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
|
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
dict_get,
ExtractorError,
int_or_none,
parse_duration,
try_get,
update_url_query,
)
class NaverBaseIE(InfoExtractor):
_CAPTION_EXT_RE = r'\.(?:ttml|vtt)'
def _extract_video_info(self, video_id, vid, key):
video_data = self._download_json(
'http://play.rmcnmv.naver.com/vod/play/v2.0/' + vid,
video_id, query={
'key': key,
})
meta = video_data['meta']
title = meta['subject']
formats = []
get_list = lambda x: try_get(video_data, lambda y: y[x + 's']['list'], list) or []
def extract_formats(streams, stream_type, query={}):
for stream in streams:
stream_url = stream.get('source')
if not stream_url:
continue
stream_url = update_url_query(stream_url, query)
encoding_option = stream.get('encodingOption', {})
bitrate = stream.get('bitrate', {})
formats.append({
'format_id': '%s_%s' % (stream.get('type') or stream_type, dict_get(encoding_option, ('name', 'id'))),
'url': stream_url,
'width': int_or_none(encoding_option.get('width')),
'height': int_or_none(encoding_option.get('height')),
'vbr': int_or_none(bitrate.get('video')),
'abr': int_or_none(bitrate.get('audio')),
'filesize': int_or_none(stream.get('size')),
'protocol': 'm3u8_native' if stream_type == 'HLS' else None,
})
extract_formats(get_list('video'), 'H264')
for stream_set in video_data.get('streams', []):
query = {}
for param in stream_set.get('keys', []):
query[param['name']] = param['value']
stream_type = stream_set.get('type')
videos = stream_set.get('videos')
if videos:
extract_formats(videos, stream_type, query)
elif stream_type == 'HLS':
stream_url = stream_set.get('source')
if not stream_url:
continue
formats.extend(self._extract_m3u8_formats(
update_url_query(stream_url, query), video_id,
'mp4', 'm3u8_native', m3u8_id=stream_type, fatal=False))
self._sort_formats(formats)
replace_ext = lambda x, y: re.sub(self._CAPTION_EXT_RE, '.' + y, x)
def get_subs(caption_url):
if re.search(self._CAPTION_EXT_RE, caption_url):
return [{
'url': replace_ext(caption_url, 'ttml'),
}, {
'url': replace_ext(caption_url, 'vtt'),
}]
else:
return [{'url': caption_url}]
automatic_captions = {}
subtitles = {}
for caption in get_list('caption'):
caption_url = caption.get('source')
if not caption_url:
continue
sub_dict = automatic_captions if caption.get('type') == 'auto' else subtitles
sub_dict.setdefault(dict_get(caption, ('locale', 'language')), []).extend(get_subs(caption_url))
user = meta.get('user', {})
return {
'id': video_id,
'title': title,
'formats': formats,
'subtitles': subtitles,
'automatic_captions': automatic_captions,
'thumbnail': try_get(meta, lambda x: x['cover']['source']),
'view_count': int_or_none(meta.get('count')),
'uploader_id': user.get('id'),
'uploader': user.get('name'),
'uploader_url': user.get('url'),
}
class NaverIE(NaverBaseIE):
_VALID_URL = r'https?://(?:m\.)?tv(?:cast)?\.naver\.com/(?:v|embed)/(?P<id>\d+)'
_GEO_BYPASS = False
_TESTS = [{
'url': 'http://tv.naver.com/v/81652',
'info_dict': {
'id': '81652',
'ext': 'mp4',
'title': '[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번',
'description': '메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.',
'timestamp': 1378200754,
'upload_date': '20130903',
'uploader': '메가스터디, 합격불변의 법칙',
'uploader_id': 'megastudy',
},
}, {
'url': 'http://tv.naver.com/v/395837',
'md5': '8a38e35354d26a17f73f4e90094febd3',
'info_dict': {
'id': '395837',
'ext': 'mp4',
'title': '9년이 지나도 아픈 기억, 전효성의 아버지',
'description': 'md5:eb6aca9d457b922e43860a2a2b1984d3',
'timestamp': 1432030253,
'upload_date': '20150519',
'uploader': '4가지쇼 시즌2',
'uploader_id': 'wrappinguser29',
},
'skip': 'Georestricted',
}, {
'url': 'http://tvcast.naver.com/v/81652',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
content = self._download_json(
'https://tv.naver.com/api/json/v/' + video_id,
video_id, headers=self.geo_verification_headers())
player_info_json = content.get('playerInfoJson') or {}
current_clip = player_info_json.get('currentClip') or {}
vid = current_clip.get('videoId')
in_key = current_clip.get('inKey')
if not vid or not in_key:
player_auth = try_get(player_info_json, lambda x: x['playerOption']['auth'])
if player_auth == 'notCountry':
self.raise_geo_restricted(countries=['KR'])
elif player_auth == 'notLogin':
self.raise_login_required()
raise ExtractorError('couldn\'t extract vid and key')
info = self._extract_video_info(video_id, vid, in_key)
info.update({
'description': clean_html(current_clip.get('description')),
'timestamp': int_or_none(current_clip.get('firstExposureTime'), 1000),
'duration': parse_duration(current_clip.get('displayPlayTime')),
'like_count': int_or_none(current_clip.get('recommendPoint')),
'age_limit': 19 if current_clip.get('adult') else None,
})
return info
class NaverLiveIE(InfoExtractor):
IE_NAME = 'Naver:live'
_VALID_URL = r'https?://(?:m\.)?tv(?:cast)?\.naver\.com/l/(?P<id>\d+)'
_GEO_BYPASS = False
_TESTS = [{
'url': 'https://tv.naver.com/l/52010',
'info_dict': {
'id': '52010',
'ext': 'm3u8',
'title': '[LIVE] 뉴스특보 : "수도권 거리두기, 2주간 2단계로 조정"',
'description': 'md5:df7f0c237a5ed5e786ce5c91efbeaab3',
'channel_id': 'NTV-ytnnews24-0',
'start_time': 1597026780000,
},
}, {
'url': 'https://tv.naver.com/l/51549',
'info_dict': {
'id': '51549',
'ext': 'm3u8',
'title': '연합뉴스TV - 코로나19 뉴스특보',
'description': 'md5:c655e82091bc21e413f549c0eaccc481',
'channel_id': 'NTV-yonhapnewstv-0',
'start_time': 1596406380000,
},
}, {
'url': 'https://tv.naver.com/l/54887',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
page = self._download_webpage(url, video_id, 'Downloading Page', 'Unable to download Page')
secure_url = self._search_regex(r'sApiF:\s+(?:"|\')([^"\']+)', page, 'secureurl')
info = self._extract_video_info(video_id, secure_url)
info.update({
'description': self._og_search_description(page)
})
return info
def _extract_video_info(self, video_id, url):
video_data = self._download_json(url, video_id, headers=self.geo_verification_headers())
meta = video_data.get('meta')
status = meta.get('status')
if status == 'CLOSED':
raise ExtractorError('Stream is offline.', expected=True)
elif status != 'OPENED':
raise ExtractorError('Unknown status %s' % status)
title = meta.get('title')
stream_list = video_data.get('streams')
if stream_list is None:
raise ExtractorError('Could not get stream data.', expected=True)
formats = []
for quality in stream_list:
if not quality.get('url'):
continue
prop = quality.get('property')
if prop.get('abr'): # This abr doesn't mean Average audio bitrate.
continue
formats.extend(self._extract_m3u8_formats(
quality.get('url'), video_id, 'm3u8',
m3u8_id=quality.get('qualityId'), live=True
))
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'formats': formats,
'channel_id': meta.get('channelId'),
'channel_url': meta.get('channelUrl'),
'thumbnail': meta.get('imgUrl'),
'start_time': meta.get('startTime'),
'categories': [meta.get('categoryId')],
'is_live': True
}
|
