2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
8 compat_urllib_parse_unquote
,
9 compat_urllib_parse_urlparse
,
22 class CeskaTelevizeIE(InfoExtractor
):
23 _VALID_URL
= r
'https?://(?:www\.)?ceskatelevize\.cz/ivysilani/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
25 'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
27 'id': '61924494877246241',
29 'title': 'Hyde Park Civilizace: Život v Grónsku',
30 'description': 'md5:3fec8f6bb497be5cdb0c9e8781076626',
31 'thumbnail': r
're:^https?://.*\.jpg',
36 'skip_download': True,
39 'url': 'http://www.ceskatelevize.cz/ivysilani/10441294653-hyde-park-civilizace/215411058090502/bonus/20641-bonus-01-en',
41 'id': '61924494877028507',
43 'title': 'Hyde Park Civilizace: Bonus 01 - En',
44 'description': 'English Subtittles',
45 'thumbnail': r
're:^https?://.*\.jpg',
50 'skip_download': True,
54 'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/',
58 'title': r
're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
63 'skip_download': True,
65 'skip': 'Georestricted to Czech Republic',
67 'url': 'http://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php?hash=d6a3e1370d2e4fa76296b90bad4dfc19673b641e&IDEC=217 562 22150/0004&channelID=1&width=100%25',
68 'only_matching': True,
71 def _real_extract(self
, url
):
72 playlist_id
= self
._match
_id
(url
)
74 webpage
= self
._download
_webpage
(url
, playlist_id
)
76 NOT_AVAILABLE_STRING
= 'This content is not available at your territory due to limited copyright.'
77 if '%s</p>' % NOT_AVAILABLE_STRING
in webpage
:
78 raise ExtractorError(NOT_AVAILABLE_STRING
, expected
=True)
83 playlist
= self
._parse
_json
(
85 r
'getPlaylistUrl\(\[({.+?})\]', webpage
, 'playlist',
86 default
='{}'), playlist_id
)
88 type_
= playlist
.get('type')
89 episode_id
= playlist
.get('id')
92 type_
= self
._html
_search
_regex
(
93 r
'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],',
96 episode_id
= self
._html
_search
_regex
(
97 r
'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],',
98 webpage
, 'episode_id')
101 'playlist[0][type]': type_
,
102 'playlist[0][id]': episode_id
,
103 'requestUrl': compat_urllib_parse_urlparse(url
).path
,
104 'requestSource': 'iVysilani',
109 for user_agent
in (None, USER_AGENTS
['Safari']):
110 req
= sanitized_Request(
111 'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
112 data
=urlencode_postdata(data
))
114 req
.add_header('Content-type', 'application/x-www-form-urlencoded')
115 req
.add_header('x-addr', '127.0.0.1')
116 req
.add_header('X-Requested-With', 'XMLHttpRequest')
118 req
.add_header('User-Agent', user_agent
)
119 req
.add_header('Referer', url
)
121 playlistpage
= self
._download
_json
(req
, playlist_id
, fatal
=False)
126 playlist_url
= playlistpage
['url']
127 if playlist_url
== 'error_region':
128 raise ExtractorError(NOT_AVAILABLE_STRING
, expected
=True)
130 req
= sanitized_Request(compat_urllib_parse_unquote(playlist_url
))
131 req
.add_header('Referer', url
)
133 playlist_title
= self
._og
_search
_title
(webpage
, default
=None)
134 playlist_description
= self
._og
_search
_description
(webpage
, default
=None)
136 playlist
= self
._download
_json
(req
, playlist_id
, fatal
=False)
140 playlist
= playlist
.get('playlist')
141 if not isinstance(playlist
, list):
144 playlist_len
= len(playlist
)
146 for num
, item
in enumerate(playlist
):
147 is_live
= item
.get('type') == 'LIVE'
149 for format_id
, stream_url
in item
.get('streamUrls', {}).items():
150 if 'playerType=flash' in stream_url
:
151 stream_formats
= self
._extract
_m
3u8_formats
(
152 stream_url
, playlist_id
, 'mp4', 'm3u8_native',
153 m3u8_id
='hls-%s' % format_id
, fatal
=False)
155 stream_formats
= self
._extract
_mpd
_formats
(
156 stream_url
, playlist_id
,
157 mpd_id
='dash-%s' % format_id
, fatal
=False)
158 # See https://github.com/rg3/youtube-dl/issues/12119#issuecomment-280037031
159 if format_id
== 'audioDescription':
160 for f
in stream_formats
:
161 f
['source_preference'] = -10
162 formats
.extend(stream_formats
)
164 if user_agent
and len(entries
) == playlist_len
:
165 entries
[num
]['formats'].extend(formats
)
168 item_id
= item
.get('id') or item
['assetId']
169 title
= item
['title']
171 duration
= float_or_none(item
.get('duration'))
172 thumbnail
= item
.get('previewImageUrl')
175 if item
.get('type') == 'VOD':
176 subs
= item
.get('subtitles')
178 subtitles
= self
.extract_subtitles(episode_id
, subs
)
180 if playlist_len
== 1:
181 final_title
= playlist_title
or title
183 final_title
= self
._live
_title
(final_title
)
185 final_title
= '%s (%s)' % (playlist_title
, title
)
189 'title': final_title
,
190 'description': playlist_description
if playlist_len
== 1 else None,
191 'thumbnail': thumbnail
,
192 'duration': duration
,
194 'subtitles': subtitles
,
199 self
._sort
_formats
(e
['formats'])
201 return self
.playlist_result(entries
, playlist_id
, playlist_title
, playlist_description
)
203 def _get_subtitles(self
, episode_id
, subs
):
204 original_subtitles
= self
._download
_webpage
(
205 subs
[0]['url'], episode_id
, 'Downloading subtitles')
206 srt_subs
= self
._fix
_subtitles
(original_subtitles
)
215 def _fix_subtitles(subtitles
):
216 """ Convert millisecond-based subtitles to SRT """
218 def _msectotimecode(msec
):
219 """ Helper utility to convert milliseconds to timecode """
221 for divider
in [1000, 60, 60, 100]:
222 components
.append(msec
% divider
)
224 return '{3:02}:{2:02}:{1:02},{0:03}'.format(*components
)
226 def _fix_subtitle(subtitle
):
227 for line
in subtitle
.splitlines():
228 m
= re
.match(r
'^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$', line
)
231 start
, stop
= (_msectotimecode(int(t
)) for t
in m
.groups()[1:])
232 yield '{0} --> {1}'.format(start
, stop
)
236 return '\r\n'.join(_fix_subtitle(subtitles
))
239 class CeskaTelevizePoradyIE(InfoExtractor
):
240 _VALID_URL
= r
'https?://(?:www\.)?ceskatelevize\.cz/porady/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
242 # video with 18+ caution trailer
243 'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
245 'id': '215562210900007-bogotart',
246 'title': 'Queer: Bogotart',
247 'description': 'Alternativní průvodce současným queer světem',
251 'id': '61924494876844842',
253 'title': 'Queer: Bogotart (Varování 18+)',
258 'id': '61924494877068022',
260 'title': 'Queer: Bogotart (Queer)',
261 'thumbnail': r
're:^https?://.*\.jpg',
267 'skip_download': True,
271 'url': 'http://www.ceskatelevize.cz/porady/10614999031-neviditelni/21251212048/',
272 'only_matching': True,
275 def _real_extract(self
, url
):
276 video_id
= self
._match
_id
(url
)
278 webpage
= self
._download
_webpage
(url
, video_id
)
280 data_url
= update_url_query(unescapeHTML(self
._search
_regex
(
281 (r
'<span[^>]*\bdata-url=(["\'])(?P
<url
>(?
:(?
!\
1).)+)\
1',
282 r'<iframe
[^
>]+\bsrc
=(["\'])(?P<url>(?:https?:)?//(?:www\.)?ceskatelevize\.cz/ivysilani/embed/iFramePlayer\.php.*?)\1'),
283 webpage, 'iframe player url', group='url')), query={
287 return self.url_result(data_url, ie=CeskaTelevizeIE.ie_key())