X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/3477c644417600d9ec8f8d2a44f82da0a4b15eb5..7fb7d379fb909a4268a2193ba2c84fdca6a4c820:/youtube_dl/extractor/mitele.py diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py index c595f20..40f214a 100644 --- a/youtube_dl/extractor/mitele.py +++ b/youtube_dl/extractor/mitele.py @@ -1,89 +1,120 @@ +# coding: utf-8 from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urlparse, -) from ..utils import ( - encode_dict, - get_element_by_attribute, int_or_none, + smuggle_url, + parse_duration, ) class MiTeleIE(InfoExtractor): IE_DESC = 'mitele.es' - _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P[^/]+)/' + _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P[^/]+)/player' _TESTS = [{ - 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/', - 'md5': '0ff1a13aebb35d9bc14081ff633dd324', + 'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player', 'info_dict': { - 'id': '0NF1jJnxS1Wu3pHrmvFyw2', - 'display_id': 'programa-144', - 'ext': 'flv', + 'id': 'FhYW1iNTE6J6H7NkQRIEzfne6t2quqPg', + 'ext': 'mp4', 'title': 'Tor, la web invisible', 'description': 'md5:3b6fce7eaa41b2d97358726378d9369f', - 'thumbnail': 're:(?i)^https?://.*\.jpg$', + 'series': 'Diario de', + 'season': 'La redacción', + 'season_number': 14, + 'season_id': 'diario_de_t14_11981', + 'episode': 'Programa 144', + 'episode_number': 3, + 'thumbnail': r're:(?i)^https?://.*\.jpg$', 'duration': 2913, }, + 'add_ie': ['Ooyala'], + }, { + # no explicit title + 'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player', + 'info_dict': { + 'id': 'oyNG1iNTE6TAPP-JmCjbwfwJqqMMX3Vq', + 'ext': 'mp4', + 'title': 'Cuarto Milenio Temporada 6 Programa 226', + 'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f', + 'series': 'Cuarto Milenio', + 'season': 'Temporada 6', + 'season_number': 6, + 'season_id': 'cuarto_milenio_t06_12715', + 'episode': 'Programa 226', + 'episode_number': 24, + 'thumbnail': r're:(?i)^https?://.*\.jpg$', + 'duration': 7313, + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': ['Ooyala'], + }, { + 'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player', + 'only_matching': True, }] def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - config_url = self._search_regex( - r'data-config\s*=\s*"([^"]+)"', webpage, 'data config url') - config_url = compat_urlparse.urljoin(url, config_url) - - config = self._download_json( - config_url, display_id, 'Downloading config JSON') - - mmc = self._download_json( - config['services']['mmc'], display_id, 'Downloading mmc JSON') - - formats = [] - for location in mmc['locations']: - gat = self._proto_relative_url(location.get('gat'), 'http:') - bas = location.get('bas') - loc = location.get('loc') - ogn = location.get('ogn') - if None in (gat, bas, loc, ogn): - continue - token_data = { - 'bas': bas, - 'icd': loc, - 'ogn': ogn, - 'sta': '0', - } - media = self._download_json( - '%s/?%s' % (gat, compat_urllib_parse.urlencode(encode_dict(token_data))), - display_id, 'Downloading %s JSON' % location['loc']) - file_ = media.get('file') - if not file_: - continue - formats.extend(self._extract_f4m_formats( - file_ + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18', - display_id, f4m_id=loc)) - - title = self._search_regex( - r'class="Destacado-text"[^>]*>\s*([^<]+)', webpage, 'title') - - video_id = self._search_regex( - r'data-media-id\s*=\s*"([^"]+)"', webpage, - 'data media id', default=None) or display_id - thumbnail = config.get('poster', {}).get('imageUrl') - duration = int_or_none(mmc.get('duration')) + video_id = self._match_id(url) + + paths = self._download_json( + 'https://www.mitele.es/amd/agp/web/metadata/general_configuration', + video_id, 'Downloading paths JSON') + + ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search'] + base_url = ooyala_s.get('base_url', 'cdn-search-mediaset.carbyne.ps.ooyala.com') + full_path = ooyala_s.get('full_path', '/search/v1/full/providers/') + source = self._download_json( + '%s://%s%s%s/docs/%s' % ( + ooyala_s.get('protocol', 'https'), base_url, full_path, + ooyala_s.get('provider_id', '104951'), video_id), + video_id, 'Downloading data JSON', query={ + 'include_titles': 'Series,Season', + 'product_name': ooyala_s.get('product_name', 'test'), + 'format': 'full', + })['hits']['hits'][0]['_source'] + + embedCode = source['offers'][0]['embed_codes'][0] + titles = source['localizable_titles'][0] + + title = titles.get('title_medium') or titles['title_long'] + + description = titles.get('summary_long') or titles.get('summary_medium') + + def get(key1, key2): + value1 = source.get(key1) + if not value1 or not isinstance(value1, list): + 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 { + '_type': 'url_transparent', + # for some reason only HLS is supported + 'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8,dash'}), 'id': video_id, - 'display_id': display_id, 'title': title, - 'description': get_element_by_attribute('class', 'text', webpage), - 'thumbnail': thumbnail, + 'description': description, + 'series': series, + 'season': season, + 'season_number': season_number, + 'season_id': season_id, + 'episode': episode, + 'episode_number': episode_number, 'duration': duration, - 'formats': formats, + 'thumbnail': get('images', 'url'), }