summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/leeco.py
blob: 5d61a607f7cf30abae973276e3f13b5db5cac9db (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
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
import datetime as dt
import hashlib
import re
import time

from .common import InfoExtractor
from ..compat import (
    compat_b64decode,
    compat_ord,
    compat_str,
    compat_urllib_parse_urlencode,
)
from ..utils import (
    determine_ext,
    encode_data_uri,
    ExtractorError,
    int_or_none,
    orderedSet,
    parse_iso8601,
    str_or_none,
    url_basename,
    urshift,
)


class LeIE(InfoExtractor):
    IE_DESC = '乐视网'
    _VALID_URL = r'https?://(?:www\.le\.com/ptv/vplay|(?:sports\.le|(?:www\.)?lesports)\.com/(?:match|video))/(?P<id>\d+)\.html'
    _GEO_COUNTRIES = ['CN']
    _URL_TEMPLATE = 'http://www.le.com/ptv/vplay/%s.html'

    _TESTS = [{
        'url': 'http://www.le.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.le.com/ptv/vplay/1415246.html',
        'info_dict': {
            'id': '1415246',
            'ext': 'mp4',
            'title': '美人天下01',
            'description': 'md5:28942e650e82ed4fcc8e4de919ee854d',
        },
        'params': {
            'hls_prefer_native': True,
        },
    }, {
        'note': 'This video is available only in Mainland China, thus a proxy is needed',
        'url': 'http://www.le.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,
        },
    }, {
        'url': 'http://sports.le.com/video/25737697.html',
        'only_matching': True,
    }, {
        'url': 'http://www.lesports.com/match/1023203003.html',
        'only_matching': True,
    }, {
        'url': 'http://sports.le.com/match/1023203003.html',
        'only_matching': True,
    }]

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

    def calc_time_key(self, param1):
        _loc2_ = 185025305
        return self.ror(param1, _loc2_ % 17) ^ _loc2_

    # 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(2 * len(encrypted_data))
        for idx, val in enumerate(encrypted_data):
            b = compat_ord(val)
            _loc4_[2 * idx] = b // 16
            _loc4_[2 * idx + 1] = b % 16
        idx = len(_loc4_) - 11
        _loc4_ = _loc4_[idx:] + _loc4_[:idx]
        _loc7_ = bytearray(len(encrypted_data))
        for i in range(len(encrypted_data)):
            _loc7_[i] = _loc4_[2 * i] * 16 + _loc4_[2 * i + 1]

        return bytes(_loc7_)

    def _check_errors(self, play_json):
        # Check for errors
        playstatus = play_json['msgs']['playstatus']
        if playstatus['status'] == 0:
            flag = playstatus['flag']
            if flag == 1:
                self.raise_geo_restricted()
            else:
                raise ExtractorError('Generic error. flag = %d' % flag, expected=True)

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

        play_json_flash = self._download_json(
            'http://player-pc.le.com/mms/out/video/playJson',
            media_id, 'Downloading flash playJson data', query={
                'id': media_id,
                'platid': 1,
                'splatid': 105,
                'format': 1,
                'source': 1000,
                'tkey': self.calc_time_key(int(time.time())),
                'domain': 'www.le.com',
                'region': 'cn',
            },
            headers=self.geo_verification_headers())
        self._check_errors(play_json_flash)

        def get_flash_urls(media_url, format_id):
            nodes_data = self._download_json(
                media_url, media_id,
                'Download JSON metadata for format %s' % format_id,
                query={
                    'm3v': 1,
                    'format': 1,
                    'expect': 3,
                    'tss': 'ios',
                })

            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())

            return {
                'hls': encode_data_uri(m3u8_data, 'application/vnd.apple.mpegurl'),
            }

        extracted_formats = []
        formats = []
        playurl = play_json_flash['msgs']['playurl']
        play_domain = playurl['domain'][0]

        for format_id, format_data in playurl.get('dispatch', []).items():
            if format_id in extracted_formats:
                continue
            extracted_formats.append(format_id)

            media_url = play_domain + format_data[0]
            for protocol, format_url in get_flash_urls(media_url, format_id).items():
                f = {
                    'url': format_url,
                    'ext': determine_ext(format_data[1]),
                    'format_id': '%s-%s' % (protocol, format_id),
                    'protocol': 'm3u8_native' if protocol == 'hls' else 'http',
                    'quality': int_or_none(format_id),
                }

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

                formats.append(f)

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

        return {
            'id': media_id,
            'formats': formats,
            'title': playurl['title'],
            'thumbnail': playurl['pic'],
            'description': description,
            'timestamp': publish_time,
            '_format_sort_fields': ('res', 'quality'),
        }


class LePlaylistIE(InfoExtractor):
    _VALID_URL = r'https?://[a-z]+\.le\.com/(?!video)[a-z]+/(?P<id>[a-z0-9_]+)'

    _TESTS = [{
        'url': 'http://www.le.com/tv/46177.html',
        'info_dict': {
            'id': '46177',
            'title': '美人天下',
            'description': 'md5:395666ff41b44080396e59570dbac01c'
        },
        'playlist_count': 35
    }, {
        'url': 'http://tv.le.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.le.com/pzt/lswjzzjc/index.shtml',
        # This series is moved to http://www.le.com/tv/10005297.html
        'only_matching': True,
    }, {
        'url': 'http://www.le.com/comic/92063.html',
        'only_matching': True,
    }, {
        'url': 'http://list.le.com/listn/c1009_sc532002_d2_p1_o1.html',
        'only_matching': True,
    }]

    @classmethod
    def suitable(cls, url):
        return False if LeIE.suitable(url) else super(LePlaylistIE, cls).suitable(url)

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

        # Currently old domain names are still used in playlists
        media_ids = orderedSet(re.findall(
            r'<a[^>]+href="http://www\.letv\.com/ptv/vplay/(\d+)\.html', page))
        entries = [self.url_result(LeIE._URL_TEMPLATE % media_id, ie='Le')
                   for media_id in media_ids]

        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 LetvCloudIE(InfoExtractor):
    # Most of *.letv.com is changed to *.le.com on 2016/01/02
    # but yuntv.letv.com is kept, so also keep the extractor name
    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': 'Video p7jnfw5hw9_467623dedf',
        },
    }, {
        'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=ec93197892&pu=2c7cd40209&auto_play=1&gpcflag=1&width=640&height=360',
        'md5': 'e03d9cc8d9c13191e1caf277e42dbd31',
        'info_dict': {
            'id': 'p7jnfw5hw9_ec93197892',
            'ext': 'mp4',
            'title': 'Video p7jnfw5hw9_ec93197892',
        },
    }, {
        'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=187060b6fd',
        'md5': 'cb988699a776b22d4a41b9d43acfb3ac',
        'info_dict': {
            'id': 'p7jnfw5hw9_187060b6fd',
            'ext': 'mp4',
            'title': 'Video p7jnfw5hw9_187060b6fd',
        },
    }]

    @staticmethod
    def sign_data(obj):
        if obj['cf'] == 'flash':
            salt = '2f9d6924b33a165a6d8b5d3d42f4f987'
            items = ['cf', 'format', 'ran', 'uu', 'ver', 'vu']
        elif obj['cf'] == 'html5':
            salt = 'fbeh5player12c43eccf2bec3300344'
            items = ['cf', 'ran', 'uu', 'bver', 'vu']
        input_data = ''.join([item + obj[item] for item in items]) + salt
        obj['sign'] = hashlib.md5(input_data.encode('utf-8')).hexdigest()

    def _get_formats(self, cf, uu, vu, media_id):
        def get_play_json(cf, timestamp):
            data = {
                'cf': cf,
                'ver': '2.2',
                'bver': 'firefox44.0',
                'format': 'json',
                'uu': uu,
                'vu': vu,
                'ran': compat_str(timestamp),
            }
            self.sign_data(data)
            return self._download_json(
                'http://api.letvcloud.com/gpc.php?' + compat_urllib_parse_urlencode(data),
                media_id, 'Downloading playJson data for type %s' % cf)

        play_json = get_play_json(cf, time.time())
        # The server time may be different from local time
        if play_json.get('code') == 10071:
            play_json = get_play_json(cf, play_json['timestamp'])

        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 unknown error')

        def b64decode(s):
            return compat_b64decode(s).decode('utf-8')

        formats = []
        for media in play_json['data']['video_info']['media'].values():
            play_url = media['play_url']
            url = b64decode(play_url['main_url'])
            decoded_url = b64decode(url_basename(url))
            formats.append({
                'url': url,
                'ext': determine_ext(decoded_url),
                'format_id': str_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')),
            })

        return formats

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

        formats = self._get_formats('flash', uu, vu, media_id) + self._get_formats('html5', uu, vu, media_id)

        return {
            'id': media_id,
            'title': 'Video %s' % media_id,
            'formats': formats,
        }