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

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