aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/letv.py
blob: ff74b51412ab3f08b2e830bf24832ae702d2bf76 (plain)
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
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
# coding: utf-8
from __future__ import unicode_literals

import datetime
import re
import time
import base64

from .common import InfoExtractor
from ..compat import (
    compat_urllib_parse,
    compat_ord,
)
from ..utils import (
    determine_ext,
    ExtractorError,
    parse_iso8601,
    sanitized_Request,
    int_or_none,
    str_or_none,
    encode_data_uri,
)


class LetvIE(InfoExtractor):
    IE_DESC = '乐视网'
    _VALID_URL = r'http://www\.letv\.com/ptv/vplay/(?P<id>\d+).html'

    _TESTS = [{
        'url': 'http://www.letv.com/ptv/vplay/22005890.html',
        'md5': 'edadcfe5406976f42f9f266057ee5e40',
        'info_dict': {
            'id': '22005890',
            'ext': 'mp4',
            'title': '第87届奥斯卡颁奖礼完美落幕 《鸟人》成最大赢家',
            'description': 'md5:a9cb175fd753e2962176b7beca21a47c',
        },
        'params': {
            'hls_prefer_native': True,
        },
    }, {
        'url': 'http://www.letv.com/ptv/vplay/1415246.html',
        'info_dict': {
            'id': '1415246',
            'ext': 'mp4',
            'title': '美人天下01',
            'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda',
        },
        'params': {
            'hls_prefer_native': True,
        },
    }, {
        'note': 'This video is available only in Mainland China, thus a proxy is needed',
        'url': 'http://www.letv.com/ptv/vplay/1118082.html',
        'md5': '2424c74948a62e5f31988438979c5ad1',
        'info_dict': {
            'id': '1118082',
            'ext': 'mp4',
            'title': '与龙共舞 完整版',
            'description': 'md5:7506a5eeb1722bb9d4068f85024e3986',
        },
        'params': {
            'hls_prefer_native': True,
        },
        'skip': 'Only available in China',
    }]

    @staticmethod
    def urshift(val, n):
        return val >> n if val >= 0 else (val + 0x100000000) >> n

    # ror() and calc_time_key() are reversed from a embedded swf file in KLetvPlayer.swf
    def ror(self, param1, param2):
        _loc3_ = 0
        while _loc3_ < param2:
            param1 = self.urshift(param1, 1) + ((param1 & 1) << 31)
            _loc3_ += 1
        return param1

    def calc_time_key(self, param1):
        _loc2_ = 773625421
        _loc3_ = self.ror(param1, _loc2_ % 13)
        _loc3_ = _loc3_ ^ _loc2_
        _loc3_ = self.ror(_loc3_, _loc2_ % 17)
        return _loc3_

    # see M3U8Encryption class in KLetvPlayer.swf
    @staticmethod
    def decrypt_m3u8(encrypted_data):
        if encrypted_data[:5].decode('utf-8').lower() != 'vc_01':
            return encrypted_data
        encrypted_data = encrypted_data[5:]

        _loc4_ = bytearray()
        while encrypted_data:
            b = compat_ord(encrypted_data[0])
            _loc4_.extend([b // 16, b & 0x0f])
            encrypted_data = encrypted_data[1:]
        idx = len(_loc4_) - 11
        _loc4_ = _loc4_[idx:] + _loc4_[:idx]
        _loc7_ = bytearray()
        while _loc4_:
            _loc7_.append(_loc4_[0] * 16 + _loc4_[1])
            _loc4_ = _loc4_[2:]

        return bytes(_loc7_)

    def _real_extract(self, url):
        media_id = self._match_id(url)
        page = self._download_webpage(url, media_id)
        params = {
            'id': media_id,
            'platid': 1,
            'splatid': 101,
            'format': 1,
            'tkey': self.calc_time_key(int(time.time())),
            'domain': 'www.letv.com'
        }
        play_json_req = sanitized_Request(
            'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
        )
        cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
        if cn_verification_proxy:
            play_json_req.add_header('Ytdl-request-proxy', cn_verification_proxy)

        play_json = self._download_json(
            play_json_req,
            media_id, 'Downloading playJson data')

        # Check for errors
        playstatus = play_json['playstatus']
        if playstatus['status'] == 0:
            flag = playstatus['flag']
            if flag == 1:
                msg = 'Country %s auth error' % playstatus['country']
            else:
                msg = 'Generic error. flag = %d' % flag
            raise ExtractorError(msg, expected=True)

        playurl = play_json['playurl']

        formats = ['350', '1000', '1300', '720p', '1080p']
        dispatch = playurl['dispatch']

        urls = []
        for format_id in formats:
            if format_id in dispatch:
                media_url = playurl['domain'][0] + dispatch[format_id][0]
                media_url += '&' + compat_urllib_parse.urlencode({
                    'm3v': 1,
                    'format': 1,
                    'expect': 3,
                    'rateid': format_id,
                })

                nodes_data = self._download_json(
                    media_url, media_id,
                    'Download JSON metadata for format %s' % format_id)

                req = self._request_webpage(
                    nodes_data['nodelist'][0]['location'], media_id,
                    note='Downloading m3u8 information for format %s' % format_id)

                m3u8_data = self.decrypt_m3u8(req.read())

                url_info_dict = {
                    'url': encode_data_uri(m3u8_data, 'application/vnd.apple.mpegurl'),
                    'ext': determine_ext(dispatch[format_id][1]),
                    'format_id': format_id,
                    'protocol': 'm3u8',
                }

                if format_id[-1:] == 'p':
                    url_info_dict['height'] = int_or_none(format_id[:-1])

                urls.append(url_info_dict)

        publish_time = parse_iso8601(self._html_search_regex(
            r'发布时间&nbsp;([^<>]+) ', page, 'publish time', default=None),
            delimiter=' ', timezone=datetime.timedelta(hours=8))
        description = self._html_search_meta('description', page, fatal=False)

        return {
            'id': media_id,
            'formats': urls,
            'title': playurl['title'],
            'thumbnail': playurl['pic'],
            'description': description,
            'timestamp': publish_time,
        }


class LetvTvIE(InfoExtractor):
    _VALID_URL = r'http://www.letv.com/tv/(?P<id>\d+).html'
    _TESTS = [{
        'url': 'http://www.letv.com/tv/46177.html',
        'info_dict': {
            'id': '46177',
            'title': '美人天下',
            'description': 'md5:395666ff41b44080396e59570dbac01c'
        },
        'playlist_count': 35
    }]

    def _real_extract(self, url):
        playlist_id = self._match_id(url)
        page = self._download_webpage(url, playlist_id)

        media_urls = list(set(re.findall(
            r'http://www.letv.com/ptv/vplay/\d+.html', page)))
        entries = [self.url_result(media_url, ie='Letv')
                   for media_url in media_urls]

        title = self._html_search_meta('keywords', page,
                                       fatal=False).split(',')[0]
        description = self._html_search_meta('description', page, fatal=False)

        return self.playlist_result(entries, playlist_id, playlist_title=title,
                                    playlist_description=description)


class LetvPlaylistIE(LetvTvIE):
    _VALID_URL = r'http://tv.letv.com/[a-z]+/(?P<id>[a-z]+)/index.s?html'
    _TESTS = [{
        'url': 'http://tv.letv.com/izt/wuzetian/index.html',
        'info_dict': {
            'id': 'wuzetian',
            'title': '武媚娘传奇',
            'description': 'md5:e12499475ab3d50219e5bba00b3cb248'
        },
        # This playlist contains some extra videos other than the drama itself
        'playlist_mincount': 96
    }, {
        'url': 'http://tv.letv.com/pzt/lswjzzjc/index.shtml',
        'info_dict': {
            'id': 'lswjzzjc',
            # The title should be "劲舞青春", but I can't find a simple way to
            # determine the playlist title
            'title': '乐视午间自制剧场',
            'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489'
        },
        'playlist_mincount': 7
    }]


class LetvCloudIE(InfoExtractor):
    IE_DESC = '乐视云'
    _VALID_URL = r'https?://yuntv\.letv\.com/bcloud.html\?.+'

    _TESTS = [{
        'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=467623dedf',
        'md5': '26450599afd64c513bc77030ad15db44',
        'info_dict': {
            'id': 'p7jnfw5hw9_467623dedf',
            'ext': 'mp4',
            'title': 'p7jnfw5hw9_467623dedf',
        },
    }, {
        'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=ec93197892&pu=2c7cd40209&auto_play=1&gpcflag=1&width=640&height=360',
        'info_dict': {
            'id': 'p7jnfw5hw9_ec93197892',
            'ext': 'mp4',
            'title': 'p7jnfw5hw9_ec93197892',
        },
    }, {
        'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=187060b6fd',
        'info_dict': {
            'id': 'p7jnfw5hw9_187060b6fd',
            'ext': 'mp4',
            'title': 'p7jnfw5hw9_187060b6fd',
        },
    }]

    def _real_extract(self, url):
        uu_mobj = re.search('uu=([\w]+)', url)
        vu_mobj = re.search('vu=([\w]+)', url)

        if not uu_mobj or not vu_mobj:
            raise ExtractorError('Invalid URL: %s' % url, expected=True)

        uu = uu_mobj.group(1)
        vu = vu_mobj.group(1)
        media_id = uu + '_' + vu

        play_json_req = sanitized_Request(
            'http://api.letvcloud.com/gpc.php?cf=html5&sign=signxxxxx&ver=2.2&format=json&' +
            'uu=' + uu + '&vu=' + vu)
        play_json = self._download_json(play_json_req, media_id, 'Downloading playJson data')

        if not play_json.get('data'):
            if play_json.get('message'):
                raise ExtractorError('Letv cloud said: %s' % play_json['message'], expected=True)
            elif play_json.get('code'):
                raise ExtractorError('Letv cloud returned error %d' % play_json['code'], expected=True)
            else:
                raise ExtractorError('Letv cloud returned an unknwon error')

        formats = []
        for media in play_json['data']['video_info']['media'].values():
            play_url = media['play_url']
            formats.append({
                'url': base64.b64decode(play_url['main_url'].encode('utf-8')).decode('utf-8'),
                'ext': 'mp4',
                'format_id': int_or_none(play_url.get('vtype')),
                'format_note': str_or_none(play_url.get('definition')),
                'width': int_or_none(play_url.get('vwidth')),
                'height': int_or_none(play_url.get('vheight')),
            })
        self._sort_formats(formats)

        return {
            'id': media_id,
            'title': media_id,
            'formats': formats,
        }