youtube_dl/extractor/vube.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_str,
   8 )
   9 from ..utils import (
  10     int_or_none,
  11     ExtractorError,
  12 )
  13
  14
  15 class VubeIE(InfoExtractor):
  16     IE_NAME = 'vube'
  17     IE_DESC = 'Vube.com'
  18     _VALID_URL = r'http://vube\.com/(?:[^/]+/)+(?P<id>[\da-zA-Z]{10})\b'
  19
  20     _TESTS = [
  21         {
  22             'url': 'http://vube.com/trending/William+Wei/Y8NUZ69Tf7?t=s',
  23             'md5': 'e7aabe1f8f1aa826b9e4735e1f9cee42',
  24             'info_dict': {
  25                 'id': 'Y8NUZ69Tf7',
  26                 'ext': 'mp4',
  27                 'title': 'Best Drummer Ever [HD]',
  28                 'description': 'md5:2d63c4b277b85c2277761c2cf7337d71',
  29                 'thumbnail': 're:^https?://.*\.jpg',
  30                 'uploader': 'William',
  31                 'timestamp': 1406876915,
  32                 'upload_date': '20140801',
  33                 'duration': 258.051,
  34                 'like_count': int,
  35                 'dislike_count': int,
  36                 'comment_count': int,
  37                 'categories': ['amazing', 'hd', 'best drummer ever', 'william wei', 'bucket drumming', 'street drummer', 'epic street drumming'],
  38             },
  39             'skip': 'Not accessible from Travis CI server',
  40         }, {
  41             'url': 'http://vube.com/Chiara+Grispo+Video+Channel/YL2qNPkqon',
  42             'md5': 'db7aba89d4603dadd627e9d1973946fe',
  43             'info_dict': {
  44                 'id': 'YL2qNPkqon',
  45                 'ext': 'mp4',
  46                 'title': 'Chiara Grispo - Price Tag by Jessie J',
  47                 'description': 'md5:8ea652a1f36818352428cb5134933313',
  48                 'thumbnail': 're:^http://frame\.thestaticvube\.com/snap/[0-9x]+/102e7e63057-5ebc-4f5c-4065-6ce4ebde131f\.jpg$',
  49                 'uploader': 'Chiara.Grispo',
  50                 'timestamp': 1388743358,
  51                 'upload_date': '20140103',
  52                 'duration': 170.56,
  53                 'like_count': int,
  54                 'dislike_count': int,
  55                 'comment_count': int,
  56                 'categories': ['pop', 'music', 'cover', 'singing', 'jessie j', 'price tag', 'chiara grispo'],
  57             },
  58             'skip': 'Removed due to DMCA',
  59         },
  60         {
  61             'url': 'http://vube.com/SerainaMusic/my-7-year-old-sister-and-i-singing-alive-by-krewella/UeBhTudbfS?t=s&n=1',
  62             'md5': '5d4a52492d76f72712117ce6b0d98d08',
  63             'info_dict': {
  64                 'id': 'UeBhTudbfS',
  65                 'ext': 'mp4',
  66                 'title': 'My 7 year old Sister and I singing "Alive" by Krewella',
  67                 'description': 'md5:40bcacb97796339f1690642c21d56f4a',
  68                 'thumbnail': 're:^http://frame\.thestaticvube\.com/snap/[0-9x]+/102265d5a9f-0f17-4f6b-5753-adf08484ee1e\.jpg$',
  69                 'uploader': 'Seraina',
  70                 'timestamp': 1396492438,
  71                 'upload_date': '20140403',
  72                 'duration': 240.107,
  73                 'like_count': int,
  74                 'dislike_count': int,
  75                 'comment_count': int,
  76                 'categories': ['seraina', 'jessica', 'krewella', 'alive'],
  77             },
  78             'skip': 'Removed due to DMCA',
  79         }, {
  80             'url': 'http://vube.com/vote/Siren+Gene/0nmsMY5vEq?n=2&t=s',
  81             'md5': '0584fc13b50f887127d9d1007589d27f',
  82             'info_dict': {
  83                 'id': '0nmsMY5vEq',
  84                 'ext': 'mp4',
  85                 'title': 'Frozen - Let It Go Cover by Siren Gene',
  86                 'description': 'My rendition of "Let It Go" originally sung by Idina Menzel.',
  87                 'thumbnail': 're:^http://frame\.thestaticvube\.com/snap/[0-9x]+/10283ab622a-86c9-4681-51f2-30d1f65774af\.jpg$',
  88                 'uploader': 'Siren',
  89                 'timestamp': 1395448018,
  90                 'upload_date': '20140322',
  91                 'duration': 221.788,
  92                 'like_count': int,
  93                 'dislike_count': int,
  94                 'comment_count': int,
  95                 'categories': ['let it go', 'cover', 'idina menzel', 'frozen', 'singing', 'disney', 'siren gene'],
  96             },
  97             'skip': 'Removed due to DMCA',
  98         }
  99     ]
 100
 101     def _real_extract(self, url):
 102         mobj = re.match(self._VALID_URL, url)
 103         video_id = mobj.group('id')
 104
 105         video = self._download_json(
 106             'http://vube.com/t-api/v1/video/%s' % video_id, video_id, 'Downloading video JSON')
 107
 108         public_id = video['public_id']
 109
 110         formats = []
 111
 112         for media in video['media'].get('video', []) + video['media'].get('audio', []):
 113             if media['transcoding_status'] != 'processed':
 114                 continue
 115             fmt = {
 116                 'url': 'http://video.thestaticvube.com/video/%s/%s.mp4' % (media['media_resolution_id'], public_id),
 117                 'abr': int(media['audio_bitrate']),
 118                 'format_id': compat_str(media['media_resolution_id']),
 119             }
 120             vbr = int(media['video_bitrate'])
 121             if vbr:
 122                 fmt.update({
 123                     'vbr': vbr,
 124                     'height': int(media['height']),
 125                 })
 126             formats.append(fmt)
 127
 128         self._sort_formats(formats)
 129
 130         if not formats and video.get('vst') == 'dmca':
 131             raise ExtractorError(
 132                 'This video has been removed in response to a complaint received under the US Digital Millennium Copyright Act.',
 133                 expected=True)
 134
 135         title = video['title']
 136         description = video.get('description')
 137         thumbnail = self._proto_relative_url(video.get('thumbnail_src'), scheme='http:')
 138         uploader = video.get('user_alias') or video.get('channel')
 139         timestamp = int_or_none(video.get('upload_time'))
 140         duration = video['duration']
 141         view_count = video.get('raw_view_count')
 142         like_count = video.get('total_likes')
 143         dislike_count = video.get('total_hates')
 144
 145         comments = video.get('comments')
 146         comment_count = None
 147         if comments is None:
 148             comment_data = self._download_json(
 149                 'http://vube.com/api/video/%s/comment' % video_id,
 150                 video_id, 'Downloading video comment JSON', fatal=False)
 151             if comment_data is not None:
 152                 comment_count = int_or_none(comment_data.get('total'))
 153         else:
 154             comment_count = len(comments)
 155
 156         categories = [tag['text'] for tag in video['tags']]
 157
 158         return {
 159             'id': video_id,
 160             'formats': formats,
 161             'title': title,
 162             'description': description,
 163             'thumbnail': thumbnail,
 164             'uploader': uploader,
 165             'timestamp': timestamp,
 166             'duration': duration,
 167             'view_count': view_count,
 168             'like_count': like_count,
 169             'dislike_count': dislike_count,
 170             'comment_count': comment_count,
 171             'categories': categories,
 172         }