aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/mtv.py
blob: 32cfa36322bb23335b3baf32f138d04937f679c3 (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
from __future__ import unicode_literals

import re
import xml.etree.ElementTree

from .common import InfoExtractor
from ..utils import (
    compat_urllib_parse,
    ExtractorError,
    find_xpath_attr,
    fix_xml_ampersands,
)


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


class MTVServicesInfoExtractor(InfoExtractor):
    @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://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
        return base + m.group('finalid')

    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_video_formats(self, metadataXml):
        if '/error_country_block.swf' in metadataXml:
            raise ExtractorError('This video is not available from your country.', expected=True)
        mdoc = xml.etree.ElementTree.fromstring(metadataXml.encode('utf-8'))

        formats = []
        for rendition in mdoc.findall('.//rendition'):
            try:
                _, _, ext = rendition.attrib['type'].partition('/')
                rtmp_video_url = rendition.find('./src').text
                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.')
        return formats

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

        description_node = itemdoc.find('description')
        if description_node is not None:
            description = description_node.text.strip()
        else:
            description = None

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

        return {
            'title': title,
            'formats': self._extract_video_formats(mediagen_page),
            'id': video_id,
            'thumbnail': self._get_thumbnail_url(uri, itemdoc),
            'description': description,
        }

    def _get_videos_info(self, uri):
        video_id = self._id_from_uri(uri)
        data = compat_urllib_parse.urlencode({'uri': uri})

        idoc = self._download_xml(
            self._FEED_URL + '?' + data, video_id,
            'Downloading info', transform_source=fix_xml_ampersands)
        return [self._get_video_info(item) for item in idoc.findall('.//item')]


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',
            'file': '853555.mp4',
            'md5': '850f3f143316b1e71fa56a4edfd6e0f8',
            'info_dict': {
                'title': 'Taylor Swift - "Ours (VH1 Storytellers)"',
                'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
            },
        },
        {
            'add_ie': ['Vevo'],
            'url': 'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml',
            'file': 'USCJY1331283.mp4',
            'md5': '73b4e7fcadd88929292fe52c3ced8caf',
            'info_dict': {
                'title': 'Everything Has Changed',
                'upload_date': '20130606',
                'uploader': 'Taylor Swift',
            },
            'skip': 'VEVO is only available in some countries',
        },
    ]

    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'isVevoVideo = true;.*?vevoVideoId = "(.*?)";',
                               webpage, re.DOTALL)
            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)