From f4ad919298968e480d14467ba20c0dca34e1a27c Mon Sep 17 00:00:00 2001 From: i6t <62123048+i6t@users.noreply.github.com> Date: Sat, 19 Mar 2022 06:06:52 +0900 Subject: [PATCH] [Veo] Fix extractor (#3101) Authored by: i6t --- yt_dlp/extractor/veo.py | 42 ++++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 19 deletions(-) diff --git a/yt_dlp/extractor/veo.py b/yt_dlp/extractor/veo.py index 9bc41114a..d87bb5b47 100644 --- a/yt_dlp/extractor/veo.py +++ b/yt_dlp/extractor/veo.py @@ -6,6 +6,7 @@ from ..utils import ( int_or_none, mimetype2ext, + str_or_none, unified_timestamp, url_or_none, ) @@ -24,6 +25,7 @@ class VeoIE(InfoExtractor): 'upload_date': '20201028', 'timestamp': 1603847208, 'duration': 1916, + 'view_count': int, } }, { 'url': 'https://app.veo.co/matches/20220313-2022-03-13_u15m-plsjq-vs-csl/', @@ -39,39 +41,41 @@ def _real_extract(self, url): video_data = self._download_json( 'https://app.veo.co/api/app/matches/%s/videos' % video_id, video_id, 'Downloading video data') - title = metadata.get('title') - thumbnail = url_or_none(metadata.get('thumbnail')) - - timestamp = unified_timestamp(metadata.get('created')) - duration = int_or_none(metadata.get('duration')) - view_count = int_or_none(metadata.get('view_count')) - formats = [] for fmt in video_data: - mimetype = fmt.get('mime_type') + mimetype = str_or_none(fmt.get('mime_type')) + format_url = url_or_none(fmt.get('url')) # skip configuration file for panoramic video - if mimetype == 'video/mp2t': + if not format_url or mimetype == 'video/mp2t': continue + height = int_or_none(fmt.get('height')) - bitrate = int_or_none(fmt.get('bit_rate'), scale=1000) - render_type = fmt.get('render_type') + render_type = str_or_none(fmt.get('render_type')) + format_id = f'{render_type}-{height}p' if render_type and height else None + + # Veo returns panoramic video information even if panoramic video is not available. + # e.g. https://app.veo.co/matches/20201027-last-period/ + if render_type == 'panorama': + if not self._is_valid_url(format_url, video_id, format_id): + continue + formats.append({ - 'url': url_or_none(fmt.get('url')), - 'format_id': '%s-%sp' % (render_type, height), + 'url': format_url, + 'format_id': format_id, 'ext': mimetype2ext(mimetype), 'width': int_or_none(fmt.get('width')), 'height': height, - 'vbr': bitrate + 'vbr': int_or_none(fmt.get('bit_rate'), scale=1000), }) self._sort_formats(formats) return { 'id': video_id, - 'title': title, + 'title': str_or_none(metadata.get('title')), 'formats': formats, - 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'view_count': view_count, - 'duration': duration + 'thumbnail': url_or_none(metadata.get('thumbnail')), + 'timestamp': unified_timestamp(metadata.get('created')), + 'view_count': int_or_none(metadata.get('view_count')), + 'duration': int_or_none(metadata.get('duration')), }