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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     parse_iso8601,
   7 )
   8
   9
  10 class BeegIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
  12     _TEST = {
  13         'url': 'http://beeg.com/5416503',
  14         'md5': '46c384def73b33dbc581262e5ee67cef',
  15         'info_dict': {
  16             'id': '5416503',
  17             'ext': 'mp4',
  18             'title': 'Sultry Striptease',
  19             'description': 'md5:d22219c09da287c14bed3d6c37ce4bc2',
  20             'timestamp': 1391813355,
  21             'upload_date': '20140207',
  22             'duration': 383,
  23             'tags': list,
  24             'age_limit': 18,
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         video = self._download_json(
  32             'http://beeg.com/api/v1/video/%s' % video_id, video_id)
  33
  34         formats = []
  35         for format_id, video_url in video.items():
  36             if not video_url:
  37                 continue
  38             height = self._search_regex(
  39                 r'^(\d+)[pP]$', format_id, 'height', default=None)
  40             if not height:
  41                 continue
  42             formats.append({
  43                 'url': self._proto_relative_url(video_url.replace('{DATA_MARKERS}', ''), 'http:'),
  44                 'format_id': format_id,
  45                 'height': int(height),
  46             })
  47         self._sort_formats(formats)
  48
  49         title = video['title']
  50         video_id = video.get('id') or video_id
  51         display_id = video.get('code')
  52         description = video.get('desc')
  53
  54         timestamp = parse_iso8601(video.get('date'), ' ')
  55         duration = int_or_none(video.get('duration'))
  56
  57         tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None
  58
  59         return {
  60             'id': video_id,
  61             'display_id': display_id,
  62             'title': title,
  63             'description': description,
  64             'timestamp': timestamp,
  65             'duration': duration,
  66             'tags': tags,
  67             'formats': formats,
  68             'age_limit': 18,
  69         }