2 from __future__ import unicode_literals
8 from .common import InfoExtractor
28 class DPlayIE(InfoExtractor):
29 _VALID_URL = r'https?://(?P<domain>www\.(?P<host>dplay\.(?P<country>dk|se|no)))/(?:video(?:er|s)/)?(?P<id>[^/]+/[^/?#]+)'
32 # non geo restricted, via secure api, unsigned download hls URL
33 'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/',
36 'display_id': 'nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet',
38 'title': 'Svensken lär sig njuta av livet',
39 'description': 'md5:d3819c9bccffd0fe458ca42451dd50d8',
41 'timestamp': 1365454320,
42 'upload_date': '20130408',
43 'creator': 'Kanal 5 (Home)',
44 'series': 'Nugammalt - 77 händelser som format Sverige',
50 # geo restricted, via secure api, unsigned download hls URL
51 'url': 'http://www.dplay.dk/mig-og-min-mor/season-6-episode-12/',
54 'display_id': 'mig-og-min-mor/season-6-episode-12',
56 'title': 'Episode 12',
57 'description': 'md5:9c86e51a93f8a4401fc9641ef9894c90',
59 'timestamp': 1429696800,
60 'upload_date': '20150422',
61 'creator': 'Kanal 4 (Home)',
62 'series': 'Mig og min mor',
68 # geo restricted, via direct unsigned hls URL
69 'url': 'http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/',
70 'only_matching': True,
73 'url': 'https://www.dplay.no/videoer/i-kongens-klr/sesong-1-episode-7',
76 'display_id': 'i-kongens-klr/sesong-1-episode-7',
79 'description': 'md5:e3e1411b2b9aebeea36a6ec5d50c60cf',
81 'timestamp': 1516726800,
82 'upload_date': '20180123',
83 'series': 'I kongens klær',
88 'format': 'bestvideo',
89 'skip_download': True,
93 'url': 'https://www.dplay.dk/videoer/singleliv/season-5-episode-3',
94 'only_matching': True,
96 'url': 'https://www.dplay.se/videos/sofias-anglar/sofias-anglar-1001',
97 'only_matching': True,
100 def _real_extract(self, url):
101 mobj = re.match(self._VALID_URL, url)
102 display_id = mobj.group('id')
103 domain = mobj.group('domain')
105 self._initialize_geo_bypass([mobj.group('country').upper()])
107 webpage = self._download_webpage(url, display_id)
109 video_id = self._search_regex(
110 r'data-video-id=["\'](\d+)', webpage, 'video id', default=None)
113 host = mobj.group('host')
114 disco_base = 'https://disco-api.%s' % host
116 '%s/token' % disco_base, display_id, 'Downloading token',
118 'realm': host.replace('.', ''),
120 video = self._download_json(
121 '%s/content/videos/%s' % (disco_base, display_id), display_id,
124 'x-disco-client': 'WEB:UNKNOWN:dplay-client:0.0.1',
128 video_id = video['data']['id']
129 info = video['data']['attributes']
132 for format_id, format_dict in self._download_json(
133 '%s/playback/videoPlaybackInfo/%s' % (disco_base, video_id),
134 display_id)['data']['attributes']['streaming'].items():
135 if not isinstance(format_dict, dict):
137 format_url = format_dict.get('url')
140 ext = determine_ext(format_url)
141 if format_id == 'dash' or ext == 'mpd':
142 formats.extend(self._extract_mpd_formats(
143 format_url, display_id, mpd_id='dash', fatal=False))
144 elif format_id == 'hls' or ext == 'm3u8':
145 formats.extend(self._extract_m3u8_formats(
146 format_url, display_id, 'mp4',
147 entry_protocol='m3u8_native', m3u8_id='hls',
152 'format_id': format_id,
154 self._sort_formats(formats)
158 included = video.get('included')
159 if isinstance(included, list):
160 show = next(e for e in included if e.get('type') == 'show')
162 show, lambda x: x['attributes']['name'], compat_str)
163 except StopIteration:
168 'display_id': display_id,
170 'description': info.get('description'),
171 'duration': float_or_none(
172 info.get('videoDuration'), scale=1000),
173 'timestamp': unified_timestamp(info.get('publishStart')),
175 'season_number': int_or_none(info.get('seasonNumber')),
176 'episode_number': int_or_none(info.get('episodeNumber')),
177 'age_limit': int_or_none(info.get('minimum_age')),
181 info = self._download_json(
182 'http://%s/api/v2/ajax/videos?video_id=%s' % (domain, video_id),
185 title = info['title']
187 PROTOCOLS = ('hls', 'hds')
190 def extract_formats(protocol, manifest_url):
191 if protocol == 'hls':
192 m3u8_formats = self._extract_m3u8_formats(
193 manifest_url, video_id, ext='mp4',
194 entry_protocol='m3u8_native', m3u8_id=protocol, fatal=False)
195 # Sometimes final URLs inside m3u8 are unsigned, let's fix this
196 # ourselves. Also fragments' URLs are only served signed for
198 query = compat_urlparse.parse_qs(compat_urlparse.urlparse(manifest_url).query)
199 for m3u8_format in m3u8_formats:
201 'url': update_url_query(m3u8_format['url'], query),
203 'User-Agent': USER_AGENTS['Safari'],
206 formats.extend(m3u8_formats)
207 elif protocol == 'hds':
208 formats.extend(self._extract_f4m_formats(
209 manifest_url + '&hdcore=3.8.0&plugin=flowplayer-3.8.0.0',
210 video_id, f4m_id=protocol, fatal=False))
212 domain_tld = domain.split('.')[-1]
213 if domain_tld in ('se', 'dk', 'no'):
214 for protocol in PROTOCOLS:
215 # Providing dsc-geo allows to bypass geo restriction in some cases
217 'secure.dplay.%s' % domain_tld, 'dsc-geo',
219 'countryCode': domain_tld.upper(),
220 'expiry': (time.time() + 20 * 60) * 1000,
222 stream = self._download_json(
223 'https://secure.dplay.%s/secure/api/v2/user/authorization/stream/%s?stream_type=%s'
224 % (domain_tld, video_id, protocol), video_id,
225 'Downloading %s stream JSON' % protocol, fatal=False)
226 if stream and stream.get(protocol):
227 extract_formats(protocol, stream[protocol])
229 # The last resort is to try direct unsigned hls/hds URLs from info dictionary.
230 # Sometimes this does work even when secure API with dsc-geo has failed (e.g.
231 # http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/).
233 for protocol in PROTOCOLS:
234 if info.get(protocol):
235 extract_formats(protocol, info[protocol])
237 self._sort_formats(formats)
240 for lang in ('se', 'sv', 'da', 'nl', 'no'):
241 for format_id in ('web_vtt', 'vtt', 'srt'):
242 subtitle_url = info.get('subtitles_%s_%s' % (lang, format_id))
244 subtitles.setdefault(lang, []).append({'url': subtitle_url})
248 'display_id': display_id,
250 'description': info.get('video_metadata_longDescription'),
251 'duration': int_or_none(info.get('video_metadata_length'), scale=1000),
252 'timestamp': int_or_none(info.get('video_publish_date')),
253 'creator': info.get('video_metadata_homeChannel'),
254 'series': info.get('video_metadata_show'),
255 'season_number': int_or_none(info.get('season')),
256 'episode_number': int_or_none(info.get('episode')),
257 'age_limit': int_or_none(info.get('minimum_age')),
259 'subtitles': subtitles,
263 class DPlayItIE(InfoExtractor):
264 _VALID_URL = r'https?://it\.dplay\.com/[^/]+/[^/]+/(?P<id>[^/?#]+)'
265 _GEO_COUNTRIES = ['IT']
267 'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/',
268 'md5': '2b808ffb00fc47b884a172ca5d13053c',
271 'display_id': 'luigi-di-maio-la-psicosi-di-stanislawskij',
273 'title': 'Biografie imbarazzanti: Luigi Di Maio: la psicosi di Stanislawskij',
274 'description': 'md5:3c7a4303aef85868f867a26f5cc14813',
275 'thumbnail': r're:^https?://.*\.jpe?g',
276 'upload_date': '20160524',
277 'series': 'Biografie imbarazzanti',
279 'episode': 'Luigi Di Maio: la psicosi di Stanislawskij',
284 def _real_extract(self, url):
285 display_id = self._match_id(url)
287 webpage = self._download_webpage(url, display_id)
289 title = remove_end(self._og_search_title(webpage), ' | Dplay')
293 info = self._search_regex(
294 r'playback_json\s*:\s*JSON\.parse\s*\(\s*("(?:\\.|[^"\\])+?")',
295 webpage, 'playback JSON', default=None)
298 info = self._parse_json(info, display_id, fatal=False)
302 video_id = try_get(info, lambda x: x['data']['id'])
305 info_url = self._search_regex(
306 r'url\s*[:=]\s*["\']((?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)',
309 video_id = info_url.rpartition('/')[-1]
312 info = self._download_json(
313 info_url, display_id, headers={
314 'Authorization': 'Bearer %s' % self._get_cookies(url).get(
315 'dplayit_token').value,
318 except ExtractorError as e:
319 if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403):
320 info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
321 error = info['errors'][0]
322 if error.get('code') == 'access.denied.geoblocked':
323 self.raise_geo_restricted(
324 msg=error.get('detail'), countries=self._GEO_COUNTRIES)
325 raise ExtractorError(info['errors'][0]['detail'], expected=True)
328 hls_url = info['data']['attributes']['streaming']['hls']['url']
330 formats = self._extract_m3u8_formats(
331 hls_url, display_id, ext='mp4', entry_protocol='m3u8_native',
334 series = self._html_search_regex(
335 r'(?s)<h1[^>]+class=["\'].*?\bshow_title\b.*?["\'][^>]*>(.+?)</h1>',
336 webpage, 'series', fatal=False)
337 episode = self._search_regex(
338 r'<p[^>]+class=["\'].*?\bdesc_ep\b.*?["\'][^>]*>\s*<br/>\s*<b>([^<]+)',
339 webpage, 'episode', fatal=False)
342 r'(?s)<span[^>]+class=["\']dates["\'][^>]*>.+?\bS\.(?P<season_number>\d+)\s+E\.(?P<episode_number>\d+)\s*-\s*(?P<upload_date>\d{2}/\d{2}/\d{4})',
345 season_number = int(mobj.group('season_number'))
346 episode_number = int(mobj.group('episode_number'))
347 upload_date = unified_strdate(mobj.group('upload_date'))
349 season_number = episode_number = upload_date = None
352 'id': compat_str(video_id or display_id),
353 'display_id': display_id,
355 'description': self._og_search_description(webpage),
356 'thumbnail': self._og_search_thumbnail(webpage),
358 'season_number': season_number,
360 'episode_number': episode_number,
361 'upload_date': upload_date,