[extractor] Add convinience function _yes_playlist

This commit is contained in:
pukkandan 2022-01-23 23:24:24 +05:30
parent 1f13021eca
commit f40ee5e9a0
No known key found for this signature in database
GPG Key ID: 0F00D95A001F4698
12 changed files with 49 additions and 87 deletions

View File

@ -300,11 +300,10 @@ def _real_extract(self, url):
unescapeHTML(webpage_data).encode('utf-8').decode('unicode_escape'), show_id) unescapeHTML(webpage_data).encode('utf-8').decode('unicode_escape'), show_id)
video_data = video_data['route']['pageData']['_embedded'] video_data = video_data['route']['pageData']['_embedded']
if self.get_param('noplaylist') and 'highlightVideo' in video_data: highlight = try_get(video_data, lambda x: ['highlightVideo']['shareUrl'])
self.to_screen('Downloading just the highlight video because of --no-playlist') if not self._yes_playlist(show_id, bool(highlight), video_label='highlight video'):
return self.url_result(video_data['highlightVideo']['shareUrl'], ie=ABCIViewIE.ie_key()) return self.url_result(highlight, ie=ABCIViewIE.ie_key())
self.to_screen(f'Downloading playlist {show_id} - add --no-playlist to just download the highlight video')
series = video_data['selectedSeries'] series = video_data['selectedSeries']
return { return {
'_type': 'playlist', '_type': 'playlist',

View File

@ -3710,6 +3710,22 @@ def _configuration_arg(self, key, default=NO_DEFAULT, *, ie_key=None, casesense=
return [] if default is NO_DEFAULT else default return [] if default is NO_DEFAULT else default
return list(val) if casesense else [x.lower() for x in val] return list(val) if casesense else [x.lower() for x in val]
def _yes_playlist(self, playlist_id, video_id, smuggled_data=None, *, playlist_label='playlist', video_label='video'):
if not playlist_id or not video_id:
return not video_id
no_playlist = (smuggled_data or {}).get('force_noplaylist')
if no_playlist is not None:
return not no_playlist
video_id = '' if video_id is True else f' {video_id}'
playlist_id = '' if playlist_id is True else f' {playlist_id}'
if self.get_param('noplaylist'):
self.to_screen(f'Downloading just the {video_label}{video_id} because of --no-playlist')
return False
self.to_screen(f'Downloading {playlist_label}{playlist_id} - add --no-playlist to download just the {video_label}{video_id}')
return True
class SearchInfoExtractor(InfoExtractor): class SearchInfoExtractor(InfoExtractor):
""" """

View File

@ -207,12 +207,10 @@ def _real_extract(self, url):
video_id, playlist_id = self._match_valid_url(url).groups() video_id, playlist_id = self._match_valid_url(url).groups()
if playlist_id: if playlist_id:
if not self.get_param('noplaylist'): if self._yes_playlist(playlist_id, video_id):
self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % playlist_id)
return self.url_result( return self.url_result(
'http://www.dailymotion.com/playlist/' + playlist_id, 'http://www.dailymotion.com/playlist/' + playlist_id,
'DailymotionPlaylist', playlist_id) 'DailymotionPlaylist', playlist_id)
self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
password = self.get_param('videopassword') password = self.get_param('videopassword')
media = self._call_api( media = self._call_api(

View File

@ -157,11 +157,8 @@ def _check_clip(self, url, list_id):
query_dict = parse_qs(url) query_dict = parse_qs(url)
if 'clipid' in query_dict: if 'clipid' in query_dict:
clip_id = query_dict['clipid'][0] clip_id = query_dict['clipid'][0]
if self.get_param('noplaylist'): if not self._yes_playlist(list_id, clip_id):
self.to_screen('Downloading just video %s because of --no-playlist' % clip_id)
return self.url_result(DaumClipIE._URL_TEMPLATE % clip_id, 'DaumClip') return self.url_result(DaumClipIE._URL_TEMPLATE % clip_id, 'DaumClip')
else:
self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id)
class DaumPlaylistIE(DaumListIE): class DaumPlaylistIE(DaumListIE):

View File

@ -64,10 +64,7 @@ def _real_extract(self, url):
domain, media_type, media_id, playlist_id = self._match_valid_url(url).groups() domain, media_type, media_id, playlist_id = self._match_valid_url(url).groups()
if playlist_id: if playlist_id:
if self.get_param('noplaylist'): if self._yes_playlist(playlist_id, media_id):
self.to_screen('Downloading just video %s because of --no-playlist' % media_id)
else:
self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % playlist_id)
media_type, media_id = 'playlist', playlist_id media_type, media_id = 'playlist', playlist_id
if media_type == 'playlist': if media_type == 'playlist':

View File

@ -7,6 +7,7 @@
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
traverse_obj,
smuggle_url, smuggle_url,
unsmuggle_url, unsmuggle_url,
) )
@ -55,9 +56,6 @@ def _extract_playlist(self, season_list, video_id, program_info, prompt=True):
episode_title = program_info['title'] episode_title = program_info['title']
content_id = season_list['contentId'] content_id = season_list['contentId']
if prompt:
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (content_id, video_id))
all_episodes = [ all_episodes = [
self.url_result(smuggle_url( self.url_result(smuggle_url(
self._URL_TEMPLATE % (program_info['contentType'], episode['contentId']), self._URL_TEMPLATE % (program_info['contentType'], episode['contentId']),
@ -71,12 +69,6 @@ def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
noplaylist = self.get_param('noplaylist')
noplaylist_prompt = True
if 'force_noplaylist' in data:
noplaylist = data['force_noplaylist']
noplaylist_prompt = False
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
program_info = self._parse_json(self._search_regex( program_info = self._parse_json(self._search_regex(
@ -84,14 +76,9 @@ def _real_extract(self, url):
video_id) video_id)
season_list = list(program_info.get('seasonList', {}).values()) season_list = list(program_info.get('seasonList', {}).values())
if season_list: playlist_id = traverse_obj(season_list, 0, 'contentId')
if not noplaylist: if self._yes_playlist(playlist_id, video_id, smuggled_data):
return self._extract_playlist( return self._extract_playlist(season_list[0], video_id, program_info)
season_list[0], video_id, program_info,
prompt=noplaylist_prompt)
if noplaylist_prompt:
self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
# In browsers `getMainUrl` request is always issued. Usually this # In browsers `getMainUrl` request is always issued. Usually this
# endpoint gives the same result as the data embedded in the webpage. # endpoint gives the same result as the data embedded in the webpage.

View File

@ -165,14 +165,10 @@ class NBAWatchIE(NBAWatchBaseIE):
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
collection_id = parse_qs(url).get('collection', [None])[0] collection_id = parse_qs(url).get('collection', [None])[0]
if collection_id: if self._yes_playlist(collection_id, display_id):
if self.get_param('noplaylist'): return self.url_result(
self.to_screen('Downloading just video %s because of --no-playlist' % display_id) 'https://www.nba.com/watch/list/collection/' + collection_id,
else: NBAWatchCollectionIE.ie_key(), collection_id)
self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % collection_id)
return self.url_result(
'https://www.nba.com/watch/list/collection/' + collection_id,
NBAWatchCollectionIE.ie_key(), collection_id)
return self._extract_video('seoName', display_id) return self._extract_video('seoName', display_id)

View File

@ -405,17 +405,12 @@ def _real_extract(self, url):
name = info['name'] name = info['name']
description = info['description'] description = info['description']
if not info['songs'] or self.get_param('noplaylist'): if not self._yes_playlist(info['songs'] and program_id, info['mainSong']['id']):
if info['songs']:
self.to_screen(
'Downloading just the main audio %s because of --no-playlist'
% info['mainSong']['id'])
formats = self.extract_formats(info['mainSong']) formats = self.extract_formats(info['mainSong'])
self._sort_formats(formats) self._sort_formats(formats)
return { return {
'id': program_id, 'id': info['mainSong']['id'],
'title': name, 'title': name,
'description': description, 'description': description,
'creator': info['dj']['brand'], 'creator': info['dj']['brand'],
@ -425,10 +420,6 @@ def _real_extract(self, url):
'formats': formats, 'formats': formats,
} }
self.to_screen(
'Downloading playlist %s - add --no-playlist to just download the main audio %s'
% (program_id, info['mainSong']['id']))
song_ids = [info['mainSong']['id']] song_ids = [info['mainSong']['id']]
song_ids.extend([song['id'] for song in info['songs']]) song_ids.extend([song['id'] for song in info['songs']])
entries = [ entries = [

View File

@ -182,14 +182,9 @@ def _real_extract(self, url):
video_id = remove_start(current_clip_info['ckmId'], 'mvp:') video_id = remove_start(current_clip_info['ckmId'], 'mvp:')
video_name = url_basename(current_clip_info['url']) video_name = url_basename(current_clip_info['url'])
if self.get_param('noplaylist'): if not self._yes_playlist(channel_id, video_name, playlist_label='channel'):
self.to_screen(
'Downloading just video %s because of --no-playlist' % video_name)
return self._extract_from_id(video_id, webpage) return self._extract_from_id(video_id, webpage)
self.to_screen(
'Downloading channel %s - add --no-playlist to just download video %s' % (
channel_id, video_name))
matches = re.findall( matches = re.findall(
r'<a[^>]+href=[\'"](%s[a-z]+/[0-9a-z-]+/[0-9a-z]+)' % self._URL_BASE_RE, r'<a[^>]+href=[\'"](%s[a-z]+/[0-9a-z-]+/[0-9a-z]+)' % self._URL_BASE_RE,
webpage) webpage)

View File

@ -59,12 +59,8 @@ def _real_extract(self, url):
videos = asset.get('videos') or [] videos = asset.get('videos') or []
if len(videos) > 1: if len(videos) > 1:
playlist_id = parse_qs(url).get('playlistId', [None])[0] playlist_id = parse_qs(url).get('playlistId', [None])[0]
if playlist_id: if not self._yes_playlist(playlist_id, asset_id):
if self.get_param('noplaylist'): videos = [videos[int(playlist_id)]]
videos = [videos[int(playlist_id)]]
self.to_screen('Downloading just a single video because of --no-playlist')
else:
self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % asset_id)
def entries(): def entries():
for i, video in enumerate(videos, 1): for i, video in enumerate(videos, 1):

View File

@ -287,8 +287,7 @@ def _real_extract(self, url):
raise ExtractorError('This video is not available in your region.', expected=True) raise ExtractorError('This video is not available in your region.', expected=True)
series_id = video_data.get('series_id') series_id = video_data.get('series_id')
if not self.get_param('noplaylist') and not idata.get('force_noplaylist'): if self._yes_playlist(series_id, video_id, idata):
self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % series_id)
series = product_data.get('series', {}) series = product_data.get('series', {})
product = series.get('product') product = series.get('product')
if product: if product:
@ -308,9 +307,6 @@ def _real_extract(self, url):
return self.playlist_result(entries, series_id, series.get('name'), series.get('description')) return self.playlist_result(entries, series_id, series.get('name'), series.get('description'))
if self.get_param('noplaylist'):
self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
duration_limit = False duration_limit = False
query = { query = {
'ccs_product_id': video_data['ccs_product_id'], 'ccs_product_id': video_data['ccs_product_id'],

View File

@ -146,30 +146,24 @@ def _real_extract(self, url):
'post/v1.0/officialVideoPost-%s', video_id, 'post/v1.0/officialVideoPost-%s', video_id,
'author{nickname},channel{channelCode,channelName},officialVideo{commentCount,exposeStatus,likeCount,playCount,playTime,status,title,type,vodId},playlist{playlistSeq,totalCount,name}') 'author{nickname},channel{channelCode,channelName},officialVideo{commentCount,exposeStatus,likeCount,playCount,playTime,status,title,type,vodId},playlist{playlistSeq,totalCount,name}')
playlist = post.get('playlist') playlist_id = str_or_none(try_get(post, lambda x: x['playlist']['playlistSeq']))
if not playlist or self.get_param('noplaylist'): if not self._yes_playlist(playlist_id, video_id):
if playlist:
self.to_screen(
'Downloading just video %s because of --no-playlist'
% video_id)
video = post['officialVideo'] video = post['officialVideo']
return self._get_vlive_info(post, video, video_id) return self._get_vlive_info(post, video, video_id)
else:
playlist_name = playlist.get('name')
playlist_id = str_or_none(playlist.get('playlistSeq'))
playlist_count = str_or_none(playlist.get('totalCount'))
playlist = self._call_api( playlist_name = str_or_none(try_get(post, lambda x: x['playlist']['name']))
'playlist/v1.0/playlist-%s/posts', playlist_id, 'data', {'limit': playlist_count}) playlist_count = str_or_none(try_get(post, lambda x: x['playlist']['totalCount']))
entries = [] playlist = self._call_api(
for video_data in playlist['data']: 'playlist/v1.0/playlist-%s/posts', playlist_id, 'data', {'limit': playlist_count})
video = video_data.get('officialVideo')
video_id = str_or_none(video.get('videoSeq'))
entries.append(self._get_vlive_info(video_data, video, video_id))
return self.playlist_result(entries, playlist_id, playlist_name) entries = []
for video_data in playlist['data']:
video = video_data.get('officialVideo')
video_id = str_or_none(video.get('videoSeq'))
entries.append(self._get_vlive_info(video_data, video, video_id))
return self.playlist_result(entries, playlist_id, playlist_name)
def _get_vlive_info(self, post, video, video_id): def _get_vlive_info(self, post, video, video_id):
def get_common_fields(): def get_common_fields():