0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-04 04:07:26 +00:00
yt-dlp/yt_dlp/extractor/stv.py

89 lines
3.2 KiB
Python
Raw Normal View History

from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
2021-01-08 16:14:50 +00:00
smuggle_url,
str_or_none,
try_get,
)
class STVPlayerIE(InfoExtractor):
IE_NAME = 'stv:player'
_VALID_URL = r'https?://player\.stv\.tv/(?P<type>episode|video)/(?P<id>[a-z0-9]{4})'
2021-01-08 16:14:50 +00:00
_TESTS = [{
# shortform
2019-11-02 17:13:31 +00:00
'url': 'https://player.stv.tv/video/4gwd/emmerdale/60-seconds-on-set-with-laura-norton/',
'md5': '5adf9439c31d554f8be0707c7abe7e0a',
'info_dict': {
2019-11-02 17:13:31 +00:00
'id': '5333973339001',
'ext': 'mp4',
2019-11-02 17:13:31 +00:00
'upload_date': '20170301',
'title': '60 seconds on set with Laura Norton',
'description': "How many questions can Laura - a.k.a Kerry Wyatt - answer in 60 seconds? Let's find out!",
2019-11-02 17:13:31 +00:00
'timestamp': 1488388054,
'uploader_id': '1486976045',
},
'skip': 'this resource is unavailable outside of the UK',
2021-01-08 16:14:50 +00:00
}, {
# episodes
'url': 'https://player.stv.tv/episode/4125/jennifer-saunders-memory-lane',
'only_matching': True,
}]
2019-11-02 17:13:31 +00:00
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1486976045/default_default/index.html?videoId=%s'
_PTYPE_MAP = {
'episode': 'episodes',
'video': 'shortform',
}
def _real_extract(self, url):
ptype, video_id = self._match_valid_url(url).groups()
2021-01-08 16:14:50 +00:00
webpage = self._download_webpage(url, video_id, fatal=False) or ''
props = self._search_nextjs_data(webpage, video_id, default={}).get('props') or {}
2021-01-08 16:14:50 +00:00
player_api_cache = try_get(
props, lambda x: x['initialReduxState']['playerApiCache']) or {}
api_path, resp = None, {}
for k, v in player_api_cache.items():
if k.startswith(('/episodes/', '/shortform/')):
2021-01-08 16:14:50 +00:00
api_path, resp = k, v
break
else:
episode_id = str_or_none(try_get(
props, lambda x: x['pageProps']['episodeId']))
api_path = f'/{self._PTYPE_MAP[ptype]}/{episode_id or video_id}'
2021-01-08 16:14:50 +00:00
result = resp.get('results')
if not result:
resp = self._download_json(
'https://player.api.stv.tv/v1' + api_path, video_id)
result = resp['results']
2019-11-02 17:13:31 +00:00
video = result['video']
video_id = str(video['id'])
2019-11-02 17:13:31 +00:00
subtitles = {}
_subtitles = result.get('_subtitles') or {}
for ext, sub_url in _subtitles.items():
subtitles.setdefault('en', []).append({
'ext': 'vtt' if ext == 'webvtt' else ext,
'url': sub_url,
})
2019-11-02 17:13:31 +00:00
programme = result.get('programme') or {}
if programme.get('drmEnabled'):
self.report_drm(video_id)
2019-11-02 17:13:31 +00:00
return {
'_type': 'url_transparent',
'id': video_id,
2021-01-08 16:14:50 +00:00
'url': smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % video_id, {'geo_countries': ['GB']}),
2019-11-02 17:13:31 +00:00
'description': result.get('summary'),
'duration': float_or_none(video.get('length'), 1000),
'subtitles': subtitles,
'view_count': int_or_none(result.get('views')),
'series': programme.get('name') or programme.get('shortName'),
'ie_key': 'BrightcoveNew',
2019-11-02 17:13:31 +00:00
}