import re
from .common import InfoExtractor
-from ..compat import compat_str
+from ..compat import (
+ compat_HTTPError,
+ compat_urlparse,
+)
from ..utils import (
+ determine_ext,
+ ExtractorError,
+ int_or_none,
parse_iso8601,
qualities,
- determine_ext,
+ try_get,
update_url_query,
- int_or_none,
+ url_or_none,
)
class TVPlayIE(InfoExtractor):
- IE_DESC = 'TV3Play and related services'
- _VALID_URL = r'''(?x)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\.novatv\.bg/programi
- )/[^/]+/(?P<id>\d+)
- '''
+ 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|viafree)\.se/program|
+ (?:(?:tv3play|viasat4play|tv6play|viafree)\.no|(?:tv3play|viafree)\.dk)/programmer|
+ play\.nova(?:tv)?\.bg/programi
+ )
+ /(?:[^/]+/)+
+ )
+ (?P<id>\d+)
+ '''
_TESTS = [
{
'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true',
'ext': 'mp4',
'title': 'Kādi ir īri? - Viņas melo labāk',
'description': 'Baiba apsmej īrus, kādi tie ir un ko viņi dara.',
+ 'series': 'Viņas melo labāk',
+ 'season': '2.sezona',
+ 'season_number': 2,
'duration': 25,
'timestamp': 1406097056,
'upload_date': '20140723',
'ext': 'flv',
'title': 'Moterys meluoja geriau',
'description': 'md5:9aec0fc68e2cbc992d2a140bd41fa89e',
+ 'series': 'Moterys meluoja geriau',
+ 'episode_number': 47,
+ 'season': '1 sezonas',
+ 'season_number': 1,
'duration': 1330,
'timestamp': 1403769181,
'upload_date': '20140626',
'skip_download': True,
},
},
+ {
+ 'url': 'https://play.nova.bg/programi/zdravei-bulgariya/764300?autostart=true',
+ 'only_matching': True,
+ },
{
'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,
+ },
+ {
+ # views is null
+ 'url': 'http://tvplay.skaties.lv/parraides/tv3-zinas/760183',
+ 'only_matching': True,
+ },
{
'url': 'http://tv3play.tv3.ee/sisu/kodu-keset-linna/238551?autostart=true',
'only_matching': True,
+ },
+ {
+ 'url': 'http://www.viafree.se/program/underhallning/i-like-radio-live/sasong-1/676869',
+ 'only_matching': True,
+ },
+ {
+ 'url': 'mtg:418113',
+ 'only_matching': True,
}
]
def _real_extract(self, url):
video_id = self._match_id(url)
-
+ 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()]})
video = self._download_json(
- 'http://playapi.mtgx.tv/v1/videos/%s' % video_id, video_id, 'Downloading video JSON')
+ 'http://playapi.mtgx.tv/v3/videos/%s' % video_id, video_id, 'Downloading video JSON')
title = video['title']
- if video.get('is_geo_blocked'):
- self.report_warning(
- 'This content might not be available in your country due to copyright reasons')
-
- streams = self._download_json(
- 'http://playapi.mtgx.tv/v1/videos/stream/%s' % video_id, video_id, 'Downloading streams JSON')
+ 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
quality = qualities(['hls', 'medium', 'high'])
formats = []
for format_id, video_url in streams.get('streams', {}).items():
- if not video_url or not isinstance(video_url, compat_str):
+ video_url = url_or_none(video_url)
+ if not video_url:
continue
ext = determine_ext(video_url)
if ext == 'f4m':
'ext': ext,
}
if video_url.startswith('rtmp'):
- m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url)
+ m = re.search(
+ r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url)
if not m:
continue
fmt.update({
'url': m.group('url'),
'app': m.group('app'),
'play_path': m.group('playpath'),
+ 'preference': -1,
})
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')
+
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,
+ }]
+
+ 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'))
+
return {
'id': video_id,
'title': title,
'description': video.get('description'),
+ 'series': series,
+ 'episode_number': episode_number,
+ 'season': season,
+ 'season_number': season_number,
'duration': int_or_none(video.get('duration')),
'timestamp': parse_iso8601(video.get('created_at')),
- 'view_count': int_or_none(video.get('views', {}).get('total')),
+ 'view_count': try_get(video, lambda x: x['views']['total'], int),
'age_limit': int_or_none(video.get('age_limit', 0)),
'formats': formats,
+ 'subtitles': subtitles,
+ }
+
+
+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,
+ },
+ }, {
+ # 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
+ '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,
+ }]
+ _GEO_BYPASS = False
+
+ @classmethod
+ def suitable(cls, url):
+ return False if TVPlayIE.suitable(url) else super(ViafreeIE, cls).suitable(url)
+
+ def _real_extract(self, url):
+ country, path = re.match(self._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 = self._extract_m3u8_formats(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'),
+ '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):
+ _VALID_URL = r'https?://tvplay\.(?: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,
+ },
+ 'add_ie': [TVPlayIE.ie_key()],
+ }, {
+ '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,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_id = self._search_regex(
+ r'data-asset-id\s*=\s*["\'](\d{5,})\b', webpage, 'video id')
+
+ if len(video_id) < 8:
+ return self.url_result(
+ 'mtg:%s' % video_id, ie=TVPlayIE.ie_key(), video_id=video_id)
+
+ m3u8_url = self._search_regex(
+ r'data-file\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+ 'm3u8 url', group='url')
+
+ formats = self._extract_m3u8_formats(
+ m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls')
+ self._sort_formats(formats)
+
+ title = self._search_regex(
+ r'data-title\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
+ 'title', default=None, group='value') or self._html_search_meta(
+ 'title', webpage, default=None) or self._og_search_title(
+ webpage)
+
+ description = self._html_search_meta(
+ 'description', webpage,
+ default=None) or self._og_search_description(webpage)
+
+ thumbnail = self._search_regex(
+ r'data-image\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+ 'thumbnail', default=None, group='url') or self._html_search_meta(
+ 'thumbnail', webpage, default=None) or self._og_search_thumbnail(
+ webpage)
+
+ duration = int_or_none(self._search_regex(
+ r'data-duration\s*=\s*["\'](\d+)', webpage, 'duration',
+ fatal=False))
+
+ season = self._search_regex(
+ (r'data-series-title\s*=\s*(["\'])[^/]+/(?P<value>(?:(?!\1).)+)\1',
+ r'\bseason\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
+ 'season', default=None, group='value')
+ season_number = int_or_none(self._search_regex(
+ r'(\d+)(?:[.\s]+sezona|\s+HOOAEG)', season or '', 'season number',
+ default=None))
+ episode = self._search_regex(
+ (r'\bepisode\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+ r'data-subtitle\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
+ 'episode', default=None, group='value')
+ episode_number = int_or_none(self._search_regex(
+ r'(?:S[eē]rija|Osa)\s+(\d+)', episode or '', 'episode number',
+ default=None))
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'season': season,
+ 'season_number': season_number,
+ 'episode': episode,
+ 'episode_number': episode_number,
+ 'formats': formats,
}
projects / youtube-dl / blobdiff