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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     float_or_none,
   6     int_or_none,
   7 )
   8
   9
  10 class ViddlerIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
  12     _TEST = {
  13         "url": "http://www.viddler.com/v/43903784",
  14         'md5': 'ae43ad7cb59431ce043f0ff7fa13cbf4',
  15         'info_dict': {
  16             'id': '43903784',
  17             'ext': 'mp4',
  18             "title": "Video Made Easy",
  19             'description': 'You don\'t need to be a professional to make high-quality video content. Viddler provides some quick and easy tips on how to produce great video content with limited resources. ',
  20             "uploader": "viddler",
  21             'timestamp': 1335371429,
  22             'upload_date': '20120425',
  23             "duration": 100.89,
  24             'thumbnail': 're:^https?://.*\.jpg$',
  25             'view_count': int,
  26             'categories': ['video content', 'high quality video', 'video made easy', 'how to produce video with limited resources', 'viddler'],
  27         }
  28     }
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32
  33         json_url = (
  34             'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json?video_id=%s&key=v0vhrt7bg2xq1vyxhkct' %
  35             video_id)
  36         data = self._download_json(json_url, video_id)['video']
  37
  38         formats = []
  39         for filed in data['files']:
  40             if filed.get('status', 'ready') != 'ready':
  41                 continue
  42             f = {
  43                 'format_id': filed['profile_id'],
  44                 'format_note': filed['profile_name'],
  45                 'url': self._proto_relative_url(filed['url']),
  46                 'width': int_or_none(filed.get('width')),
  47                 'height': int_or_none(filed.get('height')),
  48                 'filesize': int_or_none(filed.get('size')),
  49                 'ext': filed.get('ext'),
  50                 'source_preference': -1,
  51             }
  52             formats.append(f)
  53
  54             if filed.get('cdn_url'):
  55                 f = f.copy()
  56                 f['url'] = self._proto_relative_url(filed['cdn_url'])
  57                 f['format_id'] = filed['profile_id'] + '-cdn'
  58                 f['source_preference'] = 1
  59                 formats.append(f)
  60
  61             if filed.get('html5_video_source'):
  62                 f = f.copy()
  63                 f['url'] = self._proto_relative_url(
  64                     filed['html5_video_source'])
  65                 f['format_id'] = filed['profile_id'] + '-html5'
  66                 f['source_preference'] = 0
  67                 formats.append(f)
  68         self._sort_formats(formats)
  69
  70         categories = [
  71             t.get('text') for t in data.get('tags', []) if 'text' in t]
  72
  73         return {
  74             '_type': 'video',
  75             'id': video_id,
  76             'title': data['title'],
  77             'formats': formats,
  78             'description': data.get('description'),
  79             'timestamp': int_or_none(data.get('upload_time')),
  80             'thumbnail': self._proto_relative_url(data.get('thumbnail_url')),
  81             'uploader': data.get('author'),
  82             'duration': float_or_none(data.get('length')),
  83             'view_count': int_or_none(data.get('view_count')),
  84             'categories': categories,
  85         }