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

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     remove_start,
   9 )
  10
  11
  12 class BlinkxIE(InfoExtractor):
  13     _VALID_URL = r'^(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P<id>[^?]+)'
  14     IE_NAME = 'blinkx'
  15
  16     _TEST = {
  17         'url': 'http://www.blinkx.com/ce/8aQUy7GVFYgFzpKhT0oqsilwOGFRVXk3R1ZGWWdGenBLaFQwb3FzaWx3OGFRVXk3R1ZGWWdGenB',
  18         'file': '8aQUy7GV.mp4',
  19         'md5': '2e9a07364af40163a908edbf10bb2492',
  20         'info_dict': {
  21             'title': 'Police Car Rolls Away',
  22             'uploader': 'stupidvideos.com',
  23             'upload_date': '20131215',
  24             'timestamp': 1387068000,
  25             'description': 'A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!',
  26             'duration': 14.886,
  27             'thumbnails': [{
  28                 'width': 100,
  29                 'height': 76,
  30                 'url': 'http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg',
  31             }],
  32         },
  33     }
  34
  35     def _real_extract(self, rl):
  36         m = re.match(self._VALID_URL, rl)
  37         video_id = m.group('id')
  38         display_id = video_id[:8]
  39
  40         api_url = (u'https://apib4.blinkx.com/api.php?action=play_video&' +
  41                    'video=%s' % video_id)
  42         data_json = self._download_webpage(api_url, display_id)
  43         data = json.loads(data_json)['api']['results'][0]
  44         duration = None
  45         thumbnails = []
  46         formats = []
  47         for m in data['media']:
  48             if m['type'] == 'jpg':
  49                 thumbnails.append({
  50                     'url': m['link'],
  51                     'width': int(m['w']),
  52                     'height': int(m['h']),
  53                 })
  54             elif m['type'] == 'original':
  55                 duration = m['d']
  56             elif m['type'] == 'youtube':
  57                 yt_id = m['link']
  58                 self.to_screen(u'Youtube video detected: %s' % yt_id)
  59                 return self.url_result(yt_id, 'Youtube', video_id=yt_id)
  60             elif m['type'] in ('flv', 'mp4'):
  61                 vcodec = remove_start(m['vcodec'], 'ff')
  62                 acodec = remove_start(m['acodec'], 'ff')
  63                 tbr = (int(m['vbr']) + int(m['abr'])) // 1000
  64                 format_id = u'%s-%sk-%s' % (vcodec, tbr, m['w'])
  65                 formats.append({
  66                     'format_id': format_id,
  67                     'url': m['link'],
  68                     'vcodec': vcodec,
  69                     'acodec': acodec,
  70                     'abr': int(m['abr']) // 1000,
  71                     'vbr': int(m['vbr']) // 1000,
  72                     'tbr': tbr,
  73                     'width': int(m['w']),
  74                     'height': int(m['h']),
  75                 })
  76
  77         self._sort_formats(formats)
  78
  79         return {
  80             'id': display_id,
  81             'fullid': video_id,
  82             'title': data['title'],
  83             'formats': formats,
  84             'uploader': data['channel_name'],
  85             'timestamp': data['pubdate_epoch'],
  86             'description': data.get('description'),
  87             'thumbnails': thumbnails,
  88             'duration': duration,
  89         }