yt-dlp/yt_dlp/extractor/tvplay.py

506 lines
18 KiB
Python
Raw Normal View History

2014-07-25 10:33:29 -04:00
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_urlparse,
)
2014-07-25 10:33:29 -04:00
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
2021-01-01 07:26:37 -05:00
parse_duration,
2014-07-25 10:33:29 -04:00
parse_iso8601,
qualities,
2016-08-16 13:32:28 -04:00
try_get,
2016-07-11 09:51:44 -04:00
update_url_query,
2018-07-21 08:08:28 -04:00
url_or_none,
2021-01-01 07:26:37 -05:00
urljoin,
2014-07-25 10:33:29 -04:00
)
class TVPlayIE(InfoExtractor):
IE_NAME = 'mtg'
IE_DESC = 'MTG services'
_VALID_URL = r'''(?x)
(?:
mtg:|
https?://
(?:www\.)?
(?:
tvplay(?:\.skaties)?\.lv(?:/parraides)?|
(?:tv3play|play\.tv3)\.lt(?:/programos)?|
tv3play(?:\.tv3)?\.ee/sisu|
(?:tv(?:3|6|8|10)play)\.se/program|
(?:(?:tv3play|viasat4play|tv6play)\.no|(?:tv3play)\.dk)/programmer|
play\.nova(?:tv)?\.bg/programi
)
/(?:[^/]+/)+
)
(?P<id>\d+)
'''
2014-07-25 10:33:29 -04:00
_TESTS = [
{
'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true',
2016-07-11 09:51:44 -04:00
'md5': 'a1612fe0849455423ad8718fe049be21',
2014-07-25 10:33:29 -04:00
'info_dict': {
'id': '418113',
2016-07-11 09:51:44 -04:00
'ext': 'mp4',
2014-07-25 10:33:29 -04:00
'title': 'Kādi ir īri? - Viņas melo labāk',
'description': 'Baiba apsmej īrus, kādi tie ir un ko viņi dara.',
2016-08-05 11:37:38 -04:00
'series': 'Viņas melo labāk',
'season': '2.sezona',
'season_number': 2,
2014-07-25 10:33:29 -04:00
'duration': 25,
'timestamp': 1406097056,
'upload_date': '20140723',
},
},
{
'url': 'http://play.tv3.lt/programos/moterys-meluoja-geriau/409229?autostart=true',
'info_dict': {
'id': '409229',
'ext': 'flv',
'title': 'Moterys meluoja geriau',
'description': 'md5:9aec0fc68e2cbc992d2a140bd41fa89e',
2016-08-05 11:37:38 -04:00
'series': 'Moterys meluoja geriau',
'episode_number': 47,
'season': '1 sezonas',
'season_number': 1,
'duration': 1330,
'timestamp': 1403769181,
'upload_date': '20140626',
},
'params': {
# rtmp download
'skip_download': True,
},
},
{
'url': 'http://www.tv3play.ee/sisu/kodu-keset-linna/238551?autostart=true',
'info_dict': {
'id': '238551',
'ext': 'flv',
'title': 'Kodu keset linna 398537',
'description': 'md5:7df175e3c94db9e47c0d81ffa5d68701',
'duration': 1257,
'timestamp': 1292449761,
'upload_date': '20101215',
},
'params': {
# rtmp download
'skip_download': True,
},
},
{
'url': 'http://www.tv3play.se/program/husraddarna/395385?autostart=true',
'info_dict': {
'id': '395385',
2016-07-11 09:51:44 -04:00
'ext': 'mp4',
'title': 'Husräddarna S02E07',
'description': 'md5:f210c6c89f42d4fc39faa551be813777',
'duration': 2574,
'timestamp': 1400596321,
'upload_date': '20140520',
},
'params': {
'skip_download': True,
},
},
{
'url': 'http://www.tv6play.se/program/den-sista-dokusapan/266636?autostart=true',
'info_dict': {
'id': '266636',
2016-07-11 09:51:44 -04:00
'ext': 'mp4',
'title': 'Den sista dokusåpan S01E08',
'description': 'md5:295be39c872520221b933830f660b110',
'duration': 1492,
'timestamp': 1330522854,
'upload_date': '20120229',
2015-08-10 15:49:23 -04:00
'age_limit': 18,
},
'params': {
'skip_download': True,
},
},
{
'url': 'http://www.tv8play.se/program/antikjakten/282756?autostart=true',
'info_dict': {
'id': '282756',
2016-07-11 09:51:44 -04:00
'ext': 'mp4',
'title': 'Antikjakten S01E10',
'description': 'md5:1b201169beabd97e20c5ad0ad67b13b8',
'duration': 2646,
'timestamp': 1348575868,
'upload_date': '20120925',
},
'params': {
'skip_download': True,
},
},
{
'url': 'http://www.tv3play.no/programmer/anna-anka-soker-assistent/230898?autostart=true',
'info_dict': {
'id': '230898',
2016-07-11 09:51:44 -04:00
'ext': 'mp4',
'title': 'Anna Anka søker assistent - Ep. 8',
'description': 'md5:f80916bf5bbe1c5f760d127f8dd71474',
'duration': 2656,
'timestamp': 1277720005,
'upload_date': '20100628',
},
'params': {
'skip_download': True,
},
},
{
'url': 'http://www.viasat4play.no/programmer/budbringerne/21873?autostart=true',
'info_dict': {
'id': '21873',
2016-07-11 09:51:44 -04:00
'ext': 'mp4',
'title': 'Budbringerne program 10',
'description': 'md5:4db78dc4ec8a85bb04fd322a3ee5092d',
'duration': 1297,
'timestamp': 1254205102,
'upload_date': '20090929',
},
'params': {
'skip_download': True,
},
},
{
'url': 'http://www.tv6play.no/programmer/hotelinspektor-alex-polizzi/361883?autostart=true',
'info_dict': {
'id': '361883',
2016-07-11 09:51:44 -04:00
'ext': 'mp4',
'title': 'Hotelinspektør Alex Polizzi - Ep. 10',
'description': 'md5:3ecf808db9ec96c862c8ecb3a7fdaf81',
'duration': 2594,
'timestamp': 1393236292,
'upload_date': '20140224',
},
'params': {
'skip_download': True,
},
},
2015-06-14 13:58:15 -04:00
{
'url': 'http://play.novatv.bg/programi/zdravei-bulgariya/624952?autostart=true',
'info_dict': {
'id': '624952',
'ext': 'flv',
'title': 'Здравей, България (12.06.2015 г.) ',
'description': 'md5:99f3700451ac5bb71a260268b8daefd7',
'duration': 8838,
'timestamp': 1434100372,
'upload_date': '20150612',
},
'params': {
# rtmp download
'skip_download': True,
},
},
{
'url': 'https://play.nova.bg/programi/zdravei-bulgariya/764300?autostart=true',
'only_matching': True,
},
2016-07-11 09:51:44 -04:00
{
'url': 'http://tvplay.skaties.lv/parraides/vinas-melo-labak/418113?autostart=true',
'only_matching': True,
},
{
'url': 'https://tvplay.skaties.lv/vinas-melo-labak/418113/?autostart=true',
'only_matching': True,
},
2016-08-16 13:32:28 -04:00
{
# views is null
'url': 'http://tvplay.skaties.lv/parraides/tv3-zinas/760183',
'only_matching': True,
},
2016-07-11 09:51:44 -04:00
{
'url': 'http://tv3play.tv3.ee/sisu/kodu-keset-linna/238551?autostart=true',
'only_matching': True,
},
{
'url': 'mtg:418113',
'only_matching': True,
2016-07-11 09:51:44 -04:00
}
2014-07-25 10:33:29 -04:00
]
def _real_extract(self, url):
video_id = self._match_id(url)
2017-04-01 02:26:40 -04:00
geo_country = self._search_regex(
r'https?://[^/]+\.([a-z]{2})', url,
'geo country', default=None)
if geo_country:
self._initialize_geo_bypass({'countries': [geo_country.upper()]})
2014-07-25 10:33:29 -04:00
video = self._download_json(
'http://playapi.mtgx.tv/v3/videos/%s' % video_id, video_id, 'Downloading video JSON')
2014-07-25 10:33:29 -04:00
2016-07-11 09:51:44 -04:00
title = video['title']
try:
streams = self._download_json(
'http://playapi.mtgx.tv/v3/videos/stream/%s' % video_id,
video_id, 'Downloading streams JSON')
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
msg = self._parse_json(e.cause.read().decode('utf-8'), video_id)
raise ExtractorError(msg['msg'], expected=True)
raise
2014-07-25 10:33:29 -04:00
quality = qualities(['hls', 'medium', 'high'])
formats = []
2016-07-11 09:51:44 -04:00
for format_id, video_url in streams.get('streams', {}).items():
2018-07-21 08:08:28 -04:00
video_url = url_or_none(video_url)
if not video_url:
2014-07-25 10:33:29 -04:00
continue
2016-07-11 09:51:44 -04:00
ext = determine_ext(video_url)
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(
2016-07-11 09:51:44 -04:00
update_url_query(video_url, {
'hdcore': '3.5.0',
'plugin': 'aasp-3.5.0.151.81'
}), video_id, f4m_id='hds', fatal=False))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
2014-07-25 10:33:29 -04:00
else:
2016-07-11 09:51:44 -04:00
fmt = {
'format_id': format_id,
'quality': quality(format_id),
'ext': ext,
}
if video_url.startswith('rtmp'):
m = re.search(
r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url)
2016-07-11 09:51:44 -04:00
if not m:
continue
fmt.update({
'ext': 'flv',
'url': m.group('url'),
'app': m.group('app'),
'play_path': m.group('playpath'),
'preference': -1,
2016-07-11 09:51:44 -04:00
})
else:
fmt.update({
'url': video_url,
})
formats.append(fmt)
if not formats and video.get('is_geo_blocked'):
self.raise_geo_restricted(
'This content might not be available in your country due to copyright reasons',
metadata_available=True)
2014-07-25 10:33:29 -04:00
self._sort_formats(formats)
# TODO: webvtt in m3u8
subtitles = {}
sami_path = video.get('sami_path')
if sami_path:
lang = self._search_regex(
r'_([a-z]{2})\.xml', sami_path, 'lang',
default=compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1])
subtitles[lang] = [{
'url': sami_path,
}]
2016-08-05 11:37:38 -04:00
series = video.get('format_title')
episode_number = int_or_none(video.get('format_position', {}).get('episode'))
season = video.get('_embedded', {}).get('season', {}).get('title')
season_number = int_or_none(video.get('format_position', {}).get('season'))
2014-07-25 10:33:29 -04:00
return {
'id': video_id,
2016-07-11 09:51:44 -04:00
'title': title,
'description': video.get('description'),
2016-08-05 11:37:38 -04:00
'series': series,
'episode_number': episode_number,
'season': season,
'season_number': season_number,
2016-07-11 09:51:44 -04:00
'duration': int_or_none(video.get('duration')),
'timestamp': parse_iso8601(video.get('created_at')),
2016-08-16 13:32:28 -04:00
'view_count': try_get(video, lambda x: x['views']['total'], int),
2016-07-11 09:51:44 -04:00
'age_limit': int_or_none(video.get('age_limit', 0)),
2014-07-25 10:33:29 -04:00
'formats': formats,
'subtitles': subtitles,
2014-07-25 10:33:29 -04:00
}
class ViafreeIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:www\.)?
viafree\.(?P<country>dk|no|se)
/(?P<id>program(?:mer)?/(?:[^/]+/)+[^/?#&]+)
'''
_TESTS = [{
'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
'info_dict': {
'id': '757786',
'ext': 'mp4',
'title': 'Det beste vorspielet - Sesong 2 - Episode 1',
'description': 'md5:b632cb848331404ccacd8cd03e83b4c3',
'series': 'Det beste vorspielet',
'season_number': 2,
'duration': 1116,
'timestamp': 1471200600,
'upload_date': '20160814',
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.viafree.dk/programmer/humor/comedy-central-roast-of-charlie-sheen/film/1047660',
'info_dict': {
'id': '1047660',
'ext': 'mp4',
'title': 'Comedy Central Roast of Charlie Sheen - Comedy Central Roast of Charlie Sheen',
'description': 'md5:ec956d941ae9fd7c65a48fd64951dc6d',
'series': 'Comedy Central Roast of Charlie Sheen',
'season_number': 1,
'duration': 3747,
'timestamp': 1608246060,
'upload_date': '20201217'
},
'params': {
'format': 'bestvideo',
'skip_download': True
}
}, {
# with relatedClips
'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-1',
'only_matching': True,
}, {
# Different og:image URL schema
2016-09-14 11:45:23 -04:00
'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-2',
'only_matching': True,
}, {
'url': 'http://www.viafree.se/program/livsstil/husraddarna/sasong-2/avsnitt-2',
'only_matching': True,
}, {
'url': 'http://www.viafree.dk/programmer/reality/paradise-hotel/saeson-7/episode-5',
'only_matching': True,
}, {
'url': 'http://www.viafree.se/program/underhallning/i-like-radio-live/sasong-1/676869',
'only_matching': True,
}]
_GEO_BYPASS = False
def _real_extract(self, url):
country, path = self._match_valid_url(url).groups()
content = self._download_json(
'https://viafree-content.mtg-api.com/viafree-content/v1/%s/path/%s' % (country, path), path)
program = content['_embedded']['viafreeBlocks'][0]['_embedded']['program']
guid = program['guid']
meta = content['meta']
title = meta['title']
try:
stream_href = self._download_json(
program['_links']['streamLink']['href'], guid,
headers=self.geo_verification_headers())['embedded']['prioritizedStreams'][0]['links']['stream']['href']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
self.raise_geo_restricted(countries=[country])
raise
formats, subtitles = self._extract_m3u8_formats_and_subtitles(stream_href, guid, 'mp4')
self._sort_formats(formats)
episode = program.get('episode') or {}
return {
'id': guid,
'title': title,
'thumbnail': meta.get('image'),
'description': meta.get('description'),
'series': episode.get('seriesTitle'),
'subtitles': subtitles,
'episode_number': int_or_none(episode.get('episodeNumber')),
'season_number': int_or_none(episode.get('seasonNumber')),
'duration': int_or_none(try_get(program, lambda x: x['video']['duration']['milliseconds']), 1000),
'timestamp': parse_iso8601(try_get(program, lambda x: x['availability']['start'])),
'formats': formats,
}
class TVPlayHomeIE(InfoExtractor):
2021-01-01 07:26:37 -05:00
_VALID_URL = r'https?://(?:tv3?)?play\.(?:tv3\.lt|skaties\.lv|tv3\.ee)/(?:[^/]+/)*[^/?#&]+-(?P<id>\d+)'
_TESTS = [{
'url': 'https://tvplay.tv3.lt/aferistai-n-7/aferistai-10047125/',
'info_dict': {
'id': '366367',
'ext': 'mp4',
'title': 'Aferistai',
'description': 'Aferistai. Kalėdinė pasaka.',
'series': 'Aferistai [N-7]',
'season': '1 sezonas',
'season_number': 1,
'duration': 464,
'timestamp': 1394209658,
'upload_date': '20140307',
'age_limit': 18,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://tvplay.skaties.lv/vinas-melo-labak/vinas-melo-labak-10280317/',
'only_matching': True,
}, {
'url': 'https://tvplay.tv3.ee/cool-d-ga-mehhikosse/cool-d-ga-mehhikosse-10044354/',
'only_matching': True,
2021-01-01 07:26:37 -05:00
}, {
'url': 'https://play.tv3.lt/aferistai-10047125',
'only_matching': True,
}, {
'url': 'https://tv3play.skaties.lv/vinas-melo-labak-10280317',
'only_matching': True,
}, {
'url': 'https://play.tv3.ee/cool-d-ga-mehhikosse-10044354',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
2021-01-01 07:26:37 -05:00
asset = self._download_json(
urljoin(url, '/sb/public/asset/' + video_id), video_id)
2021-01-01 07:26:37 -05:00
m3u8_url = asset['movie']['contentUrl']
video_id = asset['assetId']
asset_title = asset['title']
title = asset_title['title']
formats = self._extract_m3u8_formats(
2021-01-01 07:26:37 -05:00
m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
self._sort_formats(formats)
2021-01-01 07:26:37 -05:00
thumbnails = None
image_url = asset.get('imageUrl')
if image_url:
thumbnails = [{
'url': urljoin(url, image_url),
'ext': 'jpg',
}]
2021-01-01 07:26:37 -05:00
metadata = asset.get('metadata') or {}
return {
'id': video_id,
'title': title,
2021-01-01 07:26:37 -05:00
'description': asset_title.get('summaryLong') or asset_title.get('summaryShort'),
'thumbnails': thumbnails,
'duration': parse_duration(asset_title.get('runTime')),
'series': asset.get('tvSeriesTitle'),
'season': asset.get('tvSeasonTitle'),
'season_number': int_or_none(metadata.get('seasonNumber')),
'episode': asset_title.get('titleBrief'),
'episode_number': int_or_none(metadata.get('episodeNumber')),
'formats': formats,
}