2 from __future__ import unicode_literals
8 from .common import InfoExtractor
20 class LetvIE(InfoExtractor):
21 _VALID_URL = r'http://www\.letv\.com/ptv/vplay/(?P<id>\d+).html'
24 'url': 'http://www.letv.com/ptv/vplay/22005890.html',
25 'md5': 'cab23bd68d5a8db9be31c9a222c1e8df',
29 'title': '第87届奥斯卡颁奖礼完美落幕 《鸟人》成最大赢家',
30 'timestamp': 1424747397,
31 'upload_date': '20150224',
32 'description': 'md5:a9cb175fd753e2962176b7beca21a47c',
35 'url': 'http://www.letv.com/ptv/vplay/1415246.html',
40 'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda',
42 'expected_warnings': [
46 # http://www.letv.com/ptv/vplay/1118082.html
47 # This video is available only in Mainland China
51 return val >> n if val >= 0 else (val + 0x100000000) >> n
53 # ror() and calc_time_key() are reversed from a embedded swf file in KLetvPlayer.swf
54 def ror(self, param1, param2):
56 while _loc3_ < param2:
57 param1 = self.urshift(param1, 1) + ((param1 & 1) << 31)
61 def calc_time_key(self, param1):
63 _loc3_ = self.ror(param1, _loc2_ % 13)
64 _loc3_ = _loc3_ ^ _loc2_
65 _loc3_ = self.ror(_loc3_, _loc2_ % 17)
68 def _real_extract(self, url):
69 media_id = self._match_id(url)
70 page = self._download_webpage(url, media_id)
76 'tkey': self.calc_time_key(int(time.time())),
77 'domain': 'www.letv.com'
79 play_json = self._download_json(
80 'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params),
81 media_id, 'playJson data')
84 playstatus = play_json['playstatus']
85 if playstatus['status'] == 0:
86 flag = playstatus['flag']
88 msg = 'Country %s auth error' % playstatus['country']
90 msg = 'Generic error. flag = %d' % flag
91 raise ExtractorError(msg, expected=True)
93 playurl = play_json['playurl']
95 formats = ['350', '1000', '1300', '720p', '1080p']
96 dispatch = playurl['dispatch']
99 for format_id in formats:
100 if format_id in dispatch:
101 media_url = playurl['domain'][0] + dispatch[format_id][0]
103 # Mimic what flvxz.com do
104 url_parts = list(compat_urlparse.urlparse(media_url))
105 qs = dict(compat_urlparse.parse_qs(url_parts[4]))
112 url_parts[4] = compat_urllib_parse.urlencode(qs)
113 media_url = compat_urlparse.urlunparse(url_parts)
117 'ext': determine_ext(dispatch[format_id][1])
120 if format_id[-1:] == 'p':
121 url_info_dict['height'] = format_id[:-1]
123 urls.append(url_info_dict)
125 publish_time = parse_iso8601(self._html_search_regex(
126 r'发布时间 ([^<>]+) ', page, 'publish time', fatal=False),
127 delimiter=' ', timezone=datetime.timedelta(hours=8))
128 description = self._html_search_meta('description', page, fatal=False)
133 'title': playurl['title'],
134 'thumbnail': playurl['pic'],
135 'description': description,
136 'timestamp': publish_time,
140 class LetvTvIE(InfoExtractor):
141 _VALID_URL = r'http://www.letv.com/tv/(?P<id>\d+).html'
143 'url': 'http://www.letv.com/tv/46177.html',
147 'description': 'md5:395666ff41b44080396e59570dbac01c'
152 def _real_extract(self, url):
153 playlist_id = self._match_id(url)
154 page = self._download_webpage(url, playlist_id)
156 media_urls = list(set(re.findall(
157 r'http://www.letv.com/ptv/vplay/\d+.html', page)))
158 entries = [self.url_result(media_url, ie='Letv')
159 for media_url in media_urls]
161 title = self._html_search_meta('keywords', page,
162 fatal=False).split(',')[0]
163 description = self._html_search_meta('description', page, fatal=False)
165 return self.playlist_result(entries, playlist_id, playlist_title=title,
166 playlist_description=description)
169 class LetvPlaylistIE(LetvTvIE):
170 _VALID_URL = r'http://tv.letv.com/[a-z]+/(?P<id>[a-z]+)/index.s?html'
172 'url': 'http://tv.letv.com/izt/wuzetian/index.html',
176 'description': 'md5:e12499475ab3d50219e5bba00b3cb248'
178 # This playlist contains some extra videos other than the drama itself
179 'playlist_mincount': 96
181 'url': 'http://tv.letv.com/pzt/lswjzzjc/index.shtml',
184 # The title should be "劲舞青春", but I can't find a simple way to
185 # determine the playlist title
187 'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489'
189 'playlist_mincount': 7