motorsport import MotorsportIE from .moviepilot import MoviepilotIE diff --git a/yt_dlp/extractor/motherless.py b/yt_dlp/extractor/motherless.py index e359c44e93..160150a7b6 100644 --- a/yt_dlp/extractor/motherless.py +++ b/yt_dlp/extractor/motherless.py @@ -177,6 +177,7 @@ def _real_extract(self, url): class MotherlessPaginatedIE(InfoExtractor): + _EXTRA_QUERY = {} _PAGE_SIZE = 60 def _correct_path(self, url, item_id): @@ -199,7 +200,7 @@ def _real_extract(self, url): def get_page(idx): page = idx + 1 current_page = webpage if not idx else self._download_webpage( - real_url, item_id, note=f'Downloading page {page}', query={'page': page}) + real_url, item_id, note=f'Downloading page {page}', query={'page': page, **self._EXTRA_QUERY}) yield from self._extract_entries(current_page, real_url) return self.playlist_result( @@ -213,7 +214,7 @@ class MotherlessGroupIE(MotherlessPaginatedIE): 'url': 'http://motherless.com/gv/movie_scenes', 'info_dict': { 'id': 'movie_scenes', - 'title': 'Movie Scenes', + 'title': 'Movie Scenes - Videos - Hot and sexy scenes from "regular" movies... Beautiful actresses fully', }, 'playlist_mincount': 540, }, { @@ -244,7 +245,7 @@ class MotherlessGalleryIE(MotherlessPaginatedIE): 'id': '338999F', 'title': 'Random', }, - 'playlist_mincount': 190, + 'playlist_mincount': 171, }, { 'url': 'https://motherless.com/GVABD6213', 'info_dict': { @@ -270,3 +271,27 @@ class MotherlessGalleryIE(MotherlessPaginatedIE): def _correct_path(self, url, item_id): return urllib.parse.urljoin(url, f'/GV{item_id}') + + +class MotherlessUploaderIE(MotherlessPaginatedIE): + _VALID_URL = r'https?://(?:www\.)?motherless\.com/u/(?P\w+)/?(?:$|[?#])' + _TESTS = [{ + 'url': 'https://motherless.com/u/Mrgo4hrs2023', + 'info_dict': { + 'id': 'Mrgo4hrs2023', + 'title': "Mrgo4hrs2023's Uploads - Videos", + }, + 'playlist_mincount': 32, + }, { + 'url': 'https://motherless.com/u/Happy_couple?t=v', + 'info_dict': { + 'id': 'Happy_couple', + 'title': "Happy_couple's Uploads - Videos", + }, + 'playlist_mincount': 8, + }] + + _EXTRA_QUERY = {'t': 'v'} + + def _correct_path(self, url, item_id): + return urllib.parse.urljoin(url, f'/u/{item_id}?t=v')