_ Git - youtube-dl/blob - youtube_dl/extractor/mtv.py

   1 import re
   2 import socket
   3 import xml.etree.ElementTree
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_http_client,
   8     compat_str,
   9     compat_urllib_error,
  10     compat_urllib_request,
  11
  12     ExtractorError,
  13 )
  14
  15
  16 class MTVIE(InfoExtractor):
  17     _VALID_URL = r'^(?P<proto>https?://)?(?:www\.)?mtv\.com/videos/[^/]+/(?P<videoid>[0-9]+)/[^/]+$'
  18
  19     def _real_extract(self, url):
  20         mobj = re.match(self._VALID_URL, url)
  21         if mobj is None:
  22             raise ExtractorError(u'Invalid URL: %s' % url)
  23         if not mobj.group('proto'):
  24             url = 'http://' + url
  25         video_id = mobj.group('videoid')
  26
  27         webpage = self._download_webpage(url, video_id)
  28
  29         song_name = self._html_search_regex(r'<meta name="mtv_vt" content="([^"]+)"/>',
  30             webpage, u'song name', fatal=False)
  31
  32         video_title = self._html_search_regex(r'<meta name="mtv_an" content="([^"]+)"/>',
  33             webpage, u'title')
  34
  35         mtvn_uri = self._html_search_regex(r'<meta name="mtvn_uri" content="([^"]+)"/>',
  36             webpage, u'mtvn_uri', fatal=False)
  37
  38         content_id = self._search_regex(r'MTVN.Player.defaultPlaylistId = ([0-9]+);',
  39             webpage, u'content id', fatal=False)
  40
  41         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
  42         self.report_extraction(video_id)
  43         request = compat_urllib_request.Request(videogen_url)
  44         try:
  45             metadataXml = compat_urllib_request.urlopen(request).read()
  46         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
  47             raise ExtractorError(u'Unable to download video metadata: %s' % compat_str(err))
  48
  49         mdoc = xml.etree.ElementTree.fromstring(metadataXml)
  50         print(metadataXml)
  51         renditions = mdoc.findall('.//rendition')
  52
  53         # For now, always pick the highest quality.
  54         rendition = renditions[-1]
  55
  56         try:
  57             _,_,ext = rendition.attrib['type'].partition('/')
  58             format = ext + '-' + rendition.attrib['width'] + 'x' + rendition.attrib['height'] + '_' + rendition.attrib['bitrate']
  59             video_url = rendition.find('./src').text
  60         except KeyError:
  61             raise ExtractorError('Invalid rendition field.')
  62
  63         info = {
  64             'id': video_id,
  65             'url': video_url,
  66             'uploader': performer,
  67             'upload_date': None,
  68             'title': video_title,
  69             'ext': ext,
  70             'format': format,
  71         }
  72
  73         return [info]