aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/iqiyi.py
blob: 9106dd07491c18b6521ad3894d16ea56238aa9aa (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
# coding: utf-8
from __future__ import unicode_literals

import hashlib
import math
import os.path
import random
import re
import time
import uuid
import zlib

from .common import InfoExtractor
from ..compat import compat_urllib_parse
from ..utils import (
    ExtractorError,
    url_basename,
)


class IqiyiIE(InfoExtractor):
    IE_NAME = 'iqiyi'

    _VALID_URL = r'http://(?:www\.)iqiyi.com/v_.+?\.html'

    _TESTS = [{
        'url': 'http://www.iqiyi.com/v_19rrojlavg.html',
        'md5': '2cb594dc2781e6c941a110d8f358118b',
        'info_dict': {
            'id': '9c1fb1b99d192b21c559e5a1a2cb3c73',
            'title': '美国德州空中惊现奇异云团 酷似UFO',
            'ext': 'f4v',
        }
    }, {
        'url': 'http://www.iqiyi.com/v_19rrhnnclk.html',
        'info_dict': {
            'id': 'e3f585b550a280af23c98b6cb2be19fb',
            'title': '名侦探柯南第752集',
        },
        'playlist': [{
            'md5': '7e49376fecaffa115d951634917fe105',
            'info_dict': {
                'id': 'e3f585b550a280af23c98b6cb2be19fb_part1',
                'ext': 'f4v',
                'title': '名侦探柯南第752集',
            },
        }, {
            'md5': '41b75ba13bb7ac0e411131f92bc4f6ca',
            'info_dict': {
                'id': 'e3f585b550a280af23c98b6cb2be19fb_part2',
                'ext': 'f4v',
                'title': '名侦探柯南第752集',
            },
        }, {
            'md5': '0cee1dd0a3d46a83e71e2badeae2aab0',
            'info_dict': {
                'id': 'e3f585b550a280af23c98b6cb2be19fb_part3',
                'ext': 'f4v',
                'title': '名侦探柯南第752集',
            },
        }, {
            'md5': '4f8ad72373b0c491b582e7c196b0b1f9',
            'info_dict': {
                'id': 'e3f585b550a280af23c98b6cb2be19fb_part4',
                'ext': 'f4v',
                'title': '名侦探柯南第752集',
            },
        }, {
            'md5': 'd89ad028bcfad282918e8098e811711d',
            'info_dict': {
                'id': 'e3f585b550a280af23c98b6cb2be19fb_part5',
                'ext': 'f4v',
                'title': '名侦探柯南第752集',
            },
        }, {
            'md5': '9cb1e5c95da25dff0660c32ae50903b7',
            'info_dict': {
                'id': 'e3f585b550a280af23c98b6cb2be19fb_part6',
                'ext': 'f4v',
                'title': '名侦探柯南第752集',
            },
        }, {
            'md5': '155116e0ff1867bbc9b98df294faabc9',
            'info_dict': {
                'id': 'e3f585b550a280af23c98b6cb2be19fb_part7',
                'ext': 'f4v',
                'title': '名侦探柯南第752集',
            },
        }, {
            'md5': '53f5db77622ae14fa493ed2a278a082b',
            'info_dict': {
                'id': 'e3f585b550a280af23c98b6cb2be19fb_part8',
                'ext': 'f4v',
                'title': '名侦探柯南第752集',
            },
        }],
    }]

    _FORMATS_MAP = [
        ('1', 'h6'),
        ('2', 'h5'),
        ('3', 'h4'),
        ('4', 'h3'),
        ('5', 'h2'),
        ('10', 'h1'),
    ]

    def construct_video_urls(self, data, video_id, _uuid):
        def do_xor(x, y):
            a = y % 3
            if a == 1:
                return x ^ 121
            if a == 2:
                return x ^ 72
            return x ^ 103

        def get_encode_code(l):
            a = 0
            b = l.split('-')
            c = len(b)
            s = ''
            for i in range(c - 1, -1, -1):
                a = do_xor(int(b[c - i - 1], 16), i)
                s += chr(a)
            return s[::-1]

        def get_path_key(x, format_id, segment_index):
            mg = ')(*&^flash@#$%a'
            tm = self._download_json(
                'http://data.video.qiyi.com/t?tn=' + str(random.random()), video_id,
                note='Download path key of segment %d for format %s' % (segment_index + 1, format_id)
            )['t']
            t = str(int(math.floor(int(tm) / (600.0))))
            return hashlib.md5((t + mg + x).encode('utf8')).hexdigest()

        video_urls_dict = {}
        for format_item in data['vp']['tkl'][0]['vs']:
            if 0 < int(format_item['bid']) <= 10:
                format_id = self.get_format(format_item['bid'])
            else:
                continue

            video_urls = []

            video_urls_info = format_item['fs']
            if not format_item['fs'][0]['l'].startswith('/'):
                t = get_encode_code(format_item['fs'][0]['l'])
                if t.endswith('mp4'):
                    video_urls_info = format_item['flvs']

            for segment_index, segment in enumerate(video_urls_info):
                vl = segment['l']
                if not vl.startswith('/'):
                    vl = get_encode_code(vl)
                key = get_path_key(
                    vl.split('/')[-1].split('.')[0], format_id, segment_index)
                filesize = segment['b']
                base_url = data['vp']['du'].split('/')
                base_url.insert(-1, key)
                base_url = '/'.join(base_url)
                param = {
                    'su': _uuid,
                    'qyid': uuid.uuid4().hex,
                    'client': '',
                    'z': '',
                    'bt': '',
                    'ct': '',
                    'tn': str(int(time.time()))
                }
                api_video_url = base_url + vl + '?' + \
                    compat_urllib_parse.urlencode(param)
                js = self._download_json(
                    api_video_url, video_id,
                    note='Download video info of segment %d for format %s' % (segment_index + 1, format_id))
                video_url = js['l']
                video_urls.append(
                    (video_url, filesize))

            video_urls_dict[format_id] = video_urls
        return video_urls_dict

    def get_format(self, bid):
        matched_format_ids = [_format_id for _bid, _format_id in self._FORMATS_MAP if _bid == str(bid)]
        return matched_format_ids[0] if len(matched_format_ids) else None

    def get_bid(self, format_id):
        matched_bids = [_bid for _bid, _format_id in self._FORMATS_MAP if _format_id == format_id]
        return matched_bids[0] if len(matched_bids) else None

    def get_raw_data(self, tvid, video_id, enc_key, _uuid):
        tm = str(int(time.time()))
        param = {
            'key': 'fvip',
            'src': hashlib.md5(b'youtube-dl').hexdigest(),
            'tvId': tvid,
            'vid': video_id,
            'vinfo': 1,
            'tm': tm,
            'enc': hashlib.md5(
                (enc_key + tm + tvid).encode('utf8')).hexdigest(),
            'qyid': _uuid,
            'tn': random.random(),
            'um': 0,
            'authkey': hashlib.md5(
                (tm + tvid).encode('utf8')).hexdigest()
        }

        api_url = 'http://cache.video.qiyi.com/vms' + '?' + \
            compat_urllib_parse.urlencode(param)
        raw_data = self._download_json(api_url, video_id)
        return raw_data

    def get_enc_key(self, swf_url, video_id):
        filename, _ = os.path.splitext(url_basename(swf_url))
        enc_key_json = self._downloader.cache.load('iqiyi-enc-key', filename)
        if enc_key_json is not None:
            return enc_key_json[0]

        req = self._request_webpage(
            swf_url, video_id, note='download swf content')
        cn = req.read()
        cn = zlib.decompress(cn[8:])
        pt = re.compile(b'MixerRemote\x08(?P<enc_key>.+?)\$&vv')
        enc_key = self._search_regex(pt, cn, 'enc_key').decode('utf8')

        self._downloader.cache.store('iqiyi-enc-key', filename, [enc_key])

        return enc_key

    def _real_extract(self, url):
        webpage = self._download_webpage(
            url, 'temp_id', note='download video page')
        tvid = self._search_regex(
            r'data-player-tvid\s*=\s*[\'"](\d+)', webpage, 'tvid')
        video_id = self._search_regex(
            r'data-player-videoid\s*=\s*[\'"]([a-f\d]+)', webpage, 'video_id')
        swf_url = self._search_regex(
            r'(http://[^\'"]+MainPlayer[^.]+\.swf)', webpage, 'swf player URL')
        _uuid = uuid.uuid4().hex

        enc_key = self.get_enc_key(swf_url, video_id)

        raw_data = self.get_raw_data(tvid, video_id, enc_key, _uuid)

        if raw_data['code'] != 'A000000':
            raise ExtractorError('Unable to load data. Error code: ' + raw_data['code'])

        if not raw_data['data']['vp']['tkl']:
            raise ExtractorError('No support iQiqy VIP video')

        data = raw_data['data']

        title = data['vi']['vn']

        # generate video_urls_dict
        video_urls_dict = self.construct_video_urls(
            data, video_id, _uuid)

        # construct info
        entries = []
        for format_id in video_urls_dict:
            video_urls = video_urls_dict[format_id]
            for i, video_url_info in enumerate(video_urls):
                if len(entries) < i + 1:
                    entries.append({'formats': []})
                entries[i]['formats'].append(
                    {
                        'url': video_url_info[0],
                        'filesize': video_url_info[-1],
                        'format_id': format_id,
                        'preference': int(self.get_bid(format_id))
                    }
                )

        for i in range(len(entries)):
            self._sort_formats(entries[i]['formats'])
            entries[i].update(
                {
                    'id': '%s_part%d' % (video_id, i + 1),
                    'title': title,
                }
            )

        if len(entries) > 1:
            info = {
                '_type': 'multi_video',
                'id': video_id,
                'title': title,
                'entries': entries,
            }
        else:
            info = entries[0]
            info['id'] = video_id
            info['title'] = title

        return info