2 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from ..compat import (
25 class LetvIE(InfoExtractor):
27 _VALID_URL = r'http://www\.letv\.com/ptv/vplay/(?P<id>\d+).html'
30 'url': 'http://www.letv.com/ptv/vplay/22005890.html',
31 'md5': 'edadcfe5406976f42f9f266057ee5e40',
35 'title': '第87届奥斯卡颁奖礼完美落幕 《鸟人》成最大赢家',
36 'description': 'md5:a9cb175fd753e2962176b7beca21a47c',
39 'hls_prefer_native': True,
42 'url': 'http://www.letv.com/ptv/vplay/1415246.html',
47 'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda',
50 'hls_prefer_native': True,
53 'note': 'This video is available only in Mainland China, thus a proxy is needed',
54 'url': 'http://www.letv.com/ptv/vplay/1118082.html',
55 'md5': '2424c74948a62e5f31988438979c5ad1',
60 'description': 'md5:7506a5eeb1722bb9d4068f85024e3986',
63 'hls_prefer_native': True,
65 'skip': 'Only available in China',
70 return val >> n if val >= 0 else (val + 0x100000000) >> n
72 # ror() and calc_time_key() are reversed from a embedded swf file in KLetvPlayer.swf
73 def ror(self, param1, param2):
75 while _loc3_ < param2:
76 param1 = self.urshift(param1, 1) + ((param1 & 1) << 31)
80 def calc_time_key(self, param1):
82 _loc3_ = self.ror(param1, _loc2_ % 13)
83 _loc3_ = _loc3_ ^ _loc2_
84 _loc3_ = self.ror(_loc3_, _loc2_ % 17)
87 # see M3U8Encryption class in KLetvPlayer.swf
89 def decrypt_m3u8(encrypted_data):
90 if encrypted_data[:5].decode('utf-8').lower() != 'vc_01':
92 encrypted_data = encrypted_data[5:]
96 b = compat_ord(encrypted_data[0])
97 _loc4_.extend([b // 16, b & 0x0f])
98 encrypted_data = encrypted_data[1:]
99 idx = len(_loc4_) - 11
100 _loc4_ = _loc4_[idx:] + _loc4_[:idx]
103 _loc7_.append(_loc4_[0] * 16 + _loc4_[1])
108 def _real_extract(self, url):
109 media_id = self._match_id(url)
110 page = self._download_webpage(url, media_id)
116 'tkey': self.calc_time_key(int(time.time())),
117 'domain': 'www.letv.com'
119 play_json_req = sanitized_Request(
120 'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
122 cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
123 if cn_verification_proxy:
124 play_json_req.add_header('Ytdl-request-proxy', cn_verification_proxy)
126 play_json = self._download_json(
128 media_id, 'Downloading playJson data')
131 playstatus = play_json['playstatus']
132 if playstatus['status'] == 0:
133 flag = playstatus['flag']
135 msg = 'Country %s auth error' % playstatus['country']
137 msg = 'Generic error. flag = %d' % flag
138 raise ExtractorError(msg, expected=True)
140 playurl = play_json['playurl']
142 formats = ['350', '1000', '1300', '720p', '1080p']
143 dispatch = playurl['dispatch']
146 for format_id in formats:
147 if format_id in dispatch:
148 media_url = playurl['domain'][0] + dispatch[format_id][0]
149 media_url += '&' + compat_urllib_parse.urlencode({
156 nodes_data = self._download_json(
158 'Download JSON metadata for format %s' % format_id)
160 req = self._request_webpage(
161 nodes_data['nodelist'][0]['location'], media_id,
162 note='Downloading m3u8 information for format %s' % format_id)
164 m3u8_data = self.decrypt_m3u8(req.read())
167 'url': encode_data_uri(m3u8_data, 'application/vnd.apple.mpegurl'),
168 'ext': determine_ext(dispatch[format_id][1]),
169 'format_id': format_id,
173 if format_id[-1:] == 'p':
174 url_info_dict['height'] = int_or_none(format_id[:-1])
176 urls.append(url_info_dict)
178 publish_time = parse_iso8601(self._html_search_regex(
179 r'发布时间 ([^<>]+) ', page, 'publish time', default=None),
180 delimiter=' ', timezone=datetime.timedelta(hours=8))
181 description = self._html_search_meta('description', page, fatal=False)
186 'title': playurl['title'],
187 'thumbnail': playurl['pic'],
188 'description': description,
189 'timestamp': publish_time,
193 class LetvTvIE(InfoExtractor):
194 _VALID_URL = r'http://www.letv.com/tv/(?P<id>\d+).html'
196 'url': 'http://www.letv.com/tv/46177.html',
200 'description': 'md5:395666ff41b44080396e59570dbac01c'
205 def _real_extract(self, url):
206 playlist_id = self._match_id(url)
207 page = self._download_webpage(url, playlist_id)
209 media_urls = list(set(re.findall(
210 r'http://www.letv.com/ptv/vplay/\d+.html', page)))
211 entries = [self.url_result(media_url, ie='Letv')
212 for media_url in media_urls]
214 title = self._html_search_meta('keywords', page,
215 fatal=False).split(',')[0]
216 description = self._html_search_meta('description', page, fatal=False)
218 return self.playlist_result(entries, playlist_id, playlist_title=title,
219 playlist_description=description)
222 class LetvPlaylistIE(LetvTvIE):
223 _VALID_URL = r'http://tv.letv.com/[a-z]+/(?P<id>[a-z]+)/index.s?html'
225 'url': 'http://tv.letv.com/izt/wuzetian/index.html',
229 'description': 'md5:e12499475ab3d50219e5bba00b3cb248'
231 # This playlist contains some extra videos other than the drama itself
232 'playlist_mincount': 96
234 'url': 'http://tv.letv.com/pzt/lswjzzjc/index.shtml',
237 # The title should be "劲舞青春", but I can't find a simple way to
238 # determine the playlist title
240 'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489'
242 'playlist_mincount': 7
246 class LetvCloudIE(InfoExtractor):
248 _VALID_URL = r'http://yuntv\.letv\.com/bcloud.html\?.*$'
251 'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=467623dedf',
252 'md5': '26450599afd64c513bc77030ad15db44',
254 'id': 'p7jnfw5hw9_467623dedf',
256 'title': 'p7jnfw5hw9_467623dedf',
259 'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=ec93197892&pu=2c7cd40209&auto_play=1&gpcflag=1&width=640&height=360',
261 'id': 'p7jnfw5hw9_ec93197892',
263 'title': 'p7jnfw5hw9_ec93197892',
266 'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=187060b6fd',
268 'id': 'p7jnfw5hw9_187060b6fd',
270 'title': 'p7jnfw5hw9_187060b6fd',
274 def _real_extract(self, url):
275 uu = re.search('uu=([\w]+)', url).group(1)
276 vu = re.search('vu=([\w]+)', url).group(1)
277 media_id = uu + '_' + vu
279 play_json_req = sanitized_Request(
280 'http://api.letvcloud.com/gpc.php?cf=html5&sign=signxxxxx&ver=2.2&format=json&' +
281 "uu=" + uu + "&vu=" + vu)
282 play_json = self._download_json(play_json_req, media_id, 'Downloading playJson data')
285 'url': base64.b64decode(media['play_url']['main_url'].encode('utf-8')).decode("utf-8"),
287 'format_id': int_or_none(media.get('play_url', {}).get('vtype')),
288 'format_note': str_or_none(media.get('play_url', {}).get('definition')),
289 'width': int_or_none(media.get('play_url', {}).get('vwidth')),
290 'height': int_or_none(media.get('play_url', {}).get('vheight')),
291 } for media in play_json['data']['video_info']['media'].values()]
292 self._sort_formats(formats)