[extractor] Standardize _live_title

This commit is contained in:
pukkandan 2021-12-15 21:30:46 +05:30
parent 46383212b3
commit 39ca3b5c7f
No known key found for this signature in database
GPG Key ID: 0F00D95A001F4698
67 changed files with 68 additions and 94 deletions

View File

@ -2673,6 +2673,9 @@ def process_info(self, info_dict):
if self._num_downloads >= int(max_downloads):
raise MaxDownloadsReached()
if info_dict.get('is_live'):
info_dict['title'] += ' ' + datetime.datetime.now().strftime('%Y-%m-%d %H:%M')
# TODO: backward compatibility, to be removed
info_dict['fulltitle'] = info_dict['title']

View File

@ -233,8 +233,6 @@ def tokenize_url(url, token):
}]
is_live = video_params.get('livestream') == '1'
if is_live:
title = self._live_title(title)
return {
'id': video_id,

View File

@ -31,7 +31,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'formats': formats,
'is_live': is_live,
}

View File

@ -158,7 +158,7 @@ def _real_extract(self, url):
return {
'id': uuid,
'title': self._live_title(title) if is_live else title,
'title': title,
'thumbnail': try_get(video, lambda x: x['promo_image']['url']),
'description': try_get(video, lambda x: x['subheadlines']['basic']),
'formats': formats,

View File

@ -280,7 +280,7 @@ def _real_extract(self, url):
info.update({
'id': video_id,
'title': self._live_title(title) if info.get('is_live') else title,
'title': title,
'description': description,
'thumbnail': thumbnail,
})

View File

@ -41,7 +41,7 @@ def _parse_video_data(self, video_data, video_id, is_live):
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'description': video_data.get('description_en') or video_data.get('description_ar'),
'thumbnail': 'http://admin.mangomolo.com/analytics/%s' % img if img else None,
'duration': int_or_none(video_data.get('duration')),

View File

@ -51,7 +51,7 @@ def _real_extract(self, url):
return {
'id': username,
'title': self._live_title(channel['data']['title']),
'title': channel['data']['title'],
'uploader': username,
'uploader_id': username,
'formats': formats,

View File

@ -49,7 +49,7 @@ def _real_extract(self, url):
return {
'id': channel_id,
'title': self._live_title(uploader or uploader_id),
'title': uploader or uploader_id,
'uploader': uploader,
'uploader_id': uploader_id,
'like_count': like_count,

View File

@ -581,7 +581,7 @@ def build_format_id(kind):
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'description': clean_html(json_data.get('description')),
'thumbnail': json_data.get('thumbnail') or json_data.get('poster'),
'thumbnials': thumbnails,

View File

@ -25,7 +25,7 @@ def _real_extract(self, url):
return {
'id': channel_id,
'title': self._live_title(channel_id),
'title': channel_id,
'is_live': True,
'age_limit': 18,
'formats': formats,

View File

@ -91,7 +91,7 @@ def _real_extract(self, url):
return {
'id': user_id,
'title': self._live_title(user_id),
'title': user_id,
'is_live': True,
'formats': formats,
'age_limit': 18

View File

@ -212,8 +212,6 @@ def _real_extract(self, url):
if playlist_len == 1:
final_title = playlist_title or title
if is_live:
final_title = self._live_title(final_title)
else:
final_title = '%s (%s)' % (playlist_title, title)

View File

@ -101,7 +101,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'title': self._live_title(video_id),
'title': video_id,
'thumbnail': 'https://roomimg.stream.highwebmedia.com/ri/%s.jpg' % video_id,
'age_limit': self._rta_search(webpage),
'is_live': True,

View File

@ -3456,10 +3456,8 @@ def _parse_jwplayer_formats(self, jwplayer_sources_data, video_id=None,
return formats
def _live_title(self, name):
""" Generate the title for a live video """
now = datetime.datetime.now()
now_str = now.strftime('%Y-%m-%d %H:%M')
return name + ' ' + now_str
self._downloader.deprecation_warning('yt_dlp.InfoExtractor._live_title is deprecated and does not work as expected')
return name
def _int(self, v, name, fatal=False, **kwargs):
res = int_or_none(v, **kwargs)

View File

@ -305,7 +305,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'description': clean_html(media.get('description')),
'thumbnails': thumbnails,
'duration': int_or_none(metadata.get('duration')) or None,

View File

@ -84,7 +84,7 @@ def _real_extract(self, url):
self._sort_formats(formats)
return {
'id': display_name,
'title': self._live_title(title),
'title': title,
'uploader': display_name,
'uploader_id': username,
'formats': formats,

View File

@ -105,7 +105,7 @@ def _real_extract(self, url):
'aid': 'pcclient'
})['data']['live_url']
title = self._live_title(unescapeHTML(room['room_name']))
title = unescapeHTML(room['room_name'])
description = room.get('show_details')
thumbnail = room.get('room_src')
uploader = room.get('nickname')

View File

@ -321,7 +321,7 @@ def _real_extract(self, url):
channel_data = self._download_json(
'https://www.dr.dk/mu-online/api/1.0/channel/' + channel_id,
channel_id)
title = self._live_title(channel_data['Title'])
title = channel_data['Title']
formats = []
for streaming_server in channel_data.get('StreamingServers', []):

View File

@ -170,7 +170,7 @@ def _real_extract(self, url):
return {
'id': channel_id,
'display_id': channel_data.get('alias'),
'title': self._live_title(title) if is_live else title,
'title': title,
'description': channel_data.get('description'),
'thumbnails': thumbnails,
'formats': formats,

View File

@ -203,7 +203,7 @@ def _extract_video(self, video_id, catalogue=None):
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'thumbnail': image,
'duration': duration,
'timestamp': timestamp,

View File

@ -59,9 +59,6 @@ def _real_extract(self, url):
stream_url, video_id, 'mp4',
'm3u8_native', m3u8_id='hls')
if is_live:
title = self._live_title(title)
return {
'id': video_id,
'formats': formats,

View File

@ -209,6 +209,6 @@ def _real_extract(self, url):
'https://www.smashcast.tv/api/media/live', video_id)
metadata['formats'] = formats
metadata['is_live'] = True
metadata['title'] = self._live_title(metadata.get('title'))
metadata['title'] = metadata.get('title')
return metadata

View File

@ -88,7 +88,7 @@ def _real_extract(self, url):
video_data = self._download_json(dve_api_url, media_id)
is_live = media_type == 'live'
if is_live:
title = self._live_title(self._call_api('event/', media_id)['title'])
title = self._call_api('event/', media_id)['title']
else:
title = video_data['name']

View File

@ -75,7 +75,7 @@ def _real_extract(self, url):
return {
'id': server_id,
'title': self._live_title(camera_name or server_id),
'title': camera_name or server_id,
'description': description,
'is_live': True,
'formats': formats,

View File

@ -112,7 +112,7 @@ def get_flashvar(x, *args, **kwargs):
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'upload_date': unified_strdate(_v('time_date')),
'uploader': _v('meta_organisation'),
'categories': categories,
@ -161,7 +161,7 @@ def _extract_video(self, url):
return {
'id': video_id,
'display_id': display_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'description': video_data.get('description'),
'thumbnail': video_data.get('image'),
'categories': categories,

View File

@ -116,7 +116,7 @@ def _parse_broadcast_item(self, item):
return {
'id': broadcast_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'thumbnails': thumbnails,
'timestamp': int_or_none(item.get('createdAt')),
'channel': channel.get('name'),

View File

@ -176,7 +176,7 @@ def _extract_stream_info(self, stream_info):
return {
'id': broadcast_id,
'formats': formats,
'title': self._live_title(stream_info['stream_title']) if is_live else stream_info['stream_title'],
'title': stream_info['stream_title'],
'thumbnail': stream_info.get('thumbnail_url'),
'is_live': is_live,
}
@ -344,7 +344,7 @@ def _real_extract(self, url):
is_live = video_data.get('isLive')
info.update({
'id': content_id,
'title': self._live_title(info['title']) if is_live else info['title'],
'title': info['title'],
'formats': self._extract_video_formats(video_data, content_id),
'is_live': is_live,
})

View File

@ -33,7 +33,7 @@ def _real_extract(self, url):
return {
'id': page_id,
'title': self._live_title(page_id) if self._IS_LIVE else page_id,
'title': page_id,
'uploader_id': hidden_inputs.get('userid'),
'duration': int_or_none(hidden_inputs.get('duration')),
'is_live': self._IS_LIVE,

View File

@ -49,7 +49,7 @@ def _real_extract(self, url):
self._sort_formats(formats)
return {
'id': video_id,
'title': self._live_title('Матч ТВ - Прямой эфир'),
'title': 'Матч ТВ - Прямой эфир',
'is_live': True,
'formats': formats,
}

View File

@ -33,7 +33,7 @@ def _real_extract(self, url):
display_id = 'live'
webpage = self._download_webpage(url, display_id)
title = self._live_title(self._og_search_title(webpage))
title = self._og_search_title(webpage)
data_js = self._search_regex(
r'(?s)\nplaylist:\s*(\[.*?}\]),',

View File

@ -305,7 +305,7 @@ def _real_extract(self, url):
self._sort_formats(formats)
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'description': live_source.get('description'),
'formats': formats,
'is_live': is_live,
@ -545,8 +545,6 @@ def _real_extract(self, url):
title = event_config['eventTitle']
is_live = {'live': True, 'replay': False}.get(event_config.get('eventStatus'))
if is_live:
title = self._live_title(title)
source_url = self._download_json(
f'https://api-leap.nbcsports.com/feeds/assets/{pid}?application=NBCOlympics&platform=desktop&format=nbc-player&env=staging',

View File

@ -245,8 +245,6 @@ def _real_extract(self, url):
live = playlist.get('config', {}).get('streamType') in ['httpVideoLive', 'httpAudioLive']
title = config['title']
if live:
title = self._live_title(title)
uploader = ppjson.get('config', {}).get('branding')
upload_date = ppjson.get('config', {}).get('publicationDate')
duration = int_or_none(config.get('duration'))

View File

@ -89,7 +89,7 @@ def _parse_video_config(self, video_config, display_id):
'ext': determine_ext(image_url, 'jpg'),
}]
info.update({
'title': self._live_title(title) if is_live else title,
'title': title,
'is_live': is_live,
'description': clean_html(item.get('description')),
'thumbnails': thumbnails,

View File

@ -467,7 +467,7 @@ def add_format_url(format_url):
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'description': metadata.get('info'),
'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
'upload_date': unified_strdate(metadata.get('gidsdatum')),
@ -561,7 +561,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'url': stream['url'],
'title': self._live_title(title),
'title': title,
'acodec': codec,
'ext': codec,
'is_live': True,

View File

@ -235,7 +235,7 @@ def _extract_desktop(self, url):
assert title
if provider == 'LIVE_TV_APP':
info['title'] = self._live_title(title)
info['title'] = title
quality = qualities(('4', '0', '1', '2', '3', '5'))

View File

@ -25,8 +25,8 @@ def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._live_title(self._html_search_regex(
r'<h1><strong>.*?</strong>(.*?)</h1>', webpage, 'title'))
title = self._html_search_regex(
r'<h1><strong>.*?</strong>(.*?)</h1>', webpage, 'title')
clip = self._search_regex(
r"clip:\s*\{\s*url:\s*'([^']+)'", webpage, 'clip')

View File

@ -77,7 +77,7 @@ def _real_extract(self, url):
return {
'id': channel_id,
'title': self._live_title(title.strip()),
'title': title.strip(),
'is_live': True,
'channel': channel_id,
'channel_id': metadata.get('id'),

View File

@ -167,8 +167,6 @@ def _real_extract(self, url):
title = item['title']
is_live = item['type'] == 'stream'
if is_live:
title = self._live_title(title)
description = self._og_search_description(webpage, default=None) or self._html_search_meta(
'description', webpage, 'description', default=None)
timestamp = None

View File

@ -29,7 +29,7 @@ def _real_extract(self, url):
webpage, 'broadcast')
broadcast = self._parse_json(jscode, radio_id)
title = self._live_title(broadcast['name'])
title = broadcast['name']
description = broadcast.get('description') or broadcast.get('shortDescription')
thumbnail = broadcast.get('picture4Url') or broadcast.get('picture4TransUrl') or broadcast.get('logo100x100')

View File

@ -318,8 +318,7 @@ def _real_extract(self, url):
info = {
'id': remove_start(media.get('id'), 'ContentItem-') or video_id,
'display_id': video_id,
'title': self._live_title(title) if relinker_info.get(
'is_live') else title,
'title': title,
'alt_title': strip_or_none(alt_title),
'description': media.get('description'),
'uploader': strip_or_none(media.get('channel')),

View File

@ -85,8 +85,6 @@ def _real_extract(self, url):
title = data['title']
is_live = data.get('isLive')
if is_live:
title = self._live_title(title)
height_re = r'-(\d+)p\.'
formats = []

View File

@ -160,7 +160,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'formats': formats,
'thumbnail': info.get('image'),
'subtitles': subtitles,
@ -230,7 +230,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'title': self._live_title(title),
'title': title,
'formats': self._extract_png_formats(vidplayer_id),
'is_live': True,
}

View File

@ -201,7 +201,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'description': description,
'thumbnail': thumbnail,
'view_count': view_count,

View File

@ -73,7 +73,7 @@ def _real_extract(self, url):
return {
'id': compat_str(room.get('live_id') or broadcaster_id),
'title': self._live_title(title),
'title': title,
'description': room.get('description'),
'timestamp': int_or_none(room.get('current_live_started_at')),
'uploader': uploader,

View File

@ -55,7 +55,7 @@ def _parse_video(self, video, video_id):
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'formats': formats,
'thumbnail': dict_get(video, ('video_still', 'video_still_medium', 'thumb')),
'description': video.get('short_desc') or None,

View File

@ -36,7 +36,7 @@ def _real_extract(self, url):
'id': video_id,
'url': stream_url,
'ext': 'mp4',
'title': self._live_title(title),
'title': title,
'description': description,
'is_live': True,
}

View File

@ -57,7 +57,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'title': self._live_title(video_id),
'title': video_id,
'description': self._og_search_description(webpage),
'is_live': True,
'formats': formats,

View File

@ -203,10 +203,6 @@ class SVTPlayIE(SVTPlayBaseIE):
'only_matching': True,
}]
def _adjust_title(self, info):
if info['is_live']:
info['title'] = self._live_title(info['title'])
def _extract_by_video_id(self, video_id, webpage=None):
data = self._download_json(
'https://api.svt.se/videoplayer-api/video/%s' % video_id,
@ -220,7 +216,6 @@ def _extract_by_video_id(self, video_id, webpage=None):
if not title:
title = video_id
info_dict['title'] = title
self._adjust_title(info_dict)
return info_dict
def _real_extract(self, url):
@ -251,7 +246,6 @@ def _real_extract(self, url):
'title': data['context']['dispatcher']['stores']['MetaStore']['title'],
'thumbnail': thumbnail,
})
self._adjust_title(info_dict)
return info_dict
svt_id = try_get(

View File

@ -69,7 +69,7 @@ def _real_extract(self, url):
return {
'id': article_id or display_id,
'display_id': display_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'description': description,
'formats': formats,
'is_live': is_live,

View File

@ -148,7 +148,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'title': self._live_title(title) if live else title,
'title': title,
'thumbnail': config.get('poster') or None,
'description': config.get('description') or None,
'timestamp': parse_iso8601(config.get('upload_date')),

View File

@ -62,7 +62,7 @@ def _real_extract(self, url):
raise ExtractorError('%s is offline' % username, expected=True)
program_info = live_info['programInfo']
program_id = program_info['id']
title = self._live_title(program_info['title'])
title = program_info['title']
formats = []
for stream_info in (program_info.get('streamInfo') or []):

View File

@ -62,7 +62,7 @@ def _real_extract(self, url):
return {
'id': content_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'location': location,

View File

@ -205,7 +205,7 @@ def _extract_cvp_info(self, data_src, video_id, path_data={}, ap_data={}, fatal=
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'formats': formats,
'subtitles': subtitles,
'thumbnails': thumbnails,

View File

@ -106,7 +106,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'url': video_url,
'title': self._live_title(title) if is_live else title,
'title': title,
'description': strip_or_none(asset.get('description')),
'thumbnails': thumbnails,
'timestamp': parse_iso8601(asset.get('live_broadcast_time') or asset.get('update_time')),
@ -271,7 +271,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'url': video_url,
'title': self._live_title(title) if is_live else title,
'title': title,
'description': strip_or_none(asset.get('description')),
'thumbnails': thumbnails,
'timestamp': parse_iso8601(asset.get('createTime')),

View File

@ -130,9 +130,6 @@ def _real_extract(self, url):
r'data-image=(["\'])(?P<url>(?:https?:)?//.+?)\1', webpage,
'thumbnail', default=None, group='url'))
if is_live:
title = self._live_title(title)
view_count = int_or_none(self._search_regex(
r'(?s)<div[^>]+\bclass=["\'].*?view-count[^>]+>.*?(\d+).*?</div>',
webpage, 'view count', default=None))

View File

@ -80,7 +80,7 @@ def _real_extract(self, url):
return {
'id': resource_id,
'display_id': display_id,
'title': self._live_title(title),
'title': title,
'formats': formats,
'is_live': True,
}

View File

@ -903,7 +903,7 @@ def _real_extract(self, url):
return {
'id': stream_id,
'display_id': channel_name,
'title': self._live_title(title),
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,

View File

@ -242,7 +242,7 @@ def _real_extract(self, url):
info.update({
'id': video_id,
'title': self._live_title(data['title']) if is_live else data['title'],
'title': data['title'],
'description': data['description'],
'thumbnail': data['images']['main'] + '?t[]=900x506q80',
'timestamp': data['published'],

View File

@ -224,7 +224,7 @@ def _parse_config(self, config, video_id):
return {
'id': str_or_none(video_data.get('id')) or video_id,
'title': self._live_title(video_title) if is_live else video_title,
'title': video_title,
'uploader': owner.get('name'),
'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
'uploader_url': video_uploader_url,

View File

@ -434,8 +434,6 @@ def _real_extract(self, url):
# 2 = live
# 3 = post live (finished live)
is_live = data.get('live') == 2
if is_live:
title = self._live_title(title)
timestamp = unified_timestamp(self._html_search_regex(
r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page,

View File

@ -210,7 +210,7 @@ def get_common_fields():
self._sort_formats(formats)
info = get_common_fields()
info.update({
'title': self._live_title(video['title']),
'title': video['title'],
'id': video_id,
'formats': formats,
'is_live': True,

View File

@ -44,11 +44,11 @@ def _real_extract(self, url):
info = self._download_json(
'http://vybory.mos.ru/json/voting_stations/%s/%s.json'
% (compat_str(station_id)[:3], station_id),
station_id, 'Downloading station JSON', fatal=False)
station_id, 'Downloading station JSON', fatal=False) or {}
return {
'id': station_id,
'title': self._live_title(info['name'] if info else station_id),
'title': info.get('name') or station_id,
'description': info.get('address'),
'is_live': True,
'formats': formats,

View File

@ -117,7 +117,7 @@ def _real_extract(self, url):
return {
'id': tracker_data.get('trackerClipId', video_id),
'title': self._live_title(title) if is_live else title,
'title': title,
'alt_title': tracker_data.get('trackerClipSubcategory'),
'formats': formats,
'subtitles': subtitles,

View File

@ -264,7 +264,7 @@ def _extract_yahoo_video(self, video_id, country):
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'title': title,
'formats': formats,
'thumbnails': thumbnails,
'description': clean_html(video.get('description')),

View File

@ -58,7 +58,7 @@ def _real_extract(self, url):
return {
'id': uploader,
'is_live': True,
'title': self._live_title(uploader),
'title': uploader,
'thumbnail': data.get('awsUrl'),
'tags': data.get('tags'),
'categories': data.get('tags'),

View File

@ -2810,7 +2810,7 @@ def feed_entry(name):
info = {
'id': video_id,
'title': self._live_title(video_title) if is_live else video_title,
'title': video_title,
'formats': formats,
'thumbnails': thumbnails,
# The best thumbnail that we are sure exists. Prevents unnecessary

View File

@ -187,7 +187,7 @@ def _extract_video(self, channel_name, video_id, record_id=None, is_live=False):
cid = self._extract_cid(video_id, channel_name)
info_dict = {
'id': channel_name,
'title': self._live_title(channel_name),
'title': channel_name,
'is_live': True,
}
else: