A feature-rich command-line audio/video downloader
[cleanup] Fix invalid info dict fields (#17007)
sepro98036ccd4fd9
diff --git a/yt_dlp/extractor/adobetv.py b/yt_dlp/extractor/adobetv.pyindex 7a29a349c1..3d88d4f1ac 100644--- a/yt_dlp/extractor/adobetv.py+++ b/yt_dlp/extractor/adobetv.py@@ -70,7 +70,7 @@ class AdobeTVVideoIE(InfoExtractor):for fmt in fmts:fmt.update(traverse_obj(source, {'duration': ('duration', {float_or_none(scale=1000)}),- 'filesize': ('kilobytes', {float_or_none(invscale=1000)}),+ 'filesize': ('kilobytes', {int_or_none(invscale=1000)}),'format_id': (('format', 'label'), {str}, all, {lambda x: join_nonempty(*x)}),'height': ('height', {int_or_none}),'tbr': ('bitrate', {int_or_none}),diff --git a/yt_dlp/extractor/afreecatv.py b/yt_dlp/extractor/afreecatv.pyindex d8a025976e..56bfa36529 100644--- a/yt_dlp/extractor/afreecatv.py+++ b/yt_dlp/extractor/afreecatv.py@@ -13,6 +13,7 @@ from ..utils import (int_or_none,orderedSet,parse_iso8601,+ str_or_none,url_or_none,urlencode_postdata,urljoin,@@ -465,7 +466,7 @@ class AfreecaTVUserIE(AfreecaTVBaseIE):for item in info['data']:yield self.url_result(f'https://vod.sooplive.com/player/{item["title_no"]}/',- AfreecaTVIE, item['title_no'], item.get('title_name'))+ AfreecaTVIE, str_or_none(item['title_no']), item.get('title_name'))def _real_extract(self, url):user_id, user_type = self._match_valid_url(url).group('id', 'slug_type')diff --git a/yt_dlp/extractor/alura.py b/yt_dlp/extractor/alura.pyindex ce03a4265b..957a5dc0ea 100644--- a/yt_dlp/extractor/alura.py+++ b/yt_dlp/extractor/alura.py@@ -155,7 +155,7 @@ class AluraCourseIE(AluraIE): # XXX: Do not subclass from concrete IE'_type': 'url_transparent','id': self._match_id(video_url),'url': video_url,- 'id_key': self.ie_key(),+ 'ie_key': self.ie_key(),'chapter': chapter,'chapter_number': chapter_number,}diff --git a/yt_dlp/extractor/audius.py b/yt_dlp/extractor/audius.pyindex c611c6e081..830975a27d 100644--- a/yt_dlp/extractor/audius.py+++ b/yt_dlp/extractor/audius.py@@ -2,7 +2,7 @@ import randomimport urllib.parsefrom .common import InfoExtractor-from ..utils import ExtractorError, str_or_none, try_get+from ..utils import ExtractorError, str_or_none, try_get, url_or_noneclass AudiusBaseIE(InfoExtractor):@@ -143,6 +143,8 @@ class AudiusIE(AudiusBaseIE):thumbnails = []if isinstance(artworks_data, dict):for quality_key, thumbnail_url in artworks_data.items():+ if not url_or_none(thumbnail_url):+ continuethumbnail = {'url': thumbnail_url,}diff --git a/yt_dlp/extractor/bilibili.py b/yt_dlp/extractor/bilibili.pyindex 207d48241f..4e11fc63d1 100644--- a/yt_dlp/extractor/bilibili.py+++ b/yt_dlp/extractor/bilibili.py@@ -1398,7 +1398,9 @@ class BilibiliSpaceAudioIE(BilibiliSpaceBaseIE):def get_entries(page_data):# data is None when the playlist is emptyfor entry in page_data.get('data') or []:- yield self.url_result(f'https://www.bilibili.com/audio/au{entry["id"]}', BilibiliAudioIE, entry['id'])+ yield self.url_result(+ f'https://www.bilibili.com/audio/au{entry["id"]}',+ BilibiliAudioIE, str_or_none(entry['id']))_, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries)return self.playlist_result(paged_list, playlist_id)diff --git a/yt_dlp/extractor/err.py b/yt_dlp/extractor/err.pyindex c931fa82fd..64a7e28f04 100644--- a/yt_dlp/extractor/err.py+++ b/yt_dlp/extractor/err.py@@ -235,7 +235,7 @@ class ERRArhiivIE(InfoExtractor):'title': 'Kontsertpalad: 255 | L. Beethoveni sonaat c-moll, "Pateetiline"','description': 'md5:a70f4ff23c3618f3be63f704bccef063','series': 'Kontsertpalad',- 'episode_id': 255,+ 'episode_id': '255','timestamp': 1666152162,'upload_date': '20221019','release_year': 1970,@@ -282,7 +282,7 @@ class ERRArhiivIE(InfoExtractor):'title': ('title', {str}),'series': ('seriesTitle', {str}, filter),'series_id': ('seriesId', {str}, filter),- 'episode_id': ('episode', {int_or_none}),+ 'episode_id': ('episode', {str}, filter),'description': ('synopsis', {str}, filter),'timestamp': ('uploadDate', {parse_iso8601}),'modified_timestamp': ('dateModified', {parse_iso8601}),diff --git a/yt_dlp/extractor/ichinanalive.py b/yt_dlp/extractor/ichinanalive.pyindex 475d33593d..af1a002931 100644--- a/yt_dlp/extractor/ichinanalive.py+++ b/yt_dlp/extractor/ichinanalive.py@@ -125,20 +125,20 @@ class IchinanaLiveClipIE(InfoExtractor):formats = []if view_data.get('videoURL'):formats.append({- 'id': 'video',+ 'format_id': 'video','url': view_data['videoURL'],'quality': -1,})if view_data.get('transcodeURL'):formats.append({- 'id': 'transcode',+ 'format_id': 'transcode','url': view_data['transcodeURL'],'quality': -1,})if view_data.get('srcVideoURL'):# highest qualityformats.append({- 'id': 'srcVideo',+ 'format_id': 'srcVideo','url': view_data['srcVideoURL'],'quality': 1,})diff --git a/yt_dlp/extractor/idagio.py b/yt_dlp/extractor/idagio.pyindex a99c559065..16c445edb8 100644--- a/yt_dlp/extractor/idagio.py+++ b/yt_dlp/extractor/idagio.py@@ -1,5 +1,5 @@from .common import InfoExtractor-from ..utils import int_or_none, unified_timestamp, url_or_none+from ..utils import int_or_none, str_or_none, unified_timestamp, url_or_nonefrom ..utils.traversal import traverse_obj@@ -83,7 +83,7 @@ class IdagioPlaylistBaseIE(InfoExtractor):recording_id = track_data['recording']['id']yield self.url_result(f'https://app.idagio.com/recordings/{recording_id}?trackId={track_id}',- ie=IdagioTrackIE, video_id=track_id)+ ie=IdagioTrackIE, video_id=str_or_none(track_id))def _real_extract(self, url):playlist_id = self._match_id(url)diff --git a/yt_dlp/extractor/itv.py b/yt_dlp/extractor/itv.pyindex 1f4020847c..65e6443729 100644--- a/yt_dlp/extractor/itv.py+++ b/yt_dlp/extractor/itv.py@@ -13,6 +13,7 @@ from ..utils import (merge_dicts,parse_duration,smuggle_url,+ str_or_none,try_get,url_basename,url_or_none,@@ -247,7 +248,7 @@ class ITVBTCCIE(InfoExtractor):for video in json_map:if not any(traverse_obj(video, ('data', attr)) == 'Brightcove' for attr in ('name', 'type')):continue- video_id = video['data']['id']+ video_id = str_or_none(video['data']['id'])account_id = video['data']['accountId']player_id = video['data']['playerId']entries.append(self.url_result(diff --git a/yt_dlp/extractor/lecturio.py b/yt_dlp/extractor/lecturio.pyindex 4cfb872241..313bb5f702 100644--- a/yt_dlp/extractor/lecturio.py+++ b/yt_dlp/extractor/lecturio.py@@ -5,7 +5,6 @@ from ..utils import (ExtractorError,clean_html,determine_ext,- float_or_none,int_or_none,str_or_none,url_or_none,@@ -130,7 +129,7 @@ class LecturioIE(LecturioBaseIE):f = {'url': file_url,'format_id': label,- 'filesize': float_or_none(filesize, invscale=1000),+ 'filesize': int_or_none(filesize, invscale=1000),}if label:mobj = re.match(r'(\d+)p\s*\(([^)]+)\)', label)diff --git a/yt_dlp/extractor/neteasemusic.py b/yt_dlp/extractor/neteasemusic.pyindex e3b5f47936..0617187800 100644--- a/yt_dlp/extractor/neteasemusic.py+++ b/yt_dlp/extractor/neteasemusic.py@@ -658,7 +658,7 @@ class NetEaseMusicDjRadioIE(NetEaseMusicBaseIE):entries.extend(self.url_result(f'http://music.163.com/#/program?id={program["id"]}', NetEaseMusicProgramIE,- program['id'], program.get('name')) for program in info['programs'])+ str_or_none(program['id']), program.get('name')) for program in info['programs'])if not metainfo:metainfo = traverse_obj(info, ('programs', 0, 'radio', {'title': ('name', {str}),diff --git a/yt_dlp/extractor/peertube.py b/yt_dlp/extractor/peertube.pyindex 40312cf7dc..34b9bc55a7 100644--- a/yt_dlp/extractor/peertube.py+++ b/yt_dlp/extractor/peertube.py@@ -1686,7 +1686,7 @@ class PeerTubePlaylistIE(InfoExtractor):'description': 'Diversas palestras do Richard Stallman no Brasil.','title': 'Richard Stallman no Brasil','channel': 'debianbrazilteam',- 'channel_id': 1522,+ 'channel_id': '1522','thumbnail': r're:https?://peertube\.debian\.social/lazy-static/thumbnails/.+\.jpg','timestamp': 1599676222,'upload_date': '20200909',@@ -1698,7 +1698,7 @@ class PeerTubePlaylistIE(InfoExtractor):'id': 'chocobozzz','title': 'chocobozzz','channel': 'chocobozzz',- 'channel_id': 37855,+ 'channel_id': '37855','thumbnail': '','timestamp': 1553874564,'upload_date': '20190329',@@ -1710,7 +1710,7 @@ class PeerTubePlaylistIE(InfoExtractor):'id': 'bf54d359-cfad-4935-9d45-9d6be93f63e8','title': 'Les vidéos de Framasoft','channel': 'framasoft',- 'channel_id': 3,+ 'channel_id': '3','thumbnail': '','timestamp': 1519917377,'upload_date': '20180301',@@ -1720,9 +1720,10 @@ class PeerTubePlaylistIE(InfoExtractor):'url': 'https://peertube2.cpy.re/c/[email protected]/videos','info_dict': {'id': '[email protected]',- 'title': 'Official Blender Open Movies',+ 'title': 'Blender Open Movies',+ 'description': 'md5:3dfabff00857fe3896fb222eb2cb1b80','channel': 'blender',- 'channel_id': 1926,+ 'channel_id': '1926','thumbnail': '','timestamp': 1540472902,'upload_date': '20181025',@@ -1756,7 +1757,7 @@ class PeerTubePlaylistIE(InfoExtractor):playlist_description = info.get('description')playlist_timestamp = unified_timestamp(info.get('createdAt'))channel = try_get(info, lambda x: x['ownerAccount']['name']) or info.get('displayName')- channel_id = try_get(info, lambda x: x['ownerAccount']['id']) or info.get('id')+ channel_id = str_or_none(try_get(info, lambda x: x['ownerAccount']['id']) or info.get('id'))thumbnail = format_field(info, 'thumbnailPath', f'https://{host}%s')entries = OnDemandPagedList(functools.partial(diff --git a/yt_dlp/extractor/qqmusic.py b/yt_dlp/extractor/qqmusic.pyindex 56a8e7300a..f631dc983c 100644--- a/yt_dlp/extractor/qqmusic.py+++ b/yt_dlp/extractor/qqmusic.py@@ -79,7 +79,6 @@ class QQMusicIE(QQMusicBaseIE):'creators': ['ケーキ姫', 'JUMA'],'genres': ['Pop'],'description': 'md5:b5261f3d595657ae561e9e6aee7eb7d9',- 'size': 4501244,'thumbnail': r're:^https?://.*\.jpg(?:$|[#?])','subtitles': 'count:1',},@@ -113,7 +112,6 @@ class QQMusicIE(QQMusicBaseIE):'creators': ['李季美'],'genres': [],'description': 'md5:fc711212aa623b28534954dc4bd67385',- 'size': 3535730,'thumbnail': r're:^https?://.*\.jpg(?:$|[#?])',},}, {@@ -191,7 +189,7 @@ class QQMusicIE(QQMusicBaseIE):'url': urljoin('https://dl.stream.qqmusic.qq.com', media_info['purl']),'format': format_id,'format_id': format_id,- 'size': traverse_obj(info_data, ('file', f'size_{format_id}', {int_or_none})),+ 'filesize': traverse_obj(info_data, ('file', f'size_{format_id}', {int_or_none})),'quality': format_info.get('preference'),'abr': format_info.get('abr'),'ext': format_info.get('ext'),@@ -261,7 +259,6 @@ class QQMusicSingerIE(QQMusicBaseIE):'creators': ['桃几OvO'],'genres': ['Pop'],'description': 'md5:4296005a04edcb5cdbe0889d5055a7ae',- 'size': 3970822,'thumbnail': r're:^https?://.*\.jpg(?:$|[#?])',},}],diff --git a/yt_dlp/extractor/rcti.py b/yt_dlp/extractor/rcti.pyindex c8e57e2aba..cc693fec13 100644--- a/yt_dlp/extractor/rcti.py+++ b/yt_dlp/extractor/rcti.py@@ -7,6 +7,7 @@ from ..networking.exceptions import HTTPErrorfrom ..utils import (ExtractorError,dict_get,+ str_or_none,strip_or_none,traverse_obj,try_get,@@ -80,7 +81,11 @@ class RCTIPlusIE(RCTIPlusBaseIE):'timestamp': 1587561540,'upload_date': '20200422','series': 'iNews Malam',- 'channel': 'INews',+ 'channel': 'INEWS',+ 'channel_id': '4',+ 'thumbnail': 'https://static.rctiplus.id/media/2000/files/fta_rcti/Portrait/iNews_Malam/inews_malam_768x1152.jpg',+ 'categories': ['Hard News'],+ 'live_status': 'not_live',},}, { # Missed event/replay'url': 'https://www.rctiplus.com/missed-event/2507/mou-signing-ceremony-27-juli-2021-1400-wib',@@ -117,12 +122,13 @@ class RCTIPlusIE(RCTIPlusBaseIE):'url': 'https://www.rctiplus.com/live-event/1/rcti','info_dict': {'id': 'v_lt1',- 'title': 'RCTI',+ 'title': r're:RCTI \d{4}-\d{2}-\d{2} \d{2}:\d{2}','display_id': 'rcti','ext': 'mp4','timestamp': 1546344000,'upload_date': '20190101',- 'is_live': True,+ 'thumbnail': 'https://static.rctiplus.id/media/2000/files/fta_rcti/Channel_Logo/por-RCTI.png',+ 'live_status': 'is_live',},'params': {'skip_download': True,@@ -207,7 +213,7 @@ class RCTIPlusIE(RCTIPlusBaseIE):'season_number': video_meta.get('season'),'episode_number': video_meta.get('episode'),'channel': video_json.get('tv_name'),- 'channel_id': video_json.get('tv_id'),+ 'channel_id': str_or_none(video_json.get('tv_id')),'formats': formats,'thumbnails': thumbnails,'is_live': video_type == 'live-event' and not is_upcoming,diff --git a/yt_dlp/extractor/redgifs.py b/yt_dlp/extractor/redgifs.pyindex cd3cd323e5..c7787c949a 100644--- a/yt_dlp/extractor/redgifs.py+++ b/yt_dlp/extractor/redgifs.py@@ -30,7 +30,7 @@ class RedGifsBaseIE(InfoExtractor):quality = qualities(tuple(self._FORMATS.keys()))orig_height = int_or_none(gif_data.get('height'))- aspect_ratio = try_get(gif_data, lambda x: orig_height / x['width'])+ aspect_ratio = try_get(gif_data, lambda x: x['width'] / orig_height)formats = []for format_id, height in self._FORMATS.items():@@ -41,7 +41,7 @@ class RedGifsBaseIE(InfoExtractor):formats.append({'url': video_url,'format_id': format_id,- 'width': height * aspect_ratio if aspect_ratio else None,+ 'width': int_or_none(height * aspect_ratio) if aspect_ratio else None,'height': height,'quality': quality(format_id),})diff --git a/yt_dlp/extractor/rule34video.py b/yt_dlp/extractor/rule34video.pyindex 3630f5e40c..22c94ff1fe 100644--- a/yt_dlp/extractor/rule34video.py+++ b/yt_dlp/extractor/rule34video.py@@ -77,7 +77,7 @@ class Rule34VideoIE(InfoExtractor):formats.append({'url': url,'ext': ext.lower(),- 'quality': quality,+ 'quality': int_or_none(quality),})categories, creators, uploader, uploader_url = [None] * 4diff --git a/yt_dlp/extractor/sovietscloset.py b/yt_dlp/extractor/sovietscloset.pyindex d35214aa84..499402f16b 100644--- a/yt_dlp/extractor/sovietscloset.py+++ b/yt_dlp/extractor/sovietscloset.py@@ -1,6 +1,6 @@from .bunnycdn import BunnyCdnIEfrom .common import InfoExtractor-from ..utils import make_archive_id, try_get, unified_timestamp+from ..utils import make_archive_id, str_or_none, try_get, unified_timestampclass SovietsClosetBaseIE(InfoExtractor):@@ -182,7 +182,7 @@ class SovietsClosetPlaylistIE(SovietsClosetBaseIE):entries = [{**self.url_result(f'https://sovietscloset.com/video/{stream["id"]}', ie=SovietsClosetIE.ie_key()),**self.video_meta(- video_id=stream['id'], game_name=game['name'], category_name=category.get('name'),+ video_id=str_or_none(stream['id']), game_name=game['name'], category_name=category.get('name'),episode_number=i + 1, stream_date=stream.get('date')),} for i, stream in enumerate(category['streams'])]diff --git a/yt_dlp/extractor/spreaker.py b/yt_dlp/extractor/spreaker.pyindex c64c2fcd2e..ef8a5af88c 100644--- a/yt_dlp/extractor/spreaker.py+++ b/yt_dlp/extractor/spreaker.py@@ -39,7 +39,7 @@ def _extract_episode(data, episode_id=None):return {'id': str(episode_id or data['episode_id']),'url': download_url,- 'display_id': data.get('permalink'),+ 'display_id': str_or_none(data.get('permalink')),'title': title,'description': data.get('description'),'timestamp': unified_timestamp(data.get('published_at')),diff --git a/yt_dlp/extractor/teamtreehouse.py b/yt_dlp/extractor/teamtreehouse.pyindex ba25cdcf65..f4e230f522 100644--- a/yt_dlp/extractor/teamtreehouse.py+++ b/yt_dlp/extractor/teamtreehouse.py@@ -105,7 +105,7 @@ class TeamTreeHouseIE(InfoExtractor):'_type': 'url_transparent','id': self._match_id(page_url),'url': page_url,- 'id_key': self.ie_key(),+ 'ie_key': self.ie_key(),}if extract_info:entry.update(extract_info)diff --git a/yt_dlp/extractor/weibo.py b/yt_dlp/extractor/weibo.pyindex dc8a2cd753..c02ce8e028 100644--- a/yt_dlp/extractor/weibo.py+++ b/yt_dlp/extractor/weibo.py@@ -94,7 +94,7 @@ class WeiboBaseIE(InfoExtractor):**parse_resolution(resolution),**traverse_obj(media_info, ('video_details', lambda _, v: v['label'].startswith(format_id), {- 'size': ('size', {int_or_none}),+ 'filesize': ('size', {int_or_none}),'tbr': ('bitrate', {int_or_none}),},), get_all=False),diff --git a/yt_dlp/extractor/ximalaya.py b/yt_dlp/extractor/ximalaya.pyindex 02bf6a7beb..5e1b4c7804 100644--- a/yt_dlp/extractor/ximalaya.py+++ b/yt_dlp/extractor/ximalaya.py@@ -36,11 +36,11 @@ class XimalayaIE(XimalayaBaseIE):'thumbnail': r're:^https?://.*\.jpg','thumbnails': [{- 'name': 'cover_url',+ 'id': 'cover_url','url': r're:^https?://.*\.jpg',},{- 'name': 'cover_url_142',+ 'id': 'cover_url_142','url': r're:^https?://.*\.jpg','width': 180,'height': 180,@@ -65,11 +65,11 @@ class XimalayaIE(XimalayaBaseIE):'thumbnail': r're:^https?://.*\.jpg','thumbnails': [{- 'name': 'cover_url',+ 'id': 'cover_url','url': r're:^https?://.*\.jpg',},{- 'name': 'cover_url_142',+ 'id': 'cover_url_142','url': r're:^https?://.*\.jpg','width': 180,'height': 180,@@ -172,7 +172,7 @@ class XimalayaIE(XimalayaBaseIE):for k in audio_info:# cover pics kyes like: cover_url', 'cover_url_142'if k.startswith('cover_url'):- thumbnail = {'name': k, 'url': audio_info[k]}+ thumbnail = {'id': k, 'url': audio_info[k]}if k == 'cover_url_142':thumbnail['width'] = 180thumbnail['height'] = 180