depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-26 04:02:11 +00:00
Code Issues Releases Wiki Activity

Move MTV IE into its own file

Browse source
This commit is contained in:
Philipp Hagemeister 2013-06-23 21:27:38 +02:00
parent 5b286728de
commit 335056663a
1 changed files with 1 additions and 60 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

61
youtube_dl/InfoExtractors.py
View file

@ -33,6 +33,7 @@ from .extractor.googleplus import GooglePlusIE
from .extractor.googlesearch import GoogleSearchIE
from .extractor.infoq import InfoQIE
from .extractor.metacafe import MetacafeIE
from .extractor.mtv import MTVIE
from .extractor.myvideo import MyVideoIE
from .extractor.nba import NBAIE
from .extractor.statigram import StatigramIE
@ -153,66 +154,6 @@ class MixcloudIE(InfoExtractor):
}]
class MTVIE(InfoExtractor):
"""Information extractor for MTV.com"""
_VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$'
IE_NAME = u'mtv'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
if not mobj.group('proto'):
url = 'http://' + url
video_id = mobj.group('videoid')
webpage = self._download_webpage(url, video_id)
song_name = self._html_search_regex(r'<meta name="mtv_vt" content="([^"]+)"/>',
webpage, u'song name', fatal=False)
video_title = self._html_search_regex(r'<meta name="mtv_an" content="([^"]+)"/>',
webpage, u'title')
mtvn_uri = self._html_search_regex(r'<meta name="mtvn_uri" content="([^"]+)"/>',
webpage, u'mtvn_uri', fatal=False)
content_id = self._search_regex(r'MTVN.Player.defaultPlaylistId = ([0-9]+);',
webpage, u'content id', fatal=False)
videogen_url = 'http://www.mtv.com/player/includes/mediaGen.jhtml?uri=' + mtvn_uri + '&id=' + content_id + '&vid=' + video_id + '&ref=www.mtvn.com&viewUri=' + mtvn_uri
self.report_extraction(video_id)
request = compat_urllib_request.Request(videogen_url)
try:
metadataXml = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
raise ExtractorError(u'Unable to download video metadata: %s' % compat_str(err))
mdoc = xml.etree.ElementTree.fromstring(metadataXml)
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']
video_url = rendition.find('./src').text
except KeyError:
raise ExtractorError('Invalid rendition field.')
info = {
'id': video_id,
'url': video_url,
'uploader': performer,
'upload_date': None,
'title': video_title,
'ext': ext,
'format': format,
}
return [info]
class YoukuIE(InfoExtractor):