1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
|
import re
import urllib.parse
from .common import InfoExtractor
from ..networking import Request
from ..utils import (
ExtractorError,
float_or_none,
str_or_none,
traverse_obj,
urlencode_postdata,
)
USER_AGENTS = {
'Safari': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27',
}
class CeskaTelevizeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(?:ivysilani|porady|zive)/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
_TESTS = [{
'url': 'http://www.ceskatelevize.cz/ivysilani/10441294653-hyde-park-civilizace/215411058090502/bonus/20641-bonus-01-en',
'info_dict': {
'id': '61924494877028507',
'ext': 'mp4',
'title': 'Bonus 01 - En - Hyde Park Civilizace',
'description': 'English Subtittles',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 81.3,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
# live stream
'url': 'http://www.ceskatelevize.cz/zive/ct1/',
'info_dict': {
'id': '102',
'ext': 'mp4',
'title': r'ČT1 - živé vysílání online',
'description': 'Sledujte živé vysílání kanálu ČT1 online. Vybírat si můžete i z dalších kanálů České televize na kterémkoli z vašich zařízení.',
'is_live': True,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
# another
'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/',
'only_matching': True,
'info_dict': {
'id': '402',
'ext': 'mp4',
'title': r're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'is_live': True,
},
# 'skip': 'Georestricted to Czech Republic',
}, {
'url': 'http://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php?hash=d6a3e1370d2e4fa76296b90bad4dfc19673b641e&IDEC=217 562 22150/0004&channelID=1&width=100%25',
'only_matching': True,
}, {
# video with 18+ caution trailer
'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
'info_dict': {
'id': '215562210900007-bogotart',
'title': 'Bogotart - Queer',
'description': 'Hlavní město Kolumbie v doprovodu queer umělců. Vroucí svět plný vášně, sebevědomí, ale i násilí a bolesti',
},
'playlist': [{
'info_dict': {
'id': '61924494877311053',
'ext': 'mp4',
'title': 'Bogotart - Queer (Varování 18+)',
'duration': 11.9,
},
}, {
'info_dict': {
'id': '61924494877068022',
'ext': 'mp4',
'title': 'Bogotart - Queer (Queer)',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 1558.3,
},
}],
'params': {
# m3u8 download
'skip_download': True,
},
}, {
# iframe embed
'url': 'http://www.ceskatelevize.cz/porady/10614999031-neviditelni/21251212048/',
'only_matching': True,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage, urlh = self._download_webpage_handle(url, playlist_id)
parsed_url = urllib.parse.urlparse(urlh.url)
site_name = self._og_search_property('site_name', webpage, fatal=False, default='Česká televize')
playlist_title = self._og_search_title(webpage, default=None)
if site_name and playlist_title:
playlist_title = re.split(rf'\s*[—|]\s*{site_name}', playlist_title, maxsplit=1)[0]
playlist_description = self._og_search_description(webpage, default=None)
if playlist_description:
playlist_description = playlist_description.replace('\xa0', ' ')
type_ = 'IDEC'
if re.search(r'(^/porady|/zive)/', parsed_url.path):
next_data = self._search_nextjs_data(webpage, playlist_id)
if '/zive/' in parsed_url.path:
idec = traverse_obj(next_data, ('props', 'pageProps', 'data', 'liveBroadcast', 'current', 'idec'), get_all=False)
else:
idec = traverse_obj(next_data, ('props', 'pageProps', 'data', ('show', 'mediaMeta'), 'idec'), get_all=False)
if not idec:
idec = traverse_obj(next_data, ('props', 'pageProps', 'data', 'videobonusDetail', 'bonusId'), get_all=False)
if idec:
type_ = 'bonus'
if not idec:
raise ExtractorError('Failed to find IDEC id')
iframe_hash = self._download_webpage(
'https://www.ceskatelevize.cz/v-api/iframe-hash/',
playlist_id, note='Getting IFRAME hash')
query = {'hash': iframe_hash, 'origin': 'iVysilani', 'autoStart': 'true', type_: idec}
webpage = self._download_webpage(
'https://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php',
playlist_id, note='Downloading player', query=query)
NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
if f'{NOT_AVAILABLE_STRING}</p>' in webpage:
self.raise_geo_restricted(NOT_AVAILABLE_STRING)
if any(not_found in webpage for not_found in ('Neplatný parametr pro videopřehrávač', 'IDEC nebyl nalezen')):
raise ExtractorError('no video with IDEC available', video_id=idec, expected=True)
type_ = None
episode_id = None
playlist = self._parse_json(
self._search_regex(
r'getPlaylistUrl\(\[({.+?})\]', webpage, 'playlist',
default='{}'), playlist_id)
if playlist:
type_ = playlist.get('type')
episode_id = playlist.get('id')
if not type_:
type_ = self._html_search_regex(
r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],',
webpage, 'type')
if not episode_id:
episode_id = self._html_search_regex(
r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],',
webpage, 'episode_id')
data = {
'playlist[0][type]': type_,
'playlist[0][id]': episode_id,
'requestUrl': parsed_url.path,
'requestSource': 'iVysilani',
}
entries = []
for user_agent in (None, USER_AGENTS['Safari']):
req = Request(
'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist/',
data=urlencode_postdata(data))
req.headers['Content-type'] = 'application/x-www-form-urlencoded'
req.headers['x-addr'] = '127.0.0.1'
req.headers['X-Requested-With'] = 'XMLHttpRequest'
if user_agent:
req.headers['User-Agent'] = user_agent
req.headers['Referer'] = url
playlistpage = self._download_json(req, playlist_id, fatal=False)
if not playlistpage:
continue
playlist_url = playlistpage['url']
if playlist_url == 'error_region':
raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
req = Request(urllib.parse.unquote(playlist_url))
req.headers['Referer'] = url
playlist = self._download_json(req, playlist_id, fatal=False)
if not playlist:
continue
playlist = playlist.get('playlist')
if not isinstance(playlist, list):
continue
playlist_len = len(playlist)
for num, item in enumerate(playlist):
is_live = item.get('type') == 'LIVE'
formats = []
for format_id, stream_url in item.get('streamUrls', {}).items():
if 'playerType=flash' in stream_url:
stream_formats = self._extract_m3u8_formats(
stream_url, playlist_id, 'mp4', 'm3u8_native',
m3u8_id=f'hls-{format_id}', fatal=False)
else:
stream_formats = self._extract_mpd_formats(
stream_url, playlist_id,
mpd_id=f'dash-{format_id}', fatal=False)
if 'drmOnly=true' in stream_url:
for f in stream_formats:
f['has_drm'] = True
# See https://github.com/ytdl-org/youtube-dl/issues/12119#issuecomment-280037031
if format_id == 'audioDescription':
for f in stream_formats:
f['source_preference'] = -10
formats.extend(stream_formats)
if user_agent and len(entries) == playlist_len:
entries[num]['formats'].extend(formats)
continue
item_id = str_or_none(item.get('id') or item['assetId'])
title = item['title']
duration = float_or_none(item.get('duration'))
thumbnail = item.get('previewImageUrl')
subtitles = {}
if item.get('type') == 'VOD':
subs = item.get('subtitles')
if subs:
subtitles = self.extract_subtitles(episode_id, subs)
if playlist_len == 1:
final_title = playlist_title or title
else:
final_title = f'{playlist_title} ({title})'
entries.append({
'id': item_id,
'title': final_title,
'description': playlist_description if playlist_len == 1 else None,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
'subtitles': subtitles,
'is_live': is_live,
})
if len(entries) == 1:
return entries[0]
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
def _get_subtitles(self, episode_id, subs):
original_subtitles = self._download_webpage(
subs[0]['url'], episode_id, 'Downloading subtitles')
srt_subs = self._fix_subtitles(original_subtitles)
return {
'cs': [{
'ext': 'srt',
'data': srt_subs,
}],
}
@staticmethod
def _fix_subtitles(subtitles):
""" Convert millisecond-based subtitles to SRT """
def _msectotimecode(msec):
""" Helper utility to convert milliseconds to timecode """
components = []
for divider in [1000, 60, 60, 100]:
components.append(msec % divider)
msec //= divider
return '{3:02}:{2:02}:{1:02},{0:03}'.format(*components)
def _fix_subtitle(subtitle):
for line in subtitle.splitlines():
m = re.match(r'^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$', line)
if m:
yield m.group(1)
start, stop = (_msectotimecode(int(t)) for t in m.groups()[1:])
yield f'{start} --> {stop}'
else:
yield line
return '\r\n'.join(_fix_subtitle(subtitles))
|
