2 from __future__ import unicode_literals
7 from .common import InfoExtractor
16 class TelecincoIE(InfoExtractor):
17 IE_DESC = 'telecinco.es, cuatro.com and mediaset.es'
18 _VALID_URL = r'https?://(?:www\.)?(?:telecinco\.es|cuatro\.com|mediaset\.es)/(?:[^/]+/)+(?P<id>.+?)\.html'
21 'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html',
24 'title': 'Bacalao con kokotxas al pil-pil',
25 'description': 'md5:716caf5601e25c3c5ab6605b1ae71529',
28 'md5': '7ee56d665cfd241c0e6d80fd175068b0',
30 'id': 'JEA5ijCnF6p5W08A1rNKn7',
32 'title': 'Con Martín Berasategui, hacer un bacalao al pil-pil es fácil y divertido',
37 'url': 'http://www.cuatro.com/deportes/futbol/barcelona/Leo_Messi-Champions-Roma_2_2052780128.html',
38 'md5': 'c86fe0d99e3bdb46b7950d38bf6ef12a',
40 'id': 'jn24Od1zGLG4XUZcnUnZB6',
42 'title': '¿Quién es este ex futbolista con el que hablan Leo Messi y Luis Suárez?',
43 'description': 'md5:a62ecb5f1934fc787107d7b9a2262805',
47 'url': 'http://www.mediaset.es/12meses/campanas/doylacara/conlatratanohaytrato/Ayudame-dar-cara-trata-trato_2_1986630220.html',
48 'md5': 'eddb50291df704ce23c74821b995bcac',
50 'id': 'aywerkD2Sv1vGNqq9b85Q2',
52 'title': '#DOYLACARA. Con la trata no hay trato',
53 'description': 'md5:2771356ff7bfad9179c5f5cd954f1477',
57 # video in opening's content
58 'url': 'https://www.telecinco.es/vivalavida/fiorella-sobrina-edmundo-arrocet-entrevista_18_2907195140.html',
61 'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"',
62 'description': 'md5:73f340a7320143d37ab895375b2bf13a',
65 'md5': 'adb28c37238b675dad0f042292f209a7',
67 'id': 'TpI2EttSDAReWpJ1o0NVh2',
69 'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"',
74 'skip_download': True,
77 'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html',
78 'only_matching': True,
80 'url': 'http://www.telecinco.es/espanasinirmaslejos/Espana-gran-destino-turistico_2_1240605043.html',
81 'only_matching': True,
84 'url': 'http://www.cuatro.com/chesterinlove/a-carta/chester-chester_in_love-chester_edu_2_2331030022.html',
85 'only_matching': True,
88 def _parse_content(self, content, url):
89 video_id = content['dataMediaId']
90 config = self._download_json(
91 content['dataConfig'], video_id, 'Downloading config JSON')
92 title = config['info']['title']
93 services = config['services']
94 caronte = self._download_json(services['caronte'], video_id)
95 stream = caronte['dls'][0]['stream']
96 headers = self.geo_verification_headers()
98 'Content-Type': 'application/json;charset=UTF-8',
99 'Origin': re.match(r'https?://[^/]+', url).group(0),
101 cdn = self._download_json(
102 caronte['cerbero'], video_id, data=json.dumps({
103 'bbx': caronte['bbx'],
104 'gbx': self._download_json(services['gbx'], video_id)['gbx'],
105 }).encode(), headers=headers)['tokens']['1']['cdn']
106 formats = self._extract_m3u8_formats(
107 stream + '?' + cdn, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
108 self._sort_formats(formats)
114 'thumbnail': content.get('dataPoster') or config.get('poster', {}).get('imageUrl'),
115 'duration': int_or_none(content.get('dataDuration')),
118 def _real_extract(self, url):
119 display_id = self._match_id(url)
120 webpage = self._download_webpage(url, display_id)
121 article = self._parse_json(self._search_regex(
122 r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=\s*({.+})',
123 webpage, 'article'), display_id)['article']
124 title = article.get('title')
125 description = clean_html(article.get('leadParagraph')) or ''
126 if article.get('editorialType') != 'VID':
128 body = [article.get('opening')]
129 body.extend(try_get(article, lambda x: x['body'], list) or [])
131 if not isinstance(p, dict):
133 content = p.get('content')
136 type_ = p.get('type')
137 if type_ == 'paragraph':
138 content_str = str_or_none(content)
140 description += content_str
142 if type_ == 'video' and isinstance(content, dict):
143 entries.append(self._parse_content(content, url))
144 return self.playlist_result(
145 entries, str_or_none(article.get('id')), title, description)
146 content = article['opening']['content']
147 info = self._parse_content(content, url)
149 'description': description,