Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/servingsys.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6 )
   7
   8
   9 class ServingSysIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:[^.]+\.)?serving-sys\.com/BurstingPipe/adServer\.bs\?.*?&pli=(?P<id>[0-9]+)'
  11
  12     _TEST = {
  13         'url': 'http://bs.serving-sys.com/BurstingPipe/adServer.bs?cn=is&c=23&pl=VAST&pli=5349193&PluID=0&pos=7135&ord=[timestamp]&cim=1?',
  14         'info_dict': {
  15             'id': '5349193',
  16             'title': 'AdAPPter_Hyundai_demo',
  17         },
  18         'playlist': [{
  19             'md5': 'baed851342df6846eb8677a60a011a0f',
  20             'info_dict': {
  21                 'id': '29955898',
  22                 'ext': 'flv',
  23                 'title': 'AdAPPter_Hyundai_demo (1)',
  24                 'duration': 74,
  25                 'tbr': 1378,
  26                 'width': 640,
  27                 'height': 400,
  28             },
  29         }, {
  30             'md5': '979b4da2655c4bc2d81aeb915a8c5014',
  31             'info_dict': {
  32                 'id': '29907998',
  33                 'ext': 'flv',
  34                 'title': 'AdAPPter_Hyundai_demo (2)',
  35                 'duration': 34,
  36                 'width': 854,
  37                 'height': 480,
  38                 'tbr': 516,
  39             },
  40         }],
  41         'params': {
  42             'playlistend': 2,
  43         },
  44         '_skip': 'Blocked in the US [sic]',
  45     }
  46
  47     def _real_extract(self, url):
  48         pl_id = self._match_id(url)
  49         vast_doc = self._download_xml(url, pl_id)
  50
  51         title = vast_doc.find('.//AdTitle').text
  52         media = vast_doc.find('.//MediaFile').text
  53         info_url = self._search_regex(r'&adData=([^&]+)&', media, 'info URL')
  54
  55         doc = self._download_xml(info_url, pl_id, 'Downloading video info')
  56         entries = [{
  57             '_type': 'video',
  58             'id': a.attrib['id'],
  59             'title': '%s (%s)' % (title, a.attrib['assetID']),
  60             'url': a.attrib['URL'],
  61             'duration': int_or_none(a.attrib.get('length')),
  62             'tbr': int_or_none(a.attrib.get('bitrate')),
  63             'height': int_or_none(a.attrib.get('height')),
  64             'width': int_or_none(a.attrib.get('width')),
  65         } for a in doc.findall('.//AdditionalAssets/asset')]
  66
  67         return {
  68             '_type': 'playlist',
  69             'id': pl_id,
  70             'title': title,
  71             'entries': entries,
  72         }