[yt-dlp.git] / yt_dlp / extractor / rtvcplay.py

import re

from .common import InfoExtractor, ExtractorError
from ..utils import (
    clean_html,
    determine_ext,
    int_or_none,
    float_or_none,
    js_to_json,
    mimetype2ext,
    traverse_obj,
    urljoin,
    url_or_none,
)


class RTVCPlayBaseIE(InfoExtractor):
    _BASE_VALID_URL = r'https?://(?:www\.)?rtvcplay\.co'

    def _extract_player_config(self, webpage, video_id):
        return self._search_json(
            r'<script\b[^>]*>[^<]*(?:var|let|const)\s+config\s*=', re.sub(r'"\s*\+\s*"', '', webpage),
            'player_config', video_id, transform_source=js_to_json)

    def _extract_formats_and_subtitles_player_config(self, player_config, video_id):
        formats, subtitles = [], {}
        for source in traverse_obj(player_config, ('sources', ..., lambda _, v: url_or_none(v['url']))):
            ext = mimetype2ext(source.get('mimetype'), default=determine_ext(source['url']))
            if ext == 'm3u8':
                fmts, subs = self._extract_m3u8_formats_and_subtitles(
                    source['url'], video_id, 'mp4', fatal=False)
                formats.extend(fmts)
                self._merge_subtitles(subs, target=subtitles)
            else:
                formats.append({
                    'url': source['url'],
                    'ext': ext,
                })

        return formats, subtitles


class RTVCPlayIE(RTVCPlayBaseIE):
    _VALID_URL = RTVCPlayBaseIE._BASE_VALID_URL + r'/(?P<category>(?!embed)[^/]+)/(?:[^?#]+/)?(?P<id>[\w-]+)'

    _TESTS = [{
        'url': 'https://www.rtvcplay.co/en-vivo/canal-institucional',
        'info_dict': {
            'id': 'canal-institucional',
            'title': r're:^Canal Institucional',
            'description': 'md5:eff9e548394175928059320c006031ea',
            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
            'live_status': 'is_live',
            'ext': 'mp4',
        },
        'params': {
            'skip_download': 'Livestream',
        },
    }, {
        'url': 'https://www.rtvcplay.co/en-vivo/senal-colombia',
        'info_dict': {
            'id': 'senal-colombia',
            'title': r're:^Señal Colombia',
            'description': 'md5:799f16a401d97f40c33a2c6a3e2a507b',
            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
            'live_status': 'is_live',
            'ext': 'mp4',
        },
        'params': {
            'skip_download': 'Livestream',
        },
    }, {
        'url': 'https://www.rtvcplay.co/en-vivo/radio-nacional',
        'info_dict': {
            'id': 'radio-nacional',
            'title': r're:^Radio Nacional',
            'description': 'md5:5de009bc6a9fa79d2a6cf0b73f977d53',
            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
            'live_status': 'is_live',
            'ext': 'mp4',
        },
        'params': {
            'skip_download': 'Livestream',
        },
    }, {
        'url': 'https://www.rtvcplay.co/peliculas-ficcion/senoritas',
        'md5': '1288ee6f6d1330d880f98bff2ed710a3',
        'info_dict': {
            'id': 'senoritas',
            'title': 'Señoritas',
            'description': 'md5:f095a2bb52cb6cf279daf6302f86fb32',
            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
            'ext': 'mp4',
        },
    }, {
        'url': 'https://www.rtvcplay.co/competencias-basicas-ciudadanas-y-socioemocionales/profe-en-tu-casa/james-regresa-clases-28022022',
        'md5': 'f040a7380a269ad633cf837384d5e9fc',
        'info_dict': {
            'id': 'james-regresa-clases-28022022',
            'title': 'James regresa a clases - 28/02/2022',
            'description': 'md5:c5dcdf757c7ab29305e8763c6007e675',
            'ext': 'mp4',
        },
    }, {
        'url': 'https://www.rtvcplay.co/peliculas-documentales/llinas-el-cerebro-y-el-universo',
        'info_dict': {
            'id': 'llinas-el-cerebro-y-el-universo',
            'title': 'Llinás, el cerebro y el universo',
            'description': 'md5:add875bf2309bb52b3e8b9b06116d9b0',
            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
        },
        'playlist_mincount': 3,
    }, {
        'url': 'https://www.rtvcplay.co/competencias-basicas-ciudadanas-y-socioemocionales/profe-en-tu-casa',
        'info_dict': {
            'id': 'profe-en-tu-casa',
            'title': 'Profe en tu casa',
            'description': 'md5:47dbe20e263194413b1db2a2805a4f2e',
            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
        },
        'playlist_mincount': 537,
    }, {
        'url': 'https://www.rtvcplay.co/series-al-oido/relato-de-un-naufrago-una-travesia-del-periodismo-a-la-literatura',
        'info_dict': {
            'id': 'relato-de-un-naufrago-una-travesia-del-periodismo-a-la-literatura',
            'title': 'Relato de un náufrago: una travesía del periodismo a la literatura',
            'description': 'md5:6da28fdca4a5a568ea47ef65ef775603',
            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
        },
        'playlist_mincount': 5,
    }, {
        'url': 'https://www.rtvcplay.co/series-al-oido/diez-versiones',
        'info_dict': {
            'id': 'diez-versiones',
            'title': 'Diez versiones',
            'description': 'md5:997471ed971cb3fd8e41969457675306',
            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
        },
        'playlist_mincount': 20,
    }]

    def _real_extract(self, url):
        video_id, category = self._match_valid_url(url).group('id', 'category')
        webpage = self._download_webpage(url, video_id)

        hydration = self._search_json(
            r'window\.__RTVCPLAY_STATE__\s*=', webpage, 'hydration',
            video_id, transform_source=js_to_json)['content']['currentContent']

        asset_id = traverse_obj(hydration, ('video', 'assetid'))
        if asset_id:
            hls_url = hydration['base_url_hls'].replace('[node:field_asset_id]', asset_id)
        else:
            hls_url = traverse_obj(hydration, ('channel', 'hls'))

        metadata = traverse_obj(hydration, {
            'title': 'title',
            'description': 'description',
            'thumbnail': ((('channel', 'image', 'logo'), ('resource', 'image', 'cover_desktop')), 'path'),
        }, get_all=False)

        # Probably it's a program's page
        if not hls_url:
            seasons = traverse_obj(
                hydration, ('widgets', lambda _, y: y['type'] == 'seasonList', 'contents'),
                get_all=False)
            if not seasons:
                podcast_episodes = hydration.get('audios')
                if not podcast_episodes:
                    raise ExtractorError('Could not find asset_id nor program playlist nor podcast episodes')

                return self.playlist_result([
                    self.url_result(episode['file'], url_transparent=True, **traverse_obj(episode, {
                        'title': 'title',
                        'description': ('description', {clean_html}),
                        'episode_number': ('chapter_number', {float_or_none}, {int_or_none}),
                        'season_number': ('season', {int_or_none}),
                    })) for episode in podcast_episodes], video_id, **metadata)

            entries = [self.url_result(
                urljoin(url, episode['slug']), url_transparent=True,
                **traverse_obj(season, {
                    'season': 'title',
                    'season_number': ('season', {int_or_none}),
                }), **traverse_obj(episode, {
                    'title': 'title',
                    'thumbnail': ('image', 'cover', 'path'),
                    'episode_number': ('chapter_number', {int_or_none}),
                })) for season in seasons for episode in traverse_obj(season, ('contents', ...))]

            return self.playlist_result(entries, video_id, **metadata)

        formats, subtitles = self._extract_m3u8_formats_and_subtitles(hls_url, video_id, 'mp4')

        return {
            'id': video_id,
            'formats': formats,
            'subtitles': subtitles,
            'is_live': category == 'en-vivo',
            **metadata,
        }


class RTVCPlayEmbedIE(RTVCPlayBaseIE):
    _VALID_URL = RTVCPlayBaseIE._BASE_VALID_URL + r'/embed/(?P<id>[\w-]+)'

    _TESTS = [{
        'url': 'https://www.rtvcplay.co/embed/72b0e699-248b-4929-a4a8-3782702fa7f9',
        'md5': 'ed529aeaee7aa2a72afe91ac7d1177a8',
        'info_dict': {
            'id': '72b0e699-248b-4929-a4a8-3782702fa7f9',
            'title': 'Tráiler: Señoritas',
            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
            'ext': 'mp4',
        }
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(url, video_id)

        player_config = self._extract_player_config(webpage, video_id)
        formats, subtitles = self._extract_formats_and_subtitles_player_config(player_config, video_id)

        asset_id = traverse_obj(player_config, ('rtvcplay', 'assetid'))
        metadata = {} if not asset_id else self._download_json(
            f'https://cms.rtvcplay.co/api/v1/video/asset-id/{asset_id}', video_id, fatal=False)

        return {
            'id': video_id,
            'formats': formats,
            'subtitles': subtitles,
            **traverse_obj(metadata, {
                'title': 'title',
                'description': 'description',
                'thumbnail': ('image', ..., 'thumbnail', 'path'),
            }, get_all=False)
        }


class RTVCKalturaIE(RTVCPlayBaseIE):
    _VALID_URL = r'https?://media\.rtvc\.gov\.co/kalturartvc/(?P<id>[\w-]+)'

    _TESTS = [{
        'url': 'https://media.rtvc.gov.co/kalturartvc/indexSC.html',
        'info_dict': {
            'id': 'indexSC',
            'title': r're:^Señal Colombia',
            'description': 'md5:799f16a401d97f40c33a2c6a3e2a507b',
            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
            'live_status': 'is_live',
            'ext': 'mp4',
        },
        'params': {
            'skip_download': 'Livestream',
        },
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(url, video_id)

        player_config = self._extract_player_config(webpage, video_id)
        formats, subtitles = self._extract_formats_and_subtitles_player_config(player_config, video_id)

        channel_id = traverse_obj(player_config, ('rtvcplay', 'channelId'))
        metadata = {} if not channel_id else self._download_json(
            f'https://cms.rtvcplay.co/api/v1/taxonomy_term/streaming/{channel_id}', video_id, fatal=False)

        fmts, subs = self._extract_m3u8_formats_and_subtitles(
            traverse_obj(metadata, ('channel', 'hls')), video_id, 'mp4', fatal=False)
        formats.extend(fmts)
        self._merge_subtitles(subs, target=subtitles)

        return {
            'id': video_id,
            'formats': formats,
            'subtitles': subtitles,
            'is_live': True,
            **traverse_obj(metadata, {
                'title': 'title',
                'description': 'description',
                'thumbnail': ('channel', 'image', 'logo', 'path'),
            })
        }
Commit	Line	Data
9b30cd3d E	1	import re
	2
	3	from .common import InfoExtractor, ExtractorError
	4	from ..utils import (
	5	clean_html,
	6	determine_ext,
	7	int_or_none,
	8	float_or_none,
	9	js_to_json,
	10	mimetype2ext,
	11	traverse_obj,
	12	urljoin,
	13	url_or_none,
	14	)
	15
	16
	17	class RTVCPlayBaseIE(InfoExtractor):
	18	_BASE_VALID_URL = r'https?://(?:www\.)?rtvcplay\.co'
	19
	20	def _extract_player_config(self, webpage, video_id):
	21	return self._search_json(
	22	r'<script\b[^>]>[^<](?:var\|let\|const)\s+config\s=', re.sub(r'"\s\+\s*"', '', webpage),
	23	'player_config', video_id, transform_source=js_to_json)
	24
	25	def _extract_formats_and_subtitles_player_config(self, player_config, video_id):
	26	formats, subtitles = [], {}
	27	for source in traverse_obj(player_config, ('sources', ..., lambda _, v: url_or_none(v['url']))):
	28	ext = mimetype2ext(source.get('mimetype'), default=determine_ext(source['url']))
	29	if ext == 'm3u8':
	30	fmts, subs = self._extract_m3u8_formats_and_subtitles(
	31	source['url'], video_id, 'mp4', fatal=False)
	32	formats.extend(fmts)
	33	self._merge_subtitles(subs, target=subtitles)
	34	else:
	35	formats.append({
	36	'url': source['url'],
	37	'ext': ext,
	38	})
	39
	40	return formats, subtitles
	41
	42
	43	class RTVCPlayIE(RTVCPlayBaseIE):
	44	_VALID_URL = RTVCPlayBaseIE._BASE_VALID_URL + r'/(?P<category>(?!embed)[^/]+)/(?:[^?#]+/)?(?P<id>[\w-]+)'
	45
	46	_TESTS = [{
	47	'url': 'https://www.rtvcplay.co/en-vivo/canal-institucional',
	48	'info_dict': {
	49	'id': 'canal-institucional',
	50	'title': r're:^Canal Institucional',
	51	'description': 'md5:eff9e548394175928059320c006031ea',
	52	'thumbnail': r're:^https?://.*\.(?:jpg\|png)',
	53	'live_status': 'is_live',
	54	'ext': 'mp4',
	55	},
	56	'params': {
	57	'skip_download': 'Livestream',
	58	},
	59	}, {
	60	'url': 'https://www.rtvcplay.co/en-vivo/senal-colombia',
	61	'info_dict': {
	62	'id': 'senal-colombia',
	63	'title': r're:^Señal Colombia',
	64	'description': 'md5:799f16a401d97f40c33a2c6a3e2a507b',
65	'thumbnail': r're:^https?://.*\.(?:jpg\|png)',
66	'live_status': 'is_live',
67	'ext': 'mp4',
68	},
69	'params': {
70	'skip_download': 'Livestream',
71	},
72	}, {
73	'url': 'https://www.rtvcplay.co/en-vivo/radio-nacional',
74	'info_dict': {
75	'id': 'radio-nacional',
76	'title': r're:^Radio Nacional',
77	'description': 'md5:5de009bc6a9fa79d2a6cf0b73f977d53',
78	'thumbnail': r're:^https?://.*\.(?:jpg\|png)',
79	'live_status': 'is_live',
80	'ext': 'mp4',
81	},
82	'params': {
83	'skip_download': 'Livestream',
84	},
85	}, {
86	'url': 'https://www.rtvcplay.co/peliculas-ficcion/senoritas',
87	'md5': '1288ee6f6d1330d880f98bff2ed710a3',
88	'info_dict': {
89	'id': 'senoritas',
90	'title': 'Señoritas',
91	'description': 'md5:f095a2bb52cb6cf279daf6302f86fb32',
92	'thumbnail': r're:^https?://.*\.(?:jpg\|png)',
93	'ext': 'mp4',
94	},
95	}, {
96	'url': 'https://www.rtvcplay.co/competencias-basicas-ciudadanas-y-socioemocionales/profe-en-tu-casa/james-regresa-clases-28022022',
97	'md5': 'f040a7380a269ad633cf837384d5e9fc',
98	'info_dict': {
99	'id': 'james-regresa-clases-28022022',
100	'title': 'James regresa a clases - 28/02/2022',
101	'description': 'md5:c5dcdf757c7ab29305e8763c6007e675',
102	'ext': 'mp4',
103	},
104	}, {
105	'url': 'https://www.rtvcplay.co/peliculas-documentales/llinas-el-cerebro-y-el-universo',
106	'info_dict': {
107	'id': 'llinas-el-cerebro-y-el-universo',
108	'title': 'Llinás, el cerebro y el universo',
109	'description': 'md5:add875bf2309bb52b3e8b9b06116d9b0',
110	'thumbnail': r're:^https?://.*\.(?:jpg\|png)',
111	},
112	'playlist_mincount': 3,
113	}, {
114	'url': 'https://www.rtvcplay.co/competencias-basicas-ciudadanas-y-socioemocionales/profe-en-tu-casa',
115	'info_dict': {
116	'id': 'profe-en-tu-casa',
117	'title': 'Profe en tu casa',
118	'description': 'md5:47dbe20e263194413b1db2a2805a4f2e',
119	'thumbnail': r're:^https?://.*\.(?:jpg\|png)',
120	},
121	'playlist_mincount': 537,
122	}, {
123	'url': 'https://www.rtvcplay.co/series-al-oido/relato-de-un-naufrago-una-travesia-del-periodismo-a-la-literatura',
124	'info_dict': {
125	'id': 'relato-de-un-naufrago-una-travesia-del-periodismo-a-la-literatura',
126	'title': 'Relato de un náufrago: una travesía del periodismo a la literatura',
127	'description': 'md5:6da28fdca4a5a568ea47ef65ef775603',
128	'thumbnail': r're:^https?://.*\.(?:jpg\|png)',
129	},
130	'playlist_mincount': 5,
131	}, {
132	'url': 'https://www.rtvcplay.co/series-al-oido/diez-versiones',
133	'info_dict': {
134	'id': 'diez-versiones',
135	'title': 'Diez versiones',
136	'description': 'md5:997471ed971cb3fd8e41969457675306',
137	'thumbnail': r're:^https?://.*\.(?:jpg\|png)',
138	},
139	'playlist_mincount': 20,
140	}]
141
142	def _real_extract(self, url):
143	video_id, category = self._match_valid_url(url).group('id', 'category')
144	webpage = self._download_webpage(url, video_id)
145
146	hydration = self._search_json(
147	r'window\.__RTVCPLAY_STATE__\s*=', webpage, 'hydration',
148	video_id, transform_source=js_to_json)['content']['currentContent']
149
150	asset_id = traverse_obj(hydration, ('video', 'assetid'))
151	if asset_id:
152	hls_url = hydration['base_url_hls'].replace('[node:field_asset_id]', asset_id)
153	else:
154	hls_url = traverse_obj(hydration, ('channel', 'hls'))
155
156	metadata = traverse_obj(hydration, {
157	'title': 'title',
158	'description': 'description',
159	'thumbnail': ((('channel', 'image', 'logo'), ('resource', 'image', 'cover_desktop')), 'path'),
160	}, get_all=False)
161
162	# Probably it's a program's page
163	if not hls_url:
164	seasons = traverse_obj(
165	hydration, ('widgets', lambda _, y: y['type'] == 'seasonList', 'contents'),
166	get_all=False)
167	if not seasons:
168	podcast_episodes = hydration.get('audios')
169	if not podcast_episodes:
170	raise ExtractorError('Could not find asset_id nor program playlist nor podcast episodes')
171
172	return self.playlist_result([
173	self.url_result(episode['file'], url_transparent=True, **traverse_obj(episode, {
174	'title': 'title',
175	'description': ('description', {clean_html}),
176	'episode_number': ('chapter_number', {float_or_none}, {int_or_none}),
177	'season_number': ('season', {int_or_none}),
178	})) for episode in podcast_episodes], video_id, **metadata)
179
180	entries = [self.url_result(
181	urljoin(url, episode['slug']), url_transparent=True,
182	**traverse_obj(season, {
183	'season': 'title',
184	'season_number': ('season', {int_or_none}),
185	}), **traverse_obj(episode, {
186	'title': 'title',
187	'thumbnail': ('image', 'cover', 'path'),
188	'episode_number': ('chapter_number', {int_or_none}),
189	})) for season in seasons for episode in traverse_obj(season, ('contents', ...))]
190
191	return self.playlist_result(entries, video_id, **metadata)
192
193	formats, subtitles = self._extract_m3u8_formats_and_subtitles(hls_url, video_id, 'mp4')
194
195	return {
196	'id': video_id,
197	'formats': formats,
198	'subtitles': subtitles,
199	'is_live': category == 'en-vivo',
200	**metadata,
201	}
202
203
204	class RTVCPlayEmbedIE(RTVCPlayBaseIE):
205	_VALID_URL = RTVCPlayBaseIE._BASE_VALID_URL + r'/embed/(?P<id>[\w-]+)'
206
207	_TESTS = [{
208	'url': 'https://www.rtvcplay.co/embed/72b0e699-248b-4929-a4a8-3782702fa7f9',
209	'md5': 'ed529aeaee7aa2a72afe91ac7d1177a8',
210	'info_dict': {
211	'id': '72b0e699-248b-4929-a4a8-3782702fa7f9',
212	'title': 'Tráiler: Señoritas',
213	'thumbnail': r're:^https?://.*\.(?:jpg\|png)',
214	'ext': 'mp4',
215	}
216	}]
217
218	def _real_extract(self, url):
219	video_id = self._match_id(url)
220	webpage = self._download_webpage(url, video_id)
221
222	player_config = self._extract_player_config(webpage, video_id)
223	formats, subtitles = self._extract_formats_and_subtitles_player_config(player_config, video_id)
224
225	asset_id = traverse_obj(player_config, ('rtvcplay', 'assetid'))
226	metadata = {} if not asset_id else self._download_json(
227	f'https://cms.rtvcplay.co/api/v1/video/asset-id/{asset_id}', video_id, fatal=False)
228
229	return {
230	'id': video_id,
231	'formats': formats,
232	'subtitles': subtitles,
233	**traverse_obj(metadata, {
234	'title': 'title',
235	'description': 'description',
236	'thumbnail': ('image', ..., 'thumbnail', 'path'),
237	}, get_all=False)
238	}
239
240
241	class RTVCKalturaIE(RTVCPlayBaseIE):
242	_VALID_URL = r'https?://media\.rtvc\.gov\.co/kalturartvc/(?P<id>[\w-]+)'
243
244	_TESTS = [{
245	'url': 'https://media.rtvc.gov.co/kalturartvc/indexSC.html',
246	'info_dict': {
247	'id': 'indexSC',
248	'title': r're:^Señal Colombia',
249	'description': 'md5:799f16a401d97f40c33a2c6a3e2a507b',
250	'thumbnail': r're:^https?://.*\.(?:jpg\|png)',
251	'live_status': 'is_live',
252	'ext': 'mp4',
253	},
254	'params': {
255	'skip_download': 'Livestream',
256	},
257	}]
258
259	def _real_extract(self, url):
260	video_id = self._match_id(url)
261	webpage = self._download_webpage(url, video_id)
262
263	player_config = self._extract_player_config(webpage, video_id)
264	formats, subtitles = self._extract_formats_and_subtitles_player_config(player_config, video_id)
265
266	channel_id = traverse_obj(player_config, ('rtvcplay', 'channelId'))
267	metadata = {} if not channel_id else self._download_json(
268	f'https://cms.rtvcplay.co/api/v1/taxonomy_term/streaming/{channel_id}', video_id, fatal=False)
269
270	fmts, subs = self._extract_m3u8_formats_and_subtitles(
271	traverse_obj(metadata, ('channel', 'hls')), video_id, 'mp4', fatal=False)
272	formats.extend(fmts)
273	self._merge_subtitles(subs, target=subtitles)
274
275	return {
276	'id': video_id,
277	'formats': formats,
278	'subtitles': subtitles,
279	'is_live': True,
280	**traverse_obj(metadata, {
281	'title': 'title',
282	'description': 'description',
283	'thumbnail': ('channel', 'image', 'logo', 'path'),
284	})
285	}