2015-02-20 13:13:41 +01:00
# coding: utf-8
from __future__ import unicode_literals
2018-06-06 01:41:08 +02:00
import re
2015-02-20 13:13:41 +01:00
from . common import InfoExtractor
from . . utils import (
2016-09-15 19:54:34 +02:00
int_or_none ,
2015-02-20 13:13:41 +01:00
parse_iso8601 ,
)
class TV4IE ( InfoExtractor ) :
IE_DESC = ' tv4.se and tv4play.se '
_VALID_URL = r ''' (?x)https?://(?:www \ .)?
( ? :
tv4 \. se / ( ? : [ ^ / ] + ) / klipp / ( ? : . * ) - |
tv4play \. se /
( ? :
2017-09-14 18:50:19 +02:00
( ? : program | barn ) / ( ? : [ ^ / ] + / | ( ? : [ ^ \? ] + ) \? video_id = ) |
2015-02-20 13:13:41 +01:00
iframe / video / |
film / |
sport / |
)
) ( ? P < id > [ 0 - 9 ] + ) '''
2017-02-19 00:24:38 +01:00
_GEO_COUNTRIES = [ ' SE ' ]
2015-02-20 13:13:41 +01:00
_TESTS = [
{
' url ' : ' http://www.tv4.se/kalla-fakta/klipp/kalla-fakta-5-english-subtitles-2491650 ' ,
2017-01-13 10:19:53 +01:00
' md5 ' : ' cb837212f342d77cec06e6dad190e96d ' ,
2015-02-20 13:13:41 +01:00
' info_dict ' : {
' id ' : ' 2491650 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Kalla Fakta 5 (english subtitles) ' ,
2017-01-02 13:08:07 +01:00
' thumbnail ' : r ' re:^https?://.* \ .jpg$ ' ,
2015-02-20 13:13:41 +01:00
' timestamp ' : int ,
' upload_date ' : ' 20131125 ' ,
} ,
} ,
{
' url ' : ' http://www.tv4play.se/iframe/video/3054113 ' ,
2017-01-13 10:19:53 +01:00
' md5 ' : ' cb837212f342d77cec06e6dad190e96d ' ,
2015-02-20 13:13:41 +01:00
' info_dict ' : {
' id ' : ' 3054113 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Så här jobbar ficktjuvarna - se avslöjande bilder ' ,
2017-01-02 13:08:07 +01:00
' thumbnail ' : r ' re:^https?://.* \ .jpg$ ' ,
2015-02-20 13:13:41 +01:00
' description ' : ' Unika bilder avslöjar hur turisternas fickor vittjas mitt på Stockholms central. Två experter på ficktjuvarna avslöjar knepen du ska se upp för. ' ,
' timestamp ' : int ,
' upload_date ' : ' 20150130 ' ,
} ,
} ,
{
' url ' : ' http://www.tv4play.se/sport/3060959 ' ,
' only_matching ' : True ,
} ,
{
' url ' : ' http://www.tv4play.se/film/2378136 ' ,
' only_matching ' : True ,
} ,
{
' url ' : ' http://www.tv4play.se/barn/looney-tunes?video_id=3062412 ' ,
' only_matching ' : True ,
} ,
2017-09-14 18:50:19 +02:00
{
2017-09-14 20:47:23 +02:00
' url ' : ' http://www.tv4play.se/program/farang/3922081 ' ,
2017-09-14 18:50:19 +02:00
' only_matching ' : True ,
}
2015-02-20 13:13:41 +01:00
]
def _real_extract ( self , url ) :
video_id = self . _match_id ( url )
info = self . _download_json (
2019-09-18 18:45:26 +02:00
' https://playback-api.b17g.net/asset/ %s ' % video_id ,
video_id , ' Downloading video info JSON ' , query = {
' service ' : ' tv4 ' ,
' device ' : ' browser ' ,
' protocol ' : ' hls,dash ' ,
' drm ' : ' widevine ' ,
} ) [ ' metadata ' ]
2015-02-20 13:13:41 +01:00
2016-09-15 19:54:34 +02:00
title = info [ ' title ' ]
2015-02-20 13:13:41 +01:00
2018-06-06 01:41:08 +02:00
manifest_url = self . _download_json (
' https://playback-api.b17g.net/media/ ' + video_id ,
video_id , query = {
' service ' : ' tv4 ' ,
' device ' : ' browser ' ,
' protocol ' : ' hls ' ,
} ) [ ' playbackItem ' ] [ ' manifestUrl ' ]
formats = self . _extract_m3u8_formats (
manifest_url , video_id , ' mp4 ' ,
' m3u8_native ' , m3u8_id = ' hls ' , fatal = False )
formats . extend ( self . _extract_mpd_formats (
manifest_url . replace ( ' .m3u8 ' , ' .mpd ' ) ,
video_id , mpd_id = ' dash ' , fatal = False ) )
formats . extend ( self . _extract_f4m_formats (
manifest_url . replace ( ' .m3u8 ' , ' .f4m ' ) ,
video_id , f4m_id = ' hds ' , fatal = False ) )
formats . extend ( self . _extract_ism_formats (
2020-04-07 17:55:36 +02:00
re . sub ( r ' \ .ism/.*? \ .m3u8 ' , r ' .ism/Manifest ' , manifest_url ) ,
2018-06-06 01:41:08 +02:00
video_id , ism_id = ' mss ' , fatal = False ) )
2017-02-19 00:24:38 +01:00
if not formats and info . get ( ' is_geo_restricted ' ) :
self . raise_geo_restricted ( countries = self . _GEO_COUNTRIES )
2015-02-20 13:13:41 +01:00
self . _sort_formats ( formats )
2020-04-19 23:49:40 +02:00
# The subtitles are defined in the manifest_url like this:
# # SUBTITLES groups
# #EXT-X-MEDIA:TYPE=SUBTITLES,GROUP-ID="textstream",NAME="Swedish",LANGUAGE="sv",AUTOSELECT=YES,DEFAULT=YES,URI="bmetgl4z0mr(12579349_ISMUSP)-textstream_swe=3000.m3u8"
# but I don't know yet how to extract it dynamically from there so they are hardcoded as a start.
hardcoded_swedish_subs_url = manifest_url [ : - 5 ] + " -textstream_swe=3000.webvtt "
subtitles = { }
subtitles . setdefault ( ' sv ' , [ ] ) . append ( {
' url ' : hardcoded_swedish_subs_url ,
' ext ' : ' vtt ' } )
2015-02-20 13:13:41 +01:00
return {
' id ' : video_id ,
2016-09-15 19:54:34 +02:00
' title ' : title ,
2015-02-20 13:13:41 +01:00
' formats ' : formats ,
2020-04-19 23:49:40 +02:00
' subtitles ' : subtitles ,
2015-02-20 13:13:41 +01:00
' description ' : info . get ( ' description ' ) ,
' timestamp ' : parse_iso8601 ( info . get ( ' broadcast_date_time ' ) ) ,
2016-09-15 19:54:34 +02:00
' duration ' : int_or_none ( info . get ( ' duration ' ) ) ,
2015-02-20 13:13:41 +01:00
' thumbnail ' : info . get ( ' image ' ) ,
2019-09-18 18:45:26 +02:00
' is_live ' : info . get ( ' isLive ' ) is True ,
' series ' : info . get ( ' seriesTitle ' ) ,
' season_number ' : int_or_none ( info . get ( ' seasonNumber ' ) ) ,
' episode ' : info . get ( ' episodeTitle ' ) ,
' episode_number ' : int_or_none ( info . get ( ' episodeNumber ' ) ) ,
2015-02-20 13:13:41 +01:00
}