aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/dailymotion.py
blob: b312401dc69b9a9ca35cebca767b11f10174e1c2 (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
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
# coding: utf-8
from __future__ import unicode_literals

import re
import json
import itertools

from .common import InfoExtractor

from ..utils import (
    determine_ext,
    error_to_compat_str,
    ExtractorError,
    int_or_none,
    parse_iso8601,
    sanitized_Request,
    str_to_int,
    unescapeHTML,
    mimetype2ext,
)


class DailymotionBaseInfoExtractor(InfoExtractor):
    @staticmethod
    def _build_request(url):
        """Build a request with the family filter disabled"""
        request = sanitized_Request(url)
        request.add_header('Cookie', 'family_filter=off; ff=off')
        return request

    def _download_webpage_handle_no_ff(self, url, *args, **kwargs):
        request = self._build_request(url)
        return self._download_webpage_handle(request, *args, **kwargs)

    def _download_webpage_no_ff(self, url, *args, **kwargs):
        request = self._build_request(url)
        return self._download_webpage(request, *args, **kwargs)


class DailymotionIE(DailymotionBaseInfoExtractor):
    _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:embed|swf|#)/)?video/(?P<id>[^/?_]+)'
    IE_NAME = 'dailymotion'

    _FORMATS = [
        ('stream_h264_ld_url', 'ld'),
        ('stream_h264_url', 'standard'),
        ('stream_h264_hq_url', 'hq'),
        ('stream_h264_hd_url', 'hd'),
        ('stream_h264_hd1080_url', 'hd180'),
    ]

    _TESTS = [
        {
            'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
            'md5': '2137c41a8e78554bb09225b8eb322406',
            'info_dict': {
                'id': 'x2iuewm',
                'ext': 'mp4',
                'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
                'description': 'Several come bundled with the Steam Controller.',
                'thumbnail': r're:^https?:.*\.(?:jpg|png)$',
                'duration': 74,
                'timestamp': 1425657362,
                'upload_date': '20150306',
                'uploader': 'IGN',
                'uploader_id': 'xijv66',
                'age_limit': 0,
                'view_count': int,
            }
        },
        # Vevo video
        {
            'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
            'info_dict': {
                'title': 'Roar (Official)',
                'id': 'USUV71301934',
                'ext': 'mp4',
                'uploader': 'Katy Perry',
                'upload_date': '20130905',
            },
            'params': {
                'skip_download': True,
            },
            'skip': 'VEVO is only available in some countries',
        },
        # age-restricted video
        {
            'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
            'md5': '0d667a7b9cebecc3c89ee93099c4159d',
            'info_dict': {
                'id': 'xyh2zz',
                'ext': 'mp4',
                'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
                'uploader': 'HotWaves1012',
                'age_limit': 18,
            },
            'skip': 'video gone',
        },
        # geo-restricted, player v5
        {
            'url': 'http://www.dailymotion.com/video/xhza0o',
            'only_matching': True,
        },
        # with subtitles
        {
            'url': 'http://www.dailymotion.com/video/x20su5f_the-power-of-nightmares-1-the-rise-of-the-politics-of-fear-bbc-2004_news',
            'only_matching': True,
        },
        {
            'url': 'http://www.dailymotion.com/swf/video/x3n92nf',
            'only_matching': True,
        }
    ]

    @staticmethod
    def _extract_urls(webpage):
        # Look for embedded Dailymotion player
        matches = re.findall(
            r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
        return list(map(lambda m: unescapeHTML(m[1]), matches))

    def _real_extract(self, url):
        video_id = self._match_id(url)

        webpage = self._download_webpage_no_ff(
            'https://www.dailymotion.com/video/%s' % video_id, video_id)

        age_limit = self._rta_search(webpage)

        description = self._og_search_description(webpage) or self._html_search_meta(
            'description', webpage, 'description')

        view_count_str = self._search_regex(
            (r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:([\s\d,.]+)"',
             r'video_views_count[^>]+>\s+([\s\d\,.]+)'),
            webpage, 'view count', fatal=False)
        if view_count_str:
            view_count_str = re.sub(r'\s', '', view_count_str)
        view_count = str_to_int(view_count_str)
        comment_count = int_or_none(self._search_regex(
            r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserComments:(\d+)"',
            webpage, 'comment count', default=None))

        player_v5 = self._search_regex(
            [r'buildPlayer\(({.+?})\);\n',  # See https://github.com/rg3/youtube-dl/issues/7826
             r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);',
             r'buildPlayer\(({.+?})\);',
             r'var\s+config\s*=\s*({.+?});'],
            webpage, 'player v5', default=None)
        if player_v5:
            player = self._parse_json(player_v5, video_id)
            metadata = player['metadata']

            self._check_error(metadata)

            formats = []
            for quality, media_list in metadata['qualities'].items():
                for media in media_list:
                    media_url = media.get('url')
                    if not media_url:
                        continue
                    type_ = media.get('type')
                    if type_ == 'application/vnd.lumberjack.manifest':
                        continue
                    ext = mimetype2ext(type_) or determine_ext(media_url)
                    if ext == 'm3u8':
                        formats.extend(self._extract_m3u8_formats(
                            media_url, video_id, 'mp4', preference=-1,
                            m3u8_id='hls', fatal=False))
                    elif ext == 'f4m':
                        formats.extend(self._extract_f4m_formats(
                            media_url, video_id, preference=-1, f4m_id='hds', fatal=False))
                    else:
                        f = {
                            'url': media_url,
                            'format_id': 'http-%s' % quality,
                            'ext': ext,
                        }
                        m = re.search(r'H264-(?P<width>\d+)x(?P<height>\d+)', media_url)
                        if m:
                            f.update({
                                'width': int(m.group('width')),
                                'height': int(m.group('height')),
                            })
                        formats.append(f)
            self._sort_formats(formats)

            title = metadata['title']
            duration = int_or_none(metadata.get('duration'))
            timestamp = int_or_none(metadata.get('created_time'))
            thumbnail = metadata.get('poster_url')
            uploader = metadata.get('owner', {}).get('screenname')
            uploader_id = metadata.get('owner', {}).get('id')

            subtitles = {}
            subtitles_data = metadata.get('subtitles', {}).get('data', {})
            if subtitles_data and isinstance(subtitles_data, dict):
                for subtitle_lang, subtitle in subtitles_data.items():
                    subtitles[subtitle_lang] = [{
                        'ext': determine_ext(subtitle_url),
                        'url': subtitle_url,
                    } for subtitle_url in subtitle.get('urls', [])]

            return {
                'id': video_id,
                'title': title,
                'description': description,
                'thumbnail': thumbnail,
                'duration': duration,
                'timestamp': timestamp,
                'uploader': uploader,
                'uploader_id': uploader_id,
                'age_limit': age_limit,
                'view_count': view_count,
                'comment_count': comment_count,
                'formats': formats,
                'subtitles': subtitles,
            }

        # vevo embed
        vevo_id = self._search_regex(
            r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?video=(?P<id>[\w]*)',
            webpage, 'vevo embed', default=None)
        if vevo_id:
            return self.url_result('vevo:%s' % vevo_id, 'Vevo')

        # fallback old player
        embed_page = self._download_webpage_no_ff(
            'https://www.dailymotion.com/embed/video/%s' % video_id,
            video_id, 'Downloading embed page')

        timestamp = parse_iso8601(self._html_search_meta(
            'video:release_date', webpage, 'upload date'))

        info = self._parse_json(
            self._search_regex(
                r'var info = ({.*?}),$', embed_page,
                'video info', flags=re.MULTILINE),
            video_id)

        self._check_error(info)

        formats = []
        for (key, format_id) in self._FORMATS:
            video_url = info.get(key)
            if video_url is not None:
                m_size = re.search(r'H264-(\d+)x(\d+)', video_url)
                if m_size is not None:
                    width, height = map(int_or_none, (m_size.group(1), m_size.group(2)))
                else:
                    width, height = None, None
                formats.append({
                    'url': video_url,
                    'ext': 'mp4',
                    'format_id': format_id,
                    'width': width,
                    'height': height,
                })
        self._sort_formats(formats)

        # subtitles
        video_subtitles = self.extract_subtitles(video_id, webpage)

        title = self._og_search_title(webpage, default=None)
        if title is None:
            title = self._html_search_regex(
                r'(?s)<span\s+id="video_title"[^>]*>(.*?)</span>', webpage,
                'title')

        return {
            'id': video_id,
            'formats': formats,
            'uploader': info['owner.screenname'],
            'timestamp': timestamp,
            'title': title,
            'description': description,
            'subtitles': video_subtitles,
            'thumbnail': info['thumbnail_url'],
            'age_limit': age_limit,
            'view_count': view_count,
            'duration': info['duration']
        }

    def _check_error(self, info):
        if info.get('error') is not None:
            raise ExtractorError(
                '%s said: %s' % (self.IE_NAME, info['error']['title']), expected=True)

    def _get_subtitles(self, video_id, webpage):
        try:
            sub_list = self._download_webpage(
                'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
                video_id, note=False)
        except ExtractorError as err:
            self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
            return {}
        info = json.loads(sub_list)
        if (info['total'] > 0):
            sub_lang_list = dict((l['language'], [{'url': l['url'], 'ext': 'srt'}]) for l in info['list'])
            return sub_lang_list
        self._downloader.report_warning('video doesn\'t have subtitles')
        return {}


class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
    IE_NAME = 'dailymotion:playlist'
    _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
    _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'
    _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
    _TESTS = [{
        'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
        'info_dict': {
            'title': 'SPORT',
            'id': 'xv4bw_nqtv_sport',
        },
        'playlist_mincount': 20,
    }]

    def _extract_entries(self, id):
        video_ids = set()
        processed_urls = set()
        for pagenum in itertools.count(1):
            page_url = self._PAGE_TEMPLATE % (id, pagenum)
            webpage, urlh = self._download_webpage_handle_no_ff(
                page_url, id, 'Downloading page %s' % pagenum)
            if urlh.geturl() in processed_urls:
                self.report_warning('Stopped at duplicated page %s, which is the same as %s' % (
                    page_url, urlh.geturl()), id)
                break

            processed_urls.add(urlh.geturl())

            for video_id in re.findall(r'data-xid="(.+?)"', webpage):
                if video_id not in video_ids:
                    yield self.url_result(
                        'http://www.dailymotion.com/video/%s' % video_id,
                        DailymotionIE.ie_key(), video_id)
                    video_ids.add(video_id)

            if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
                break

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        playlist_id = mobj.group('id')
        webpage = self._download_webpage(url, playlist_id)

        return {
            '_type': 'playlist',
            'id': playlist_id,
            'title': self._og_search_title(webpage),
            'entries': self._extract_entries(playlist_id),
        }


class DailymotionUserIE(DailymotionPlaylistIE):
    IE_NAME = 'dailymotion:user'
    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)'
    _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
    _TESTS = [{
        'url': 'https://www.dailymotion.com/user/nqtv',
        'info_dict': {
            'id': 'nqtv',
            'title': 'Rémi Gaillard',
        },
        'playlist_mincount': 100,
    }, {
        'url': 'http://www.dailymotion.com/user/UnderProject',
        'info_dict': {
            'id': 'UnderProject',
            'title': 'UnderProject',
        },
        'playlist_mincount': 1800,
        'expected_warnings': [
            'Stopped at duplicated page',
        ],
        'skip': 'Takes too long time',
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        user = mobj.group('user')
        webpage = self._download_webpage(
            'https://www.dailymotion.com/user/%s' % user, user)
        full_user = unescapeHTML(self._html_search_regex(
            r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
            webpage, 'user'))

        return {
            '_type': 'playlist',
            'id': user,
            'title': full_user,
            'entries': self._extract_entries(user),
        }


class DailymotionCloudIE(DailymotionBaseInfoExtractor):
    _VALID_URL_PREFIX = r'https?://api\.dmcloud\.net/(?:player/)?embed/'
    _VALID_URL = r'%s[^/]+/(?P<id>[^/?]+)' % _VALID_URL_PREFIX
    _VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX

    _TESTS = [{
        # From http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html
        # Tested at FranceTvInfo_2
        'url': 'http://api.dmcloud.net/embed/4e7343f894a6f677b10006b4/556e03339473995ee145930c?auth=1464865870-0-jyhsm84b-ead4c701fb750cf9367bf4447167a3db&autoplay=1',
        'only_matching': True,
    }, {
        # http://www.francetvinfo.fr/societe/larguez-les-amarres-le-cobaturage-se-developpe_980101.html
        'url': 'http://api.dmcloud.net/player/embed/4e7343f894a6f677b10006b4/559545469473996d31429f06?auth=1467430263-0-90tglw2l-a3a4b64ed41efe48d7fccad85b8b8fda&autoplay=1',
        'only_matching': True,
    }]

    @classmethod
    def _extract_dmcloud_url(cls, webpage):
        mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL, webpage)
        if mobj:
            return mobj.group(1)

        mobj = re.search(
            r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL,
            webpage)
        if mobj:
            return mobj.group(1)

    def _real_extract(self, url):
        video_id = self._match_id(url)

        webpage = self._download_webpage_no_ff(url, video_id)

        title = self._html_search_regex(r'<title>([^>]+)</title>', webpage, 'title')

        video_info = self._parse_json(self._search_regex(
            r'var\s+info\s*=\s*([^;]+);', webpage, 'video info'), video_id)

        # TODO: parse ios_url, which is in fact a manifest
        video_url = video_info['mp4_url']

        return {
            'id': video_id,
            'url': video_url,
            'title': title,
            'thumbnail': video_info.get('thumbnail_url'),
        }