youtube_dl/extractor/roxwel.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import unified_strdate, determine_ext
   7
   8
   9 class RoxwelIE(InfoExtractor):
  10     _VALID_URL = r'https?://www\.roxwel\.com/player/(?P<filename>.+?)(\.|\?|$)'
  11
  12     _TEST = {
  13         'url': 'http://www.roxwel.com/player/passionpittakeawalklive.html',
  14         'info_dict': {
  15             'id': 'passionpittakeawalklive',
  16             'ext': 'flv',
  17             'title': 'Take A Walk (live)',
  18             'uploader': 'Passion Pit',
  19             'uploader_id': 'passionpit',
  20             'upload_date': '20120928',
  21             'description': 'Passion Pit performs "Take A Walk\" live at The Backyard in Austin, Texas. ',
  22         },
  23         'params': {
  24             # rtmp download
  25             'skip_download': True,
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         filename = mobj.group('filename')
  32         info_url = 'http://www.roxwel.com/api/videos/%s' % filename
  33         info = self._download_json(info_url, filename)
  34
  35         rtmp_rates = sorted([int(r.replace('flv_', '')) for r in info['media_rates'] if r.startswith('flv_')])
  36         best_rate = rtmp_rates[-1]
  37         url_page_url = 'http://roxwel.com/pl_one_time.php?filename=%s&quality=%s' % (filename, best_rate)
  38         rtmp_url = self._download_webpage(url_page_url, filename, 'Downloading video url')
  39         ext = determine_ext(rtmp_url)
  40         if ext == 'f4v':
  41             rtmp_url = rtmp_url.replace(filename, 'mp4:%s' % filename)
  42
  43         return {
  44             'id': filename,
  45             'title': info['title'],
  46             'url': rtmp_url,
  47             'ext': 'flv',
  48             'description': info['description'],
  49             'thumbnail': info.get('player_image_url') or info.get('image_url_large'),
  50             'uploader': info['artist'],
  51             'uploader_id': info['artistname'],
  52             'upload_date': unified_strdate(info['dbdate']),
  53         }