aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/mtv.py
blob: 824bbcb4e6d58d3856e521c6de055346164dd1db (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
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import (
    compat_urllib_parse,
    compat_str,
)
from ..utils import (
    ExtractorError,
    find_xpath_attr,
    fix_xml_ampersands,
    float_or_none,
    HEADRequest,
    sanitized_Request,
    unescapeHTML,
    url_basename,
    RegexNotFoundError,
    xpath_text,
)


def _media_xml_tag(tag):
    return '{http://search.yahoo.com/mrss/}%s' % tag


class MTVServicesInfoExtractor(InfoExtractor):
    _MOBILE_TEMPLATE = None
    _LANG = None

    @staticmethod
    def _id_from_uri(uri):
        return uri.split(':')[-1]

    # This was originally implemented for ComedyCentral, but it also works here
    @staticmethod
    def _transform_rtmp_url(rtmp_video_url):
        m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url)
        if not m:
            return rtmp_video_url
        base = 'http://viacommtvstrmfs.fplive.net/'
        return base + m.group('finalid')

    def _get_feed_url(self, uri):
        return self._FEED_URL

    def _get_thumbnail_url(self, uri, itemdoc):
        search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
        thumb_node = itemdoc.find(search_path)
        if thumb_node is None:
            return None
        else:
            return thumb_node.attrib['url']

    def _extract_mobile_video_formats(self, mtvn_id):
        webpage_url = self._MOBILE_TEMPLATE % mtvn_id
        req = sanitized_Request(webpage_url)
        # Otherwise we get a webpage that would execute some javascript
        req.add_header('User-Agent', 'curl/7')
        webpage = self._download_webpage(req, mtvn_id,
                                         'Downloading mobile page')
        metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url'))
        req = HEADRequest(metrics_url)
        response = self._request_webpage(req, mtvn_id, 'Resolving url')
        url = response.geturl()
        # Transform the url to get the best quality:
        url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, 1)
        return [{'url': url, 'ext': 'mp4'}]

    def _extract_video_formats(self, mdoc, mtvn_id):
        if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4|copyright_error\.flv(?:\?geo\b.+?)?)$', mdoc.find('.//src').text) is not None:
            if mtvn_id is not None and self._MOBILE_TEMPLATE is not None:
                self.to_screen('The normal version is not available from your '
                               'country, trying with the mobile version')
                return self._extract_mobile_video_formats(mtvn_id)
            raise ExtractorError('This video is not available from your country.',
                                 expected=True)

        formats = []
        for rendition in mdoc.findall('.//rendition'):
            try:
                _, _, ext = rendition.attrib['type'].partition('/')
                rtmp_video_url = rendition.find('./src').text
                if rtmp_video_url.endswith('siteunavail.png'):
                    continue
                formats.append({
                    'ext': ext,
                    'url': self._transform_rtmp_url(rtmp_video_url),
                    'format_id': rendition.get('bitrate'),
                    'width': int(rendition.get('width')),
                    'height': int(rendition.get('height')),
                })
            except (KeyError, TypeError):
                raise ExtractorError('Invalid rendition field.')
        self._sort_formats(formats)
        return formats

    def _extract_subtitles(self, mdoc, mtvn_id):
        subtitles = {}
        for transcript in mdoc.findall('.//transcript'):
            if transcript.get('kind') != 'captions':
                continue
            lang = transcript.get('srclang')
            subtitles[lang] = [{
                'url': compat_str(typographic.get('src')),
                'ext': typographic.get('format')
            } for typographic in transcript.findall('./typographic')]
        return subtitles

    def _get_video_info(self, itemdoc):
        uri = itemdoc.find('guid').text
        video_id = self._id_from_uri(uri)
        self.report_extraction(video_id)
        content_el = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content')))
        mediagen_url = content_el.attrib['url']
        # Remove the templates, like &device={device}
        mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', mediagen_url)
        if 'acceptMethods' not in mediagen_url:
            mediagen_url += '&' if '?' in mediagen_url else '?'
            mediagen_url += 'acceptMethods=fms'

        mediagen_doc = self._download_xml(mediagen_url, video_id,
                                          'Downloading video urls')

        item = mediagen_doc.find('./video/item')
        if item is not None and item.get('type') == 'text':
            message = '%s returned error: ' % self.IE_NAME
            if item.get('code') is not None:
                message += '%s - ' % item.get('code')
            message += item.text
            raise ExtractorError(message, expected=True)

        description = xpath_text(itemdoc, 'description')

        title_el = None
        if title_el is None:
            title_el = find_xpath_attr(
                itemdoc, './/{http://search.yahoo.com/mrss/}category',
                'scheme', 'urn:mtvn:video_title')
        if title_el is None:
            title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
        if title_el is None:
            title_el = itemdoc.find('.//title') or itemdoc.find('./title')
            if title_el.text is None:
                title_el = None

        title = title_el.text
        if title is None:
            raise ExtractorError('Could not find video title')
        title = title.strip()

        # This a short id that's used in the webpage urls
        mtvn_id = None
        mtvn_id_node = find_xpath_attr(itemdoc, './/{http://search.yahoo.com/mrss/}category',
                                       'scheme', 'urn:mtvn:id')
        if mtvn_id_node is not None:
            mtvn_id = mtvn_id_node.text

        return {
            'title': title,
            'formats': self._extract_video_formats(mediagen_doc, mtvn_id),
            'subtitles': self._extract_subtitles(mediagen_doc, mtvn_id),
            'id': video_id,
            'thumbnail': self._get_thumbnail_url(uri, itemdoc),
            'description': description,
            'duration': float_or_none(content_el.attrib.get('duration')),
        }

    def _get_feed_query(self, uri):
        data = {'uri': uri}
        if self._LANG:
            data['lang'] = self._LANG
        return compat_urllib_parse.urlencode(data)

    def _get_videos_info(self, uri):
        video_id = self._id_from_uri(uri)
        feed_url = self._get_feed_url(uri)
        info_url = feed_url + '?' + self._get_feed_query(uri)
        return self._get_videos_info_from_url(info_url, video_id)

    def _get_videos_info_from_url(self, url, video_id):
        idoc = self._download_xml(
            url, video_id,
            'Downloading info', transform_source=fix_xml_ampersands)
        return self.playlist_result(
            [self._get_video_info(item) for item in idoc.findall('.//item')])

    def _extract_mgid(self, webpage):
        try:
            # the url can be http://media.mtvnservices.com/fb/{mgid}.swf
            # or http://media.mtvnservices.com/{mgid}
            og_url = self._og_search_video_url(webpage)
            mgid = url_basename(og_url)
            if mgid.endswith('.swf'):
                mgid = mgid[:-4]
        except RegexNotFoundError:
            mgid = None

        if mgid is None or ':' not in mgid:
            mgid = self._search_regex(
                [r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'],
                webpage, 'mgid', default=None)

        if not mgid:
            sm4_embed = self._html_search_meta(
                'sm4:video:embed', webpage, 'sm4 embed', default='')
            mgid = self._search_regex(
                r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid')
        return mgid

    def _real_extract(self, url):
        title = url_basename(url)
        webpage = self._download_webpage(url, title)
        mgid = self._extract_mgid(webpage)
        videos_info = self._get_videos_info(mgid)
        return videos_info


class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
    IE_NAME = 'mtvservices:embedded'
    _VALID_URL = r'https?://media\.mtvnservices\.com/embed/(?P<mgid>.+?)(\?|/|$)'

    _TEST = {
        # From http://www.thewrap.com/peter-dinklage-sums-up-game-of-thrones-in-45-seconds-video/
        'url': 'http://media.mtvnservices.com/embed/mgid:uma:video:mtv.com:1043906/cp~vid%3D1043906%26uri%3Dmgid%3Auma%3Avideo%3Amtv.com%3A1043906',
        'md5': 'cb349b21a7897164cede95bd7bf3fbb9',
        'info_dict': {
            'id': '1043906',
            'ext': 'mp4',
            'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds',
            'description': '"Sexy sexy sexy, stabby stabby stabby, beautiful language," says Peter Dinklage as he tries summarizing "Game of Thrones" in under a minute.',
        },
    }

    @staticmethod
    def _extract_url(webpage):
        mobj = re.search(
            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media.mtvnservices.com/embed/.+?)\1', webpage)
        if mobj:
            return mobj.group('url')

    def _get_feed_url(self, uri):
        video_id = self._id_from_uri(uri)
        site_id = uri.replace(video_id, '')
        config_url = ('http://media.mtvnservices.com/pmt/e1/players/{0}/'
                      'context4/context5/config.xml'.format(site_id))
        config_doc = self._download_xml(config_url, video_id)
        feed_node = config_doc.find('.//feed')
        feed_url = feed_node.text.strip().split('?')[0]
        return feed_url

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        mgid = mobj.group('mgid')
        return self._get_videos_info(mgid)


class MTVIE(MTVServicesInfoExtractor):
    _VALID_URL = r'''(?x)^https?://
        (?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$|
           m\.mtv\.com/videos/video\.rbml\?.*?id=(?P<mgid>[^&]+))'''

    _FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/'

    _TESTS = [
        {
            'url': 'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
            'md5': '850f3f143316b1e71fa56a4edfd6e0f8',
            'info_dict': {
                'id': '853555',
                'ext': 'mp4',
                'title': 'Taylor Swift - "Ours (VH1 Storytellers)"',
                'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
            },
        },
    ]

    def _get_thumbnail_url(self, uri, itemdoc):
        return 'http://mtv.mtvnimages.com/uri/' + uri

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('videoid')
        uri = mobj.groupdict().get('mgid')
        if uri is None:
            webpage = self._download_webpage(url, video_id)

            # Some videos come from Vevo.com
            m_vevo = re.search(
                r'(?s)isVevoVideo = true;.*?vevoVideoId = "(.*?)";', webpage)
            if m_vevo:
                vevo_id = m_vevo.group(1)
                self.to_screen('Vevo video detected: %s' % vevo_id)
                return self.url_result('vevo:%s' % vevo_id, ie='Vevo')

            uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, 'uri')
        return self._get_videos_info(uri)


class MTVIggyIE(MTVServicesInfoExtractor):
    IE_NAME = 'mtviggy.com'
    _VALID_URL = r'https?://www\.mtviggy\.com/videos/.+'
    _TEST = {
        'url': 'http://www.mtviggy.com/videos/arcade-fire-behind-the-scenes-at-the-biggest-music-experiment-yet/',
        'info_dict': {
            'id': '984696',
            'ext': 'mp4',
            'title': 'Arcade Fire: Behind the Scenes at the Biggest Music Experiment Yet',
        }
    }
    _FEED_URL = 'http://all.mtvworldverticals.com/feed-xml/'


class MTVDEIE(MTVServicesInfoExtractor):
    IE_NAME = 'mtv.de'
    _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:artists|shows|news)/(?:[^/]+/)*(?P<id>\d+)-[^/#?]+/*(?:[#?].*)?$'
    _TESTS = [{
        'url': 'http://www.mtv.de/artists/10571-cro/videos/61131-traum',
        'info_dict': {
            'id': 'music_video-a50bc5f0b3aa4b3190aa',
            'ext': 'mp4',
            'title': 'MusicVideo_cro-traum',
            'description': 'Cro - Traum',
        },
        'params': {
            # rtmp download
            'skip_download': True,
        },
    }, {
        # mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97)
        'url': 'http://www.mtv.de/shows/933-teen-mom-2/staffeln/5353/folgen/63565-enthullungen',
        'info_dict': {
            'id': 'local_playlist-f5ae778b9832cc837189',
            'ext': 'mp4',
            'title': 'Episode_teen-mom-2_shows_season-5_episode-1_full-episode_part1',
        },
        'params': {
            # rtmp download
            'skip_download': True,
        },
    }, {
        # single video in pagePlaylist with different id
        'url': 'http://www.mtv.de/news/77491-mtv-movies-spotlight-pixels-teil-3',
        'info_dict': {
            'id': 'local_playlist-4e760566473c4c8c5344',
            'ext': 'mp4',
            'title': 'Article_mtv-movies-spotlight-pixels-teil-3_short-clips_part1',
            'description': 'MTV Movies Supercut',
        },
        'params': {
            # rtmp download
            'skip_download': True,
        },
    }]

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

        webpage = self._download_webpage(url, video_id)

        playlist = self._parse_json(
            self._search_regex(
                r'window\.pagePlaylist\s*=\s*(\[.+?\]);\n', webpage, 'page playlist'),
            video_id)

        # news pages contain single video in playlist with different id
        if len(playlist) == 1:
            return self._get_videos_info_from_url(playlist[0]['mrss'], video_id)

        for item in playlist:
            item_id = item.get('id')
            if item_id and compat_str(item_id) == video_id:
                return self._get_videos_info_from_url(item['mrss'], video_id)