aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/tvplay.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/tvplay.py')
-rw-r--r--youtube_dl/extractor/tvplay.py205
1 files changed, 134 insertions, 71 deletions
diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py
index 99ff82a5d..0d858c025 100644
--- a/youtube_dl/extractor/tvplay.py
+++ b/youtube_dl/extractor/tvplay.py
@@ -6,17 +6,19 @@ import re
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
- compat_str,
compat_urlparse,
)
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
+ parse_duration,
parse_iso8601,
qualities,
try_get,
update_url_query,
+ url_or_none,
+ urljoin,
)
@@ -29,12 +31,12 @@ class TVPlayIE(InfoExtractor):
https?://
(?:www\.)?
(?:
- tvplay(?:\.skaties)?\.lv/parraides|
- (?:tv3play|play\.tv3)\.lt/programos|
+ 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\.novatv\.bg/programi
+ play\.nova(?:tv)?\.bg/programi
)
/(?:[^/]+/)+
)
@@ -201,10 +203,18 @@ class TVPlayIE(InfoExtractor):
},
},
{
+ '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,
@@ -229,7 +239,7 @@ class TVPlayIE(InfoExtractor):
r'https?://[^/]+\.([a-z]{2})', url,
'geo country', default=None)
if geo_country:
- self._initialize_geo_bypass([geo_country.upper()])
+ self._initialize_geo_bypass({'countries': [geo_country.upper()]})
video = self._download_json(
'http://playapi.mtgx.tv/v3/videos/%s' % video_id, video_id, 'Downloading video JSON')
@@ -248,7 +258,8 @@ class TVPlayIE(InfoExtractor):
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':
@@ -277,6 +288,7 @@ class TVPlayIE(InfoExtractor):
'url': m.group('url'),
'app': m.group('app'),
'play_path': m.group('playpath'),
+ 'preference': -1,
})
else:
fmt.update({
@@ -327,103 +339,154 @@ class ViafreeIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:www\.)?
- viafree\.
- (?:
- (?:dk|no)/programmer|
- se/program
- )
- /(?:[^/]+/)+(?P<id>[^/?#&]+)
+ viafree\.(?P<country>dk|no|se)
+ /(?P<id>program(?:mer)?/(?:[^/]+/)+[^/?#&]+)
'''
_TESTS = [{
- 'url': 'http://www.viafree.se/program/livsstil/husraddarna/sasong-2/avsnitt-2',
+ 'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
'info_dict': {
- 'id': '395375',
+ 'id': '757786',
'ext': 'mp4',
- 'title': 'Husräddarna S02E02',
- 'description': 'md5:4db5c933e37db629b5a2f75dfb34829e',
- 'series': 'Husräddarna',
- 'season': 'Säsong 2',
+ 'title': 'Det beste vorspielet - Sesong 2 - Episode 1',
+ 'description': 'md5:b632cb848331404ccacd8cd03e83b4c3',
+ 'series': 'Det beste vorspielet',
'season_number': 2,
- 'duration': 2576,
- 'timestamp': 1400596321,
- 'upload_date': '20140520',
+ 'duration': 1116,
+ 'timestamp': 1471200600,
+ 'upload_date': '20160814',
},
'params': {
'skip_download': True,
},
- 'add_ie': [TVPlayIE.ie_key()],
}, {
# with relatedClips
'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-1',
- 'info_dict': {
- 'id': '758770',
- 'ext': 'mp4',
- 'title': 'Sommaren med YouTube-stjärnorna S01E01',
- 'description': 'md5:2bc69dce2c4bb48391e858539bbb0e3f',
- 'series': 'Sommaren med YouTube-stjärnorna',
- 'season': 'Säsong 1',
- 'season_number': 1,
- 'duration': 1326,
- 'timestamp': 1470905572,
- 'upload_date': '20160811',
- },
- 'params': {
- 'skip_download': True,
- },
- 'add_ie': [TVPlayIE.ie_key()],
+ '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.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
+ '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):
- video_id = self._match_id(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,
+ }
- webpage = self._download_webpage(url, video_id)
- data = self._parse_json(
- self._search_regex(
- r'(?s)window\.App\s*=\s*({.+?})\s*;\s*</script',
- webpage, 'data', default='{}'),
- video_id, transform_source=lambda x: re.sub(
- r'(?s)function\s+[a-zA-Z_][\da-zA-Z_]*\s*\([^)]*\)\s*{[^}]*}\s*',
- 'null', x), fatal=False)
+class TVPlayHomeIE(InfoExtractor):
+ _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,
+ }, {
+ '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,
+ }]
- video_id = None
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
- if data:
- video_id = try_get(
- data, lambda x: x['context']['dispatcher']['stores'][
- 'ContentPageProgramStore']['currentVideo']['id'],
- compat_str)
+ asset = self._download_json(
+ urljoin(url, '/sb/public/asset/' + video_id), video_id)
- # Fallback #1 (extract from og:image URL schema)
- if not video_id:
- thumbnail = self._og_search_thumbnail(webpage, default=None)
- if thumbnail:
- video_id = self._search_regex(
- # Patterns seen:
- # http://cdn.playapi.mtgx.tv/imagecache/600x315/cloud/content-images/inbox/765166/a2e95e5f1d735bab9f309fa345cc3f25.jpg
- # http://cdn.playapi.mtgx.tv/imagecache/600x315/cloud/content-images/seasons/15204/758770/4a5ba509ca8bc043e1ebd1a76131cdf2.jpg
- r'https?://[^/]+/imagecache/(?:[^/]+/)+(\d{6,})/',
- thumbnail, 'video id', default=None)
+ m3u8_url = asset['movie']['contentUrl']
+ video_id = asset['assetId']
+ asset_title = asset['title']
+ title = asset_title['title']
- # Fallback #2. Extract from raw JSON string.
- # May extract wrong video id if relatedClips is present.
- if not video_id:
- video_id = self._search_regex(
- r'currentVideo["\']\s*:\s*.+?["\']id["\']\s*:\s*["\'](\d{6,})',
- webpage, 'video id')
+ formats = self._extract_m3u8_formats(
+ m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
+ self._sort_formats(formats)
- return self.url_result('mtg:%s' % video_id, TVPlayIE.ie_key())
+ thumbnails = None
+ image_url = asset.get('imageUrl')
+ if image_url:
+ thumbnails = [{
+ 'url': urljoin(url, image_url),
+ 'ext': 'jpg',
+ }]
+
+ metadata = asset.get('metadata') or {}
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ '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,
+ }
generated by cgit v1.2.3 (git 2.26.2) at 2025-11-04 10:21:11 +0000