aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/dailymotion.py
blob: d8f9eb13f7250fdb4fc26f7e075ef19b05b68fa4 (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
# coding: utf-8
from __future__ import unicode_literals

import re
import json
import itertools

from .common import InfoExtractor

from ..compat import (
    compat_str,
    compat_urllib_request,
)
from ..utils import (
    ExtractorError,
    int_or_none,
    orderedSet,
    str_to_int,
    unescapeHTML,
)


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


class DailymotionIE(DailymotionBaseInfoExtractor):
    """Information Extractor for Dailymotion"""

    _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?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',
                'uploader': 'IGN',
                'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
                'upload_date': '20150306',
            }
        },
        # 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,
            }
        }
    ]

    def _real_extract(self, url):
        video_id = self._match_id(url)
        url = 'https://www.dailymotion.com/video/%s' % video_id

        # Retrieve video webpage to extract further information
        request = self._build_request(url)
        webpage = self._download_webpage(request, video_id)

        # Extract URL, uploader and title from webpage
        self.report_extraction(video_id)

        # It may just embed a vevo video:
        m_vevo = re.search(
            r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?video=(?P<id>[\w]*)',
            webpage)
        if m_vevo is not None:
            vevo_id = m_vevo.group('id')
            self.to_screen('Vevo video detected: %s' % vevo_id)
            return self.url_result('vevo:%s' % vevo_id, ie='Vevo')

        age_limit = self._rta_search(webpage)

        video_upload_date = None
        mobj = re.search(r'<meta property="video:release_date" content="([0-9]{4})-([0-9]{2})-([0-9]{2}).+?"/>', webpage)
        if mobj is not None:
            video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)

        embed_url = 'https://www.dailymotion.com/embed/video/%s' % video_id
        embed_request = self._build_request(embed_url)
        embed_page = self._download_webpage(
            embed_request, video_id, 'Downloading embed page')
        info = self._search_regex(r'var info = ({.*?}),$', embed_page,
                                  'video info', flags=re.MULTILINE)
        info = json.loads(info)
        if info.get('error') is not None:
            msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
            raise ExtractorError(msg, expected=True)

        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,
                })
        if not formats:
            raise ExtractorError('Unable to extract video URL')

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

        view_count = str_to_int(self._search_regex(
            r'video_views_count[^>]+>\s+([\d\.,]+)',
            webpage, 'view count', fatal=False))

        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'],
            'upload_date': video_upload_date,
            'title': title,
            'subtitles': video_subtitles,
            'thumbnail': info['thumbnail_url'],
            'age_limit': age_limit,
            'view_count': view_count,
        }

    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' % 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 = []
        for pagenum in itertools.count(1):
            request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum))
            webpage = self._download_webpage(request,
                                             id, 'Downloading page %s' % pagenum)

            video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage))

            if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
                break
        return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
                for video_id in orderedSet(video_ids)]

    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}/(?:(?: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,
    }]

    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),
        }