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