2016-10-02 13:39:18 +02:00
# coding: utf-8
2014-01-28 00:56:09 +01:00
from __future__ import unicode_literals
2013-10-16 16:57:40 +02:00
import re
2014-01-28 00:56:09 +01:00
import itertools
2013-10-16 16:57:40 +02:00
from . common import InfoExtractor
2014-12-13 12:24:42 +01:00
from . . compat import (
2013-10-16 16:57:40 +02:00
compat_str ,
2014-12-13 12:24:42 +01:00
)
from . . utils import (
2015-11-21 13:02:52 +01:00
determine_ext ,
2017-09-10 14:09:27 +02:00
bool_or_none ,
2017-07-04 11:26:02 +02:00
int_or_none ,
2021-08-22 21:02:00 +02:00
parse_qs ,
2017-09-10 14:09:27 +02:00
try_get ,
unified_timestamp ,
2018-07-21 14:08:28 +02:00
url_or_none ,
2013-10-16 16:57:40 +02:00
)
2017-09-10 13:39:13 +02:00
class RutubeBaseIE ( InfoExtractor ) :
2019-02-10 18:49:51 +01:00
def _download_api_info ( self , video_id , query = None ) :
if not query :
query = { }
query [ ' format ' ] = ' json '
return self . _download_json (
' http://rutube.ru/api/video/ %s / ' % video_id ,
video_id , ' Downloading video JSON ' ,
' Unable to download video JSON ' , query = query )
@staticmethod
def _extract_info ( video , video_id = None , require_title = True ) :
2017-09-10 13:39:13 +02:00
title = video [ ' title ' ] if require_title else video . get ( ' title ' )
age_limit = video . get ( ' is_adult ' )
if age_limit is not None :
age_limit = 18 if age_limit is True else 0
uploader_id = try_get ( video , lambda x : x [ ' author ' ] [ ' id ' ] )
category = try_get ( video , lambda x : x [ ' category ' ] [ ' name ' ] )
return {
2019-02-10 18:49:51 +01:00
' id ' : video . get ( ' id ' ) or video_id if video_id else video [ ' id ' ] ,
2017-09-10 13:39:13 +02:00
' title ' : title ,
' description ' : video . get ( ' description ' ) ,
' thumbnail ' : video . get ( ' thumbnail_url ' ) ,
' duration ' : int_or_none ( video . get ( ' duration ' ) ) ,
' uploader ' : try_get ( video , lambda x : x [ ' author ' ] [ ' name ' ] ) ,
' uploader_id ' : compat_str ( uploader_id ) if uploader_id else None ,
' timestamp ' : unified_timestamp ( video . get ( ' created_ts ' ) ) ,
' category ' : [ category ] if category else None ,
' age_limit ' : age_limit ,
' view_count ' : int_or_none ( video . get ( ' hits ' ) ) ,
' comment_count ' : int_or_none ( video . get ( ' comments_count ' ) ) ,
2017-09-10 14:09:27 +02:00
' is_live ' : bool_or_none ( video . get ( ' is_livestream ' ) ) ,
2017-09-10 13:39:13 +02:00
}
2019-02-10 18:49:51 +01:00
def _download_and_extract_info ( self , video_id , query = None ) :
return self . _extract_info (
self . _download_api_info ( video_id , query = query ) , video_id )
def _download_api_options ( self , video_id , query = None ) :
if not query :
query = { }
query [ ' format ' ] = ' json '
return self . _download_json (
' http://rutube.ru/api/play/options/ %s / ' % video_id ,
video_id , ' Downloading options JSON ' ,
' Unable to download options JSON ' ,
headers = self . geo_verification_headers ( ) , query = query )
def _extract_formats ( self , options , video_id ) :
formats = [ ]
for format_id , format_url in options [ ' video_balancer ' ] . items ( ) :
ext = determine_ext ( format_url )
if ext == ' m3u8 ' :
formats . extend ( self . _extract_m3u8_formats (
format_url , video_id , ' mp4 ' , m3u8_id = format_id , fatal = False ) )
elif ext == ' f4m ' :
formats . extend ( self . _extract_f4m_formats (
format_url , video_id , f4m_id = format_id , fatal = False ) )
else :
formats . append ( {
' url ' : format_url ,
' format_id ' : format_id ,
} )
self . _sort_formats ( formats )
return formats
def _download_and_extract_formats ( self , video_id , query = None ) :
return self . _extract_formats (
self . _download_api_options ( video_id , query = query ) , video_id )
2017-09-10 13:39:13 +02:00
class RutubeIE ( RutubeBaseIE ) :
2014-01-28 00:56:09 +01:00
IE_NAME = ' rutube '
2014-01-28 03:32:07 +01:00
IE_DESC = ' Rutube videos '
2017-03-03 18:42:51 +01:00
_VALID_URL = r ' https?://rutube \ .ru/(?:video|(?:play/)?embed)/(?P<id>[ \ da-z] {32} ) '
2013-10-16 16:57:40 +02:00
2015-12-15 23:44:17 +01:00
_TESTS = [ {
2014-01-28 00:56:09 +01:00
' url ' : ' http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/ ' ,
2019-02-10 18:49:51 +01:00
' md5 ' : ' 1d24f180fac7a02f3900712e5a5764d6 ' ,
2014-01-28 00:56:09 +01:00
' info_dict ' : {
2014-03-30 10:35:07 +02:00
' id ' : ' 3eac3b4561676c17df9132a9a1e62e3e ' ,
2019-02-10 18:49:51 +01:00
' ext ' : ' mp4 ' ,
2014-01-28 00:56:09 +01:00
' title ' : ' Раненный кенгуру забежал в аптеку ' ,
2014-01-28 03:31:14 +01:00
' description ' : ' http://www.ntdtv.ru ' ,
2019-02-10 18:49:51 +01:00
' duration ' : 81 ,
2014-01-28 00:56:09 +01:00
' uploader ' : ' NTDRussian ' ,
' uploader_id ' : ' 29790 ' ,
2017-09-10 13:39:13 +02:00
' timestamp ' : 1381943602 ,
2014-01-28 03:31:14 +01:00
' upload_date ' : ' 20131016 ' ,
2015-08-08 18:11:06 +02:00
' age_limit ' : 0 ,
2013-10-16 16:57:40 +02:00
} ,
2015-12-15 23:44:17 +01:00
} , {
' url ' : ' http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661 ' ,
' only_matching ' : True ,
2017-03-03 18:42:51 +01:00
} , {
' url ' : ' http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661 ' ,
' only_matching ' : True ,
2017-07-04 11:26:02 +02:00
} , {
' url ' : ' http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252 ' ,
' only_matching ' : True ,
2017-09-10 13:39:13 +02:00
} , {
' url ' : ' https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source ' ,
' only_matching ' : True ,
2015-12-15 23:44:17 +01:00
} ]
2013-10-16 16:57:40 +02:00
2017-07-04 11:26:02 +02:00
@classmethod
def suitable ( cls , url ) :
2017-09-10 13:39:13 +02:00
return False if RutubePlaylistIE . suitable ( url ) else super ( RutubeIE , cls ) . suitable ( url )
2017-07-04 11:26:02 +02:00
2017-03-03 18:46:33 +01:00
@staticmethod
def _extract_urls ( webpage ) :
return [ mobj . group ( ' url ' ) for mobj in re . finditer (
r ' <iframe[^>]+?src=([ " \' ])(?P<url>(?:https?:)?//rutube \ .ru/embed/[ \ da-z] {32} .*?) \ 1 ' ,
webpage ) ]
2013-10-16 16:57:40 +02:00
def _real_extract ( self , url ) :
2014-12-13 12:24:42 +01:00
video_id = self . _match_id ( url )
2019-02-10 18:49:51 +01:00
info = self . _download_and_extract_info ( video_id )
info [ ' formats ' ] = self . _download_and_extract_formats ( video_id )
2017-09-10 13:39:13 +02:00
return info
2014-01-28 00:56:09 +01:00
2019-02-10 18:49:51 +01:00
class RutubeEmbedIE ( RutubeBaseIE ) :
2015-01-04 03:15:27 +01:00
IE_NAME = ' rutube:embed '
IE_DESC = ' Rutube embedded videos '
2016-09-08 12:04:57 +02:00
_VALID_URL = r ' https?://rutube \ .ru/(?:video|play)/embed/(?P<id>[0-9]+) '
2015-01-04 03:15:27 +01:00
2015-11-21 12:39:24 +01:00
_TESTS = [ {
2015-01-04 03:15:27 +01:00
' url ' : ' http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38= ' ,
' info_dict ' : {
' id ' : ' a10e53b86e8f349080f718582ce4c661 ' ,
2019-02-10 18:49:51 +01:00
' ext ' : ' mp4 ' ,
2017-09-10 13:39:13 +02:00
' timestamp ' : 1387830582 ,
2015-01-04 03:15:27 +01:00
' upload_date ' : ' 20131223 ' ,
' uploader_id ' : ' 297833 ' ,
' description ' : ' Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89 ' ,
' uploader ' : ' subziro89 ILya ' ,
' title ' : ' Мистический городок Эйри в Индиан 5 серия озвучка subziro89 ' ,
} ,
' params ' : {
2017-09-10 13:39:13 +02:00
' skip_download ' : True ,
2015-01-04 03:15:27 +01:00
} ,
2015-11-21 12:39:24 +01:00
} , {
' url ' : ' http://rutube.ru/play/embed/8083783 ' ,
' only_matching ' : True ,
2019-02-10 18:49:51 +01:00
} , {
# private video
' url ' : ' https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ ' ,
' only_matching ' : True ,
2015-11-21 12:39:24 +01:00
} ]
2015-01-04 03:15:27 +01:00
def _real_extract ( self , url ) :
embed_id = self . _match_id ( url )
2019-02-10 18:49:51 +01:00
# Query may contain private videos token and should be passed to API
# requests (see #19163)
2021-08-22 21:02:00 +02:00
query = parse_qs ( url )
2019-02-10 18:49:51 +01:00
options = self . _download_api_options ( embed_id , query )
video_id = options [ ' effective_video ' ]
formats = self . _extract_formats ( options , video_id )
info = self . _download_and_extract_info ( video_id , query )
info . update ( {
' extractor_key ' : ' Rutube ' ,
' formats ' : formats ,
} )
return info
2015-01-04 03:15:27 +01:00
2017-09-10 13:39:13 +02:00
class RutubePlaylistBaseIE ( RutubeBaseIE ) :
def _next_page_url ( self , page_num , playlist_id , * args , * * kwargs ) :
return self . _PAGE_TEMPLATE % ( playlist_id , page_num )
def _entries ( self , playlist_id , * args , * * kwargs ) :
next_page_url = None
for pagenum in itertools . count ( 1 ) :
page = self . _download_json (
next_page_url or self . _next_page_url (
pagenum , playlist_id , * args , * * kwargs ) ,
playlist_id , ' Downloading page %s ' % pagenum )
results = page . get ( ' results ' )
if not results or not isinstance ( results , list ) :
break
for result in results :
2018-07-21 14:08:28 +02:00
video_url = url_or_none ( result . get ( ' video_url ' ) )
if not video_url :
2017-09-10 13:39:13 +02:00
continue
2019-02-10 18:49:51 +01:00
entry = self . _extract_info ( result , require_title = False )
2017-09-10 13:39:13 +02:00
entry . update ( {
' _type ' : ' url ' ,
' url ' : video_url ,
' ie_key ' : RutubeIE . ie_key ( ) ,
} )
yield entry
next_page_url = page . get ( ' next ' )
if not next_page_url or not page . get ( ' has_next ' ) :
break
def _extract_playlist ( self , playlist_id , * args , * * kwargs ) :
return self . playlist_result (
self . _entries ( playlist_id , * args , * * kwargs ) ,
playlist_id , kwargs . get ( ' playlist_name ' ) )
def _real_extract ( self , url ) :
return self . _extract_playlist ( self . _match_id ( url ) )
2021-12-12 16:56:36 +01:00
class RutubeTagsIE ( RutubePlaylistBaseIE ) :
IE_NAME = ' rutube:tags '
IE_DESC = ' Rutube tags '
2016-03-21 16:36:32 +01:00
_VALID_URL = r ' https?://rutube \ .ru/tags/video/(?P<id> \ d+) '
2014-08-28 00:58:24 +02:00
_TESTS = [ {
' url ' : ' http://rutube.ru/tags/video/1800/ ' ,
' info_dict ' : {
' id ' : ' 1800 ' ,
} ,
' playlist_mincount ' : 68 ,
} ]
2014-01-28 00:56:09 +01:00
_PAGE_TEMPLATE = ' http://rutube.ru/api/tags/video/ %s /?page= %s &format=json '
2017-09-10 13:39:13 +02:00
class RutubeMovieIE ( RutubePlaylistBaseIE ) :
2014-01-28 00:56:09 +01:00
IE_NAME = ' rutube:movie '
2014-01-28 03:32:07 +01:00
IE_DESC = ' Rutube movies '
2016-03-21 16:36:32 +01:00
_VALID_URL = r ' https?://rutube \ .ru/metainfo/tv/(?P<id> \ d+) '
2014-08-28 00:58:24 +02:00
_TESTS = [ ]
2014-01-28 00:56:09 +01:00
_MOVIE_TEMPLATE = ' http://rutube.ru/api/metainfo/tv/ %s /?format=json '
_PAGE_TEMPLATE = ' http://rutube.ru/api/metainfo/tv/ %s /video?page= %s &format=json '
def _real_extract ( self , url ) :
2014-12-13 12:24:42 +01:00
movie_id = self . _match_id ( url )
2014-03-30 11:26:35 +02:00
movie = self . _download_json (
2014-01-28 03:32:07 +01:00
self . _MOVIE_TEMPLATE % movie_id , movie_id ,
' Downloading movie JSON ' )
2017-09-10 13:39:13 +02:00
return self . _extract_playlist (
movie_id , playlist_name = movie . get ( ' name ' ) )
2014-01-28 02:47:17 +01:00
2017-09-10 13:39:13 +02:00
class RutubePersonIE ( RutubePlaylistBaseIE ) :
2014-01-28 02:47:17 +01:00
IE_NAME = ' rutube:person '
IE_DESC = ' Rutube person videos '
2016-03-21 16:36:32 +01:00
_VALID_URL = r ' https?://rutube \ .ru/video/person/(?P<id> \ d+) '
2014-08-28 00:58:24 +02:00
_TESTS = [ {
' url ' : ' http://rutube.ru/video/person/313878/ ' ,
' info_dict ' : {
' id ' : ' 313878 ' ,
} ,
' playlist_mincount ' : 37 ,
} ]
2014-01-28 02:47:17 +01:00
2014-01-28 03:32:07 +01:00
_PAGE_TEMPLATE = ' http://rutube.ru/api/video/person/ %s /?page= %s &format=json '
2017-07-04 11:26:02 +02:00
2017-09-10 13:39:13 +02:00
class R utubePlaylistIE ( RutubePlaylistBaseIE ) :
2017-07-04 11:26:02 +02:00
IE_NAME = ' rutube:playlist '
IE_DESC = ' Rutube playlists '
2017-09-10 13:39:13 +02:00
_VALID_URL = r ' https?://rutube \ .ru/(?:video|(?:play/)?embed)/[ \ da-z] {32} / \ ?.*? \ bpl_id=(?P<id> \ d+) '
2017-07-04 11:26:02 +02:00
_TESTS = [ {
2017-09-10 13:39:13 +02:00
' url ' : ' https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag ' ,
2017-07-04 11:26:02 +02:00
' info_dict ' : {
2017-09-10 13:39:13 +02:00
' id ' : ' 3097 ' ,
2017-07-04 11:26:02 +02:00
} ,
2017-09-10 13:39:13 +02:00
' playlist_count ' : 27 ,
} , {
' url ' : ' https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source ' ,
' only_matching ' : True ,
2017-07-04 11:26:02 +02:00
} ]
2017-09-10 13:39:13 +02:00
_PAGE_TEMPLATE = ' http://rutube.ru/api/playlist/ %s / %s /?page= %s &format=json '
2017-07-04 11:26:02 +02:00
2017-09-10 22:22:27 +02:00
@classmethod
def suitable ( cls , url ) :
2021-08-22 21:19:23 +02:00
from . . utils import int_or_none , parse_qs
2017-09-10 22:22:27 +02:00
if not super ( RutubePlaylistIE , cls ) . suitable ( url ) :
return False
2021-08-22 21:02:00 +02:00
params = parse_qs ( url )
2017-09-10 13:39:13 +02:00
return params . get ( ' pl_type ' , [ None ] ) [ 0 ] and int_or_none ( params . get ( ' pl_id ' , [ None ] ) [ 0 ] )
2017-07-04 11:26:02 +02:00
2017-09-10 13:39:13 +02:00
def _next_page_url ( self , page_num , playlist_id , item_kind ) :
return self . _PAGE_TEMPLATE % ( item_kind , playlist_id , page_num )
2017-07-04 11:26:02 +02:00
2017-09-10 13:39:13 +02:00
def _real_extract ( self , url ) :
2021-08-22 21:02:00 +02:00
qs = parse_qs ( url )
2017-09-10 13:39:13 +02:00
playlist_kind = qs [ ' pl_type ' ] [ 0 ]
playlist_id = qs [ ' pl_id ' ] [ 0 ]
return self . _extract_playlist ( playlist_id , item_kind = playlist_kind )
2021-12-12 16:56:36 +01:00
class RutubeChannelIE ( RutubePlaylistBaseIE ) :
IE_NAME = ' rutube:channel '
IE_DESC = ' Rutube channel '
_VALID_URL = r ' https?://rutube \ .ru/channel/(?P<id> \ d+)/videos '
_TESTS = [ {
' url ' : ' https://rutube.ru/channel/639184/videos/ ' ,
' info_dict ' : {
' id ' : ' 639184 ' ,
} ,
' playlist_mincount ' : 133 ,
} ]
_PAGE_TEMPLATE = ' http://rutube.ru/api/video/person/ %s /?page= %s &format=json '