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
|
import re
import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
ExtractorError,
)
def _media_xml_tag(tag):
return '{http://search.yahoo.com/mrss/}%s' % tag
class MTVIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$'
_FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/'
_TESTS = [
{
u'url': u'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
u'file': u'853555.mp4',
u'md5': u'850f3f143316b1e71fa56a4edfd6e0f8',
u'info_dict': {
u'title': u'Taylor Swift - "Ours (VH1 Storytellers)"',
u'description': u'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
},
},
{
u'url': u'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml',
u'file': u'USCJY1331283.mp4',
u'md5': u'73b4e7fcadd88929292fe52c3ced8caf',
u'info_dict': {
u'title': u'Everything Has Changed',
u'upload_date': u'20130606',
u'uploader': u'Taylor Swift',
},
u'skip': u'VEVO is only available in some countries',
},
]
@staticmethod
def _id_from_uri(uri):
return uri.split(':')[-1]
# This was originally implemented for ComedyCentral, but it also works here
@staticmethod
def _transform_rtmp_url(rtmp_video_url):
m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url)
if not m:
raise ExtractorError(u'Cannot transform RTMP 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 _extract_video_url(self, metadataXml):
if '/error_country_block.swf' in metadataXml:
raise ExtractorError(u'This video is not available from your country.', expected=True)
mdoc = xml.etree.ElementTree.fromstring(metadataXml.encode('utf-8'))
renditions = mdoc.findall('.//rendition')
# For now, always pick the highest quality.
rendition = renditions[-1]
try:
_,_,ext = rendition.attrib['type'].partition('/')
format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
rtmp_video_url = rendition.find('./src').text
except KeyError:
raise ExtractorError('Invalid rendition field.')
video_url = self._transform_rtmp_url(rtmp_video_url)
return {'ext': ext, 'url': video_url, 'format': format}
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']
if 'acceptMethods' not in mediagen_url:
mediagen_url += '&acceptMethods=fms'
mediagen_page = self._download_webpage(mediagen_url, video_id,
u'Downloading video urls')
video_info = self._extract_video_url(mediagen_page)
description_node = itemdoc.find('description')
if description_node is not None:
description = description_node.text
else:
description = None
video_info.update({'title': itemdoc.find('title').text,
'id': video_id,
'thumbnail': 'http://mtv.mtvnimages.com/uri/' + uri,
'description': description,
})
return video_info
def _get_videos_info(self, uri):
video_id = self._id_from_uri(uri)
data = compat_urllib_parse.urlencode({'uri': uri})
infoXml = self._download_webpage(self._FEED_URL +'?' + data, video_id,
u'Downloading info')
idoc = xml.etree.ElementTree.fromstring(infoXml.encode('utf-8'))
return [self._get_video_info(item) for item in idoc.findall('.//item')]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
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(u'Vevo video detected: %s' % vevo_id)
return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, u'uri')
return self._get_videos_info(uri)
|
