From 6f69101dc912690338d32e2aab085c32e44eba3f Mon Sep 17 00:00:00 2001 From: Vladislav <117850688+7vlad7@users.noreply.github.com> Date: Mon, 19 Jun 2023 23:43:35 +0300 Subject: [PATCH] [extractor/yappy] YappyProfile: Add extractor (#7346) Authored by: 7vlad7 --- yt_dlp/extractor/_extractors.py | 5 ++++- yt_dlp/extractor/yappy.py | 30 +++++++++++++++++++++++++++++- 2 files changed, 33 insertions(+), 2 deletions(-) diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 394f3c29d..7e1fa4a0d 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -2427,7 +2427,10 @@ ZenYandexChannelIE, ) from .yapfiles import YapFilesIE -from .yappy import YappyIE +from .yappy import ( + YappyIE, + YappyProfileIE, +) from .yesjapan import YesJapanIE from .yinyuetai import YinYueTaiIE from .yle_areena import YleAreenaIE diff --git a/yt_dlp/extractor/yappy.py b/yt_dlp/extractor/yappy.py index f168bdbf9..7b3d0cb81 100644 --- a/yt_dlp/extractor/yappy.py +++ b/yt_dlp/extractor/yappy.py @@ -1,9 +1,10 @@ from .common import InfoExtractor from ..utils import ( + OnDemandPagedList, int_or_none, traverse_obj, unified_timestamp, - url_or_none + url_or_none, ) @@ -97,3 +98,30 @@ def _real_extract(self, url): 'categories': traverse_obj(media_data, ('categories', ..., 'name')) or None, 'repost_count': int_or_none(media_data.get('sharingCount')) } + + +class YappyProfileIE(InfoExtractor): + _VALID_URL = r'https?://yappy\.media/profile/(?P\w+)' + _TESTS = [{ + 'url': 'https://yappy.media/profile/59a0c8c485e5410b9c43474bf4c6a373', + 'info_dict': { + 'id': '59a0c8c485e5410b9c43474bf4c6a373', + }, + 'playlist_mincount': 527, + }] + + def _real_extract(self, url): + profile_id = self._match_id(url) + + def fetch_page(page_num): + page_num += 1 + videos = self._download_json( + f'https://yappy.media/api/video/list/{profile_id}?page={page_num}', + profile_id, f'Downloading profile page {page_num} JSON') + + for video in traverse_obj(videos, ('results', lambda _, v: v['uuid'])): + yield self.url_result( + f'https://yappy.media/video/{video["uuid"]}', YappyIE, + video['uuid'], video.get('description')) + + return self.playlist_result(OnDemandPagedList(fetch_page, 15), profile_id)