forked from minhngoc25a/yt-dlc
[mitele] Modernize and extract more metadata
This commit is contained in:
parent
b68599ed47
commit
8eb7b5c3f1
|
@ -86,7 +86,10 @@ class MiTeleIE(InfoExtractor):
|
||||||
'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
|
'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
|
||||||
'series': 'Diario de',
|
'series': 'Diario de',
|
||||||
'season': 'La redacción',
|
'season': 'La redacción',
|
||||||
|
'season_number': 14,
|
||||||
|
'season_id': 'diario_de_t14_11981',
|
||||||
'episode': 'Programa 144',
|
'episode': 'Programa 144',
|
||||||
|
'episode_number': 3,
|
||||||
'thumbnail': 're:(?i)^https?://.*\.jpg$',
|
'thumbnail': 're:(?i)^https?://.*\.jpg$',
|
||||||
'duration': 2913,
|
'duration': 2913,
|
||||||
},
|
},
|
||||||
|
@ -101,7 +104,10 @@ class MiTeleIE(InfoExtractor):
|
||||||
'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
|
'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
|
||||||
'series': 'Cuarto Milenio',
|
'series': 'Cuarto Milenio',
|
||||||
'season': 'Temporada 6',
|
'season': 'Temporada 6',
|
||||||
|
'season_number': 6,
|
||||||
|
'season_id': 'cuarto_milenio_t06_12715',
|
||||||
'episode': 'Programa 226',
|
'episode': 'Programa 226',
|
||||||
|
'episode_number': 24,
|
||||||
'thumbnail': 're:(?i)^https?://.*\.jpg$',
|
'thumbnail': 're:(?i)^https?://.*\.jpg$',
|
||||||
'duration': 7313,
|
'duration': 7313,
|
||||||
},
|
},
|
||||||
|
@ -118,35 +124,68 @@ class MiTeleIE(InfoExtractor):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
webpage = self._download_webpage(url, video_id)
|
webpage = self._download_webpage(url, video_id)
|
||||||
|
|
||||||
gigya_url = self._search_regex(r'<gigya-api>[^>]*</gigya-api>[^>]*<script\s*src="([^"]*)">[^>]*</script>', webpage, 'gigya', default=None)
|
gigya_url = self._search_regex(
|
||||||
gigya_sc = self._download_webpage(compat_urlparse.urljoin(r'http://www.mitele.es/', gigya_url), video_id, 'Downloading gigya script')
|
r'<gigya-api>[^>]*</gigya-api>[^>]*<script\s+src="([^"]*)">[^>]*</script>',
|
||||||
|
webpage, 'gigya', default=None)
|
||||||
|
gigya_sc = self._download_webpage(
|
||||||
|
compat_urlparse.urljoin('http://www.mitele.es/', gigya_url),
|
||||||
|
video_id, 'Downloading gigya script')
|
||||||
|
|
||||||
# Get a appKey/uuid for getting the session key
|
# Get a appKey/uuid for getting the session key
|
||||||
appKey_var = self._search_regex(r'value\("appGridApplicationKey",([0-9a-f]+)\)', gigya_sc, 'appKey variable')
|
appKey_var = self._search_regex(
|
||||||
appKey = self._search_regex(r'var %s="([0-9a-f]+)"' % appKey_var, gigya_sc, 'appKey')
|
r'value\s*\(\s*["\']appGridApplicationKey["\']\s*,\s*([0-9a-f]+)',
|
||||||
uid = compat_str(uuid.uuid4())
|
gigya_sc, 'appKey variable')
|
||||||
session_url = 'https://appgrid-api.cloud.accedo.tv/session?appKey=%s&uuid=%s' % (appKey, uid)
|
appKey = self._search_regex(
|
||||||
session_json = self._download_json(session_url, video_id, 'Downloading session keys')
|
r'var\s+%s\s*=\s*["\']([0-9a-f]+)' % appKey_var, gigya_sc, 'appKey')
|
||||||
sessionKey = compat_str(session_json['sessionKey'])
|
|
||||||
|
session_json = self._download_json(
|
||||||
|
'https://appgrid-api.cloud.accedo.tv/session',
|
||||||
|
video_id, 'Downloading session keys', query={
|
||||||
|
'appKey': appKey,
|
||||||
|
'uuid': compat_str(uuid.uuid4()),
|
||||||
|
})
|
||||||
|
|
||||||
|
paths = self._download_json(
|
||||||
|
'https://appgrid-api.cloud.accedo.tv/metadata/general_configuration,%20web_configuration',
|
||||||
|
video_id, 'Downloading paths JSON',
|
||||||
|
query={'sessionKey': compat_str(session_json['sessionKey'])})
|
||||||
|
|
||||||
paths_url = 'https://appgrid-api.cloud.accedo.tv/metadata/general_configuration,%20web_configuration?sessionKey=' + sessionKey
|
|
||||||
paths = self._download_json(paths_url, video_id, 'Downloading paths JSON')
|
|
||||||
ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search']
|
ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search']
|
||||||
data_p = (
|
source = self._download_json(
|
||||||
'http://' + ooyala_s['base_url'] + ooyala_s['full_path'] + ooyala_s['provider_id'] +
|
'http://%s%s%s/docs/%s' % (
|
||||||
'/docs/' + video_id + '?include_titles=Series,Season&product_name=test&format=full')
|
ooyala_s['base_url'], ooyala_s['full_path'],
|
||||||
data = self._download_json(data_p, video_id, 'Downloading data JSON')
|
ooyala_s['provider_id'], video_id),
|
||||||
source = data['hits']['hits'][0]['_source']
|
video_id, 'Downloading data JSON', query={
|
||||||
embedCode = source['offers'][0]['embed_codes'][0]
|
'include_titles': 'Series,Season',
|
||||||
|
'product_name': 'test',
|
||||||
|
'format': 'full',
|
||||||
|
})['hits']['hits'][0]['_source']
|
||||||
|
|
||||||
|
embedCode = source['offers'][0]['embed_codes'][0]
|
||||||
titles = source['localizable_titles'][0]
|
titles = source['localizable_titles'][0]
|
||||||
|
|
||||||
title = titles.get('title_medium') or titles['title_long']
|
title = titles.get('title_medium') or titles['title_long']
|
||||||
episode = titles['title_sort_name']
|
|
||||||
description = titles['summary_long']
|
description = titles.get('summary_long') or titles.get('summary_medium')
|
||||||
titles_series = source['localizable_titles_series'][0]
|
|
||||||
series = titles_series['title_long']
|
def get(key1, key2):
|
||||||
titles_season = source['localizable_titles_season'][0]
|
value1 = source.get(key1)
|
||||||
season = titles_season['title_medium']
|
if not value1 or not isinstance(value1, list):
|
||||||
duration = parse_duration(source['videos'][0]['duration'])
|
return
|
||||||
|
if not isinstance(value1[0], dict):
|
||||||
|
return
|
||||||
|
return value1[0].get(key2)
|
||||||
|
|
||||||
|
series = get('localizable_titles_series', 'title_medium')
|
||||||
|
|
||||||
|
season = get('localizable_titles_season', 'title_medium')
|
||||||
|
season_number = int_or_none(source.get('season_number'))
|
||||||
|
season_id = source.get('season_id')
|
||||||
|
|
||||||
|
episode = titles.get('title_sort_name')
|
||||||
|
episode_number = int_or_none(source.get('episode_number'))
|
||||||
|
|
||||||
|
duration = parse_duration(get('videos', 'duration'))
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'_type': 'url_transparent',
|
'_type': 'url_transparent',
|
||||||
|
@ -157,7 +196,10 @@ class MiTeleIE(InfoExtractor):
|
||||||
'description': description,
|
'description': description,
|
||||||
'series': series,
|
'series': series,
|
||||||
'season': season,
|
'season': season,
|
||||||
|
'season_number': season_number,
|
||||||
|
'season_id': season_id,
|
||||||
'episode': episode,
|
'episode': episode,
|
||||||
|
'episode_number': episode_number,
|
||||||
'duration': duration,
|
'duration': duration,
|
||||||
'thumbnail': source['images'][0]['url'],
|
'thumbnail': get('images', 'url'),
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in New Issue