From db9743894071760f994f640a4c24358f749a78c0 Mon Sep 17 00:00:00 2001 From: Franklin Lee Date: Tue, 1 Aug 2023 11:21:16 -0700 Subject: [PATCH] [ie/PicartoVod] Fix extractor (#7727) Closes #2926 Authored by: Frankgoji --- yt_dlp/extractor/picarto.py | 54 ++++++++++++++++++++++++++++--------- 1 file changed, 42 insertions(+), 12 deletions(-) diff --git a/yt_dlp/extractor/picarto.py b/yt_dlp/extractor/picarto.py index 36a062def3..d415ba28e1 100644 --- a/yt_dlp/extractor/picarto.py +++ b/yt_dlp/extractor/picarto.py @@ -1,7 +1,10 @@ +import urllib.parse + from .common import InfoExtractor from ..utils import ( ExtractorError, - js_to_json, + str_or_none, + traverse_obj, ) @@ -84,7 +87,7 @@ def _real_extract(self, url): class PicartoVodIE(InfoExtractor): - _VALID_URL = r'https?://(?:www.)?picarto\.tv/videopopout/(?P[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?picarto\.tv/(?:videopopout|\w+/videos)/(?P[^/?#&]+)' _TESTS = [{ 'url': 'https://picarto.tv/videopopout/ArtofZod_2017.12.12.00.13.23.flv', 'md5': '3ab45ba4352c52ee841a28fb73f2d9ca', @@ -94,6 +97,18 @@ class PicartoVodIE(InfoExtractor): 'title': 'ArtofZod_2017.12.12.00.13.23.flv', 'thumbnail': r're:^https?://.*\.jpg' }, + 'skip': 'The VOD does not exist', + }, { + 'url': 'https://picarto.tv/ArtofZod/videos/772650', + 'md5': '00067a0889f1f6869cc512e3e79c521b', + 'info_dict': { + 'id': '772650', + 'ext': 'mp4', + 'title': 'Art of Zod - Drawing and Painting', + 'thumbnail': r're:^https?://.*\.jpg', + 'channel': 'ArtofZod', + 'age_limit': 18, + } }, { 'url': 'https://picarto.tv/videopopout/Plague', 'only_matching': True, @@ -102,21 +117,36 @@ class PicartoVodIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + data = self._download_json( + 'https://ptvintern.picarto.tv/ptvapi', video_id, query={ + 'query': f'''{{ + video(id: "{video_id}") {{ + id + title + adult + file_name + video_recording_image_url + channel {{ + name + }} + }} +}}''' + })['data']['video'] - vod_info = self._parse_json( - self._search_regex( - r'(?s)#vod-player["\']\s*,\s*(\{.+?\})\s*\)', webpage, - 'vod player'), - video_id, transform_source=js_to_json) + file_name = data['file_name'] + netloc = urllib.parse.urlparse(data['video_recording_image_url']).netloc formats = self._extract_m3u8_formats( - vod_info['vod'], video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls') + f'https://{netloc}/stream/hls/{file_name}/index.m3u8', video_id, 'mp4', m3u8_id='hls') return { 'id': video_id, - 'title': video_id, - 'thumbnail': vod_info.get('vodThumb'), + **traverse_obj(data, { + 'id': ('id', {str_or_none}), + 'title': ('title', {str}), + 'thumbnail': 'video_recording_image_url', + 'channel': ('channel', 'name', {str}), + 'age_limit': ('adult', {lambda x: 18 if x else 0}), + }), 'formats': formats, }