_ Git - youtube-dl/blob - youtube_dl/extractor/vube.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     int_or_none,
   8     compat_str,
   9     ExtractorError,
  10 )
  11
  12
  13 class VubeIE(InfoExtractor):
  14     IE_NAME = 'vube'
  15     IE_DESC = 'Vube.com'
  16     _VALID_URL = r'http://vube\.com/(?:[^/]+/)+(?P<id>[\da-zA-Z]{10})\b'
  17
  18     _TESTS = [
  19         {
  20             'url': 'http://vube.com/Chiara+Grispo+Video+Channel/YL2qNPkqon',
  21             'md5': 'db7aba89d4603dadd627e9d1973946fe',
  22             'info_dict': {
  23                 'id': 'YL2qNPkqon',
  24                 'ext': 'mp4',
  25                 'title': 'Chiara Grispo - Price Tag by Jessie J',
  26                 'description': 'md5:8ea652a1f36818352428cb5134933313',
  27                 'thumbnail': 're:^http://frame\.thestaticvube\.com/snap/[0-9x]+/102e7e63057-5ebc-4f5c-4065-6ce4ebde131f\.jpg$',
  28                 'uploader': 'Chiara.Grispo',
  29                 'timestamp': 1388743358,
  30                 'upload_date': '20140103',
  31                 'duration': 170.56,
  32                 'like_count': int,
  33                 'dislike_count': int,
  34                 'comment_count': int,
  35                 'categories': ['pop', 'music', 'cover', 'singing', 'jessie j', 'price tag', 'chiara grispo'],
  36             }
  37         },
  38         {
  39             'url': 'http://vube.com/SerainaMusic/my-7-year-old-sister-and-i-singing-alive-by-krewella/UeBhTudbfS?t=s&n=1',
  40             'md5': '5d4a52492d76f72712117ce6b0d98d08',
  41             'info_dict': {
  42                 'id': 'UeBhTudbfS',
  43                 'ext': 'mp4',
  44                 'title': 'My 7 year old Sister and I singing "Alive" by Krewella',
  45                 'description': 'md5:40bcacb97796339f1690642c21d56f4a',
  46                 'thumbnail': 're:^http://frame\.thestaticvube\.com/snap/[0-9x]+/102265d5a9f-0f17-4f6b-5753-adf08484ee1e\.jpg$',
  47                 'uploader': 'Seraina',
  48                 'timestamp': 1396492438,
  49                 'upload_date': '20140403',
  50                 'duration': 240.107,
  51                 'like_count': int,
  52                 'dislike_count': int,
  53                 'comment_count': int,
  54                 'categories': ['seraina', 'jessica', 'krewella', 'alive'],
  55             }
  56         }, {
  57             'url': 'http://vube.com/vote/Siren+Gene/0nmsMY5vEq?n=2&t=s',
  58             'md5': '0584fc13b50f887127d9d1007589d27f',
  59             'info_dict': {
  60                 'id': '0nmsMY5vEq',
  61                 'ext': 'mp4',
  62                 'title': 'Frozen - Let It Go Cover by Siren Gene',
  63                 'description': 'My rendition of "Let It Go" originally sung by Idina Menzel.',
  64                 'thumbnail': 're:^http://frame\.thestaticvube\.com/snap/[0-9x]+/10283ab622a-86c9-4681-51f2-30d1f65774af\.jpg$',
  65                 'uploader': 'Siren',
  66                 'timestamp': 1395448018,
  67                 'upload_date': '20140322',
  68                 'duration': 221.788,
  69                 'like_count': int,
  70                 'dislike_count': int,
  71                 'comment_count': int,
  72                 'categories': ['let it go', 'cover', 'idina menzel', 'frozen', 'singing', 'disney', 'siren gene'],
  73             }
  74         }
  75     ]
  76
  77     def _real_extract(self, url):
  78         mobj = re.match(self._VALID_URL, url)
  79         video_id = mobj.group('id')
  80
  81         video = self._download_json(
  82             'http://vube.com/t-api/v1/video/%s' % video_id, video_id, 'Downloading video JSON')
  83
  84         public_id = video['public_id']
  85
  86         formats = []
  87
  88         for media in video['media'].get('video', []) + video['media'].get('audio', []):
  89             if media['transcoding_status'] != 'processed':
  90                 continue
  91             fmt = {
  92                 'url': 'http://video.thestaticvube.com/video/%s/%s.mp4' % (media['media_resolution_id'], public_id),
  93                 'abr': int(media['audio_bitrate']),
  94                 'format_id': compat_str(media['media_resolution_id']),
  95             }
  96             vbr = int(media['video_bitrate'])
  97             if vbr:
  98                 fmt.update({
  99                     'vbr': vbr,
 100                     'height': int(media['height']),
 101                 })
 102             formats.append(fmt)
 103
 104         self._sort_formats(formats)
 105
 106         if not formats and video.get('vst') == 'dmca':
 107             raise ExtractorError(
 108                 'This video has been removed in response to a complaint received under the US Digital Millennium Copyright Act.',
 109                 expected=True)
 110
 111         title = video['title']
 112         description = video.get('description')
 113         thumbnail = self._proto_relative_url(video.get('thumbnail_src'), scheme='http:')
 114         uploader = video.get('user_alias') or video.get('channel')
 115         timestamp = int_or_none(video.get('upload_time'))
 116         duration = video['duration']
 117         view_count = video.get('raw_view_count')
 118         like_count = video.get('total_likes')
 119         dislike_count = video.get('total_hates')
 120
 121         comments = video.get('comments')
 122         comment_count = None
 123         if comments is None:
 124             comment_data = self._download_json(
 125                 'http://vube.com/api/video/%s/comment' % video_id,
 126                 video_id, 'Downloading video comment JSON', fatal=False)
 127             if comment_data is not None:
 128                 comment_count = int_or_none(comment_data.get('total'))
 129         else:
 130             comment_count = len(comments)
 131
 132         categories = [tag['text'] for tag in video['tags']]
 133
 134         return {
 135             'id': video_id,
 136             'formats': formats,
 137             'title': title,
 138             'description': description,
 139             'thumbnail': thumbnail,
 140             'uploader': uploader,
 141             'timestamp': timestamp,
 142             'duration': duration,
 143             'view_count': view_count,
 144             'like_count': like_count,
 145             'dislike_count': dislike_count,
 146             'comment_count': comment_count,
 147             'categories': categories,
 148         }