2 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from ..compat import (
26 class LetvIE(InfoExtractor):
28 _VALID_URL = r'http://www\.letv\.com/ptv/vplay/(?P<id>\d+).html'
31 'url': 'http://www.letv.com/ptv/vplay/22005890.html',
32 'md5': 'edadcfe5406976f42f9f266057ee5e40',
36 'title': '第87届奥斯卡颁奖礼完美落幕 《鸟人》成最大赢家',
37 'description': 'md5:a9cb175fd753e2962176b7beca21a47c',
40 'hls_prefer_native': True,
43 'url': 'http://www.letv.com/ptv/vplay/1415246.html',
48 'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda',
51 'hls_prefer_native': True,
54 'note': 'This video is available only in Mainland China, thus a proxy is needed',
55 'url': 'http://www.letv.com/ptv/vplay/1118082.html',
56 'md5': '2424c74948a62e5f31988438979c5ad1',
61 'description': 'md5:7506a5eeb1722bb9d4068f85024e3986',
64 'hls_prefer_native': True,
66 'skip': 'Only available in China',
71 return val >> n if val >= 0 else (val + 0x100000000) >> n
73 # ror() and calc_time_key() are reversed from a embedded swf file in KLetvPlayer.swf
74 def ror(self, param1, param2):
76 while _loc3_ < param2:
77 param1 = self.urshift(param1, 1) + ((param1 & 1) << 31)
81 def calc_time_key(self, param1):
83 _loc3_ = self.ror(param1, _loc2_ % 13)
84 _loc3_ = _loc3_ ^ _loc2_
85 _loc3_ = self.ror(_loc3_, _loc2_ % 17)
88 # see M3U8Encryption class in KLetvPlayer.swf
90 def decrypt_m3u8(encrypted_data):
91 if encrypted_data[:5].decode('utf-8').lower() != 'vc_01':
93 encrypted_data = encrypted_data[5:]
97 b = compat_ord(encrypted_data[0])
98 _loc4_.extend([b // 16, b & 0x0f])
99 encrypted_data = encrypted_data[1:]
100 idx = len(_loc4_) - 11
101 _loc4_ = _loc4_[idx:] + _loc4_[:idx]
104 _loc7_.append(_loc4_[0] * 16 + _loc4_[1])
109 def _real_extract(self, url):
110 media_id = self._match_id(url)
111 page = self._download_webpage(url, media_id)
117 'tkey': self.calc_time_key(int(time.time())),
118 'domain': 'www.letv.com'
120 play_json_req = sanitized_Request(
121 'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
123 cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
124 if cn_verification_proxy:
125 play_json_req.add_header('Ytdl-request-proxy', cn_verification_proxy)
127 play_json = self._download_json(
129 media_id, 'Downloading playJson data')
132 playstatus = play_json['playstatus']
133 if playstatus['status'] == 0:
134 flag = playstatus['flag']
136 msg = 'Country %s auth error' % playstatus['country']
138 msg = 'Generic error. flag = %d' % flag
139 raise ExtractorError(msg, expected=True)
141 playurl = play_json['playurl']
143 formats = ['350', '1000', '1300', '720p', '1080p']
144 dispatch = playurl['dispatch']
147 for format_id in formats:
148 if format_id in dispatch:
149 media_url = playurl['domain'][0] + dispatch[format_id][0]
150 media_url += '&' + compat_urllib_parse.urlencode({
157 nodes_data = self._download_json(
159 'Download JSON metadata for format %s' % format_id)
161 req = self._request_webpage(
162 nodes_data['nodelist'][0]['location'], media_id,
163 note='Downloading m3u8 information for format %s' % format_id)
165 m3u8_data = self.decrypt_m3u8(req.read())
168 'url': encode_data_uri(m3u8_data, 'application/vnd.apple.mpegurl'),
169 'ext': determine_ext(dispatch[format_id][1]),
170 'format_id': format_id,
174 if format_id[-1:] == 'p':
175 url_info_dict['height'] = int_or_none(format_id[:-1])
177 urls.append(url_info_dict)
179 publish_time = parse_iso8601(self._html_search_regex(
180 r'发布时间 ([^<>]+) ', page, 'publish time', default=None),
181 delimiter=' ', timezone=datetime.timedelta(hours=8))
182 description = self._html_search_meta('description', page, fatal=False)
187 'title': playurl['title'],
188 'thumbnail': playurl['pic'],
189 'description': description,
190 'timestamp': publish_time,
194 class LetvTvIE(InfoExtractor):
195 _VALID_URL = r'http://www.letv.com/tv/(?P<id>\d+).html'
197 'url': 'http://www.letv.com/tv/46177.html',
201 'description': 'md5:395666ff41b44080396e59570dbac01c'
206 def _real_extract(self, url):
207 playlist_id = self._match_id(url)
208 page = self._download_webpage(url, playlist_id)
210 media_urls = list(set(re.findall(
211 r'http://www.letv.com/ptv/vplay/\d+.html', page)))
212 entries = [self.url_result(media_url, ie='Letv')
213 for media_url in media_urls]
215 title = self._html_search_meta('keywords', page,
216 fatal=False).split(',')[0]
217 description = self._html_search_meta('description', page, fatal=False)
219 return self.playlist_result(entries, playlist_id, playlist_title=title,
220 playlist_description=description)
223 class LetvPlaylistIE(LetvTvIE):
224 _VALID_URL = r'http://tv.letv.com/[a-z]+/(?P<id>[a-z]+)/index.s?html'
226 'url': 'http://tv.letv.com/izt/wuzetian/index.html',
230 'description': 'md5:e12499475ab3d50219e5bba00b3cb248'
232 # This playlist contains some extra videos other than the drama itself
233 'playlist_mincount': 96
235 'url': 'http://tv.letv.com/pzt/lswjzzjc/index.shtml',
238 # The title should be "劲舞青春", but I can't find a simple way to
239 # determine the playlist title
241 'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489'
243 'playlist_mincount': 7
247 class LetvCloudIE(InfoExtractor):
249 _VALID_URL = r'https?://yuntv\.letv\.com/bcloud.html\?.+'
252 'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=467623dedf',
253 'md5': '26450599afd64c513bc77030ad15db44',
255 'id': 'p7jnfw5hw9_467623dedf',
257 'title': 'Video p7jnfw5hw9_467623dedf',
260 'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=ec93197892&pu=2c7cd40209&auto_play=1&gpcflag=1&width=640&height=360',
262 'id': 'p7jnfw5hw9_ec93197892',
264 'title': 'Video p7jnfw5hw9_ec93197892',
267 'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=187060b6fd',
269 'id': 'p7jnfw5hw9_187060b6fd',
271 'title': 'Video p7jnfw5hw9_187060b6fd',
275 def _real_extract(self, url):
276 uu_mobj = re.search('uu=([\w]+)', url)
277 vu_mobj = re.search('vu=([\w]+)', url)
279 if not uu_mobj or not vu_mobj:
280 raise ExtractorError('Invalid URL: %s' % url, expected=True)
282 uu = uu_mobj.group(1)
283 vu = vu_mobj.group(1)
284 media_id = uu + '_' + vu
286 play_json_req = sanitized_Request(
287 'http://api.letvcloud.com/gpc.php?cf=html5&sign=signxxxxx&ver=2.2&format=json&' +
288 'uu=' + uu + '&vu=' + vu)
289 play_json = self._download_json(play_json_req, media_id, 'Downloading playJson data')
291 if not play_json.get('data'):
292 if play_json.get('message'):
293 raise ExtractorError('Letv cloud said: %s' % play_json['message'], expected=True)
294 elif play_json.get('code'):
295 raise ExtractorError('Letv cloud returned error %d' % play_json['code'], expected=True)
297 raise ExtractorError('Letv cloud returned an unknwon error')
300 return base64.b64decode(s.encode('utf-8')).decode('utf-8')
303 for media in play_json['data']['video_info']['media'].values():
304 play_url = media['play_url']
305 url = b64decode(play_url['main_url'])
306 decoded_url = b64decode(url_basename(url))
309 'ext': determine_ext(decoded_url),
310 'format_id': int_or_none(play_url.get('vtype')),
311 'format_note': str_or_none(play_url.get('definition')),
312 'width': int_or_none(play_url.get('vwidth')),
313 'height': int_or_none(play_url.get('vheight')),
315 self._sort_formats(formats)
319 'title': 'Video %s' % media_id,