yt_dlp/extractor/vine.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     determine_ext,
   5     format_field,
   6     int_or_none,
   7     unified_timestamp,
   8 )
   9
  10
  11 class VineIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?vine\.co/(?:v|oembed)/(?P<id>\w+)'
  13     _EMBED_REGEX = [r'<iframe[^>]+src=[\'"](?P<url>(?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))']
  14     _TESTS = [{
  15         'url': 'https://vine.co/v/b9KOOWX7HUx',
  16         'md5': '2f36fed6235b16da96ce9b4dc890940d',
  17         'info_dict': {
  18             'id': 'b9KOOWX7HUx',
  19             'ext': 'mp4',
  20             'title': 'Chicken.',
  21             'alt_title': 'Vine by Jack',
  22             'timestamp': 1368997951,
  23             'upload_date': '20130519',
  24             'uploader': 'Jack',
  25             'uploader_id': '76',
  26             'view_count': int,
  27             'like_count': int,
  28             'comment_count': int,
  29             'repost_count': int,
  30         },
  31     }, {
  32         'url': 'https://vine.co/v/e192BnZnZ9V',
  33         'info_dict': {
  34             'id': 'e192BnZnZ9V',
  35             'ext': 'mp4',
  36             'title': 'ยิ้ม~ เขิน~ อาย~ น่าร้ากอ้ะ >//< @n_whitewo @orlameena #lovesicktheseries  #lovesickseason2',
  37             'alt_title': 'Vine by Pimry_zaa',
  38             'timestamp': 1436057405,
  39             'upload_date': '20150705',
  40             'uploader': 'Pimry_zaa',
  41             'uploader_id': '1135760698325307392',
  42             'view_count': int,
  43             'like_count': int,
  44             'comment_count': int,
  45             'repost_count': int,
  46         },
  47         'params': {
  48             'skip_download': True,
  49         },
  50     }, {
  51         'url': 'https://vine.co/v/MYxVapFvz2z',
  52         'only_matching': True,
  53     }, {
  54         'url': 'https://vine.co/v/bxVjBbZlPUH',
  55         'only_matching': True,
  56     }, {
  57         'url': 'https://vine.co/oembed/MYxVapFvz2z.json',
  58         'only_matching': True,
  59     }]
  60
  61     def _real_extract(self, url):
  62         video_id = self._match_id(url)
  63
  64         data = self._download_json(
  65             'https://archive.vine.co/posts/%s.json' % video_id, video_id)
  66
  67         def video_url(kind):
  68             for url_suffix in ('Url', 'URL'):
  69                 format_url = data.get('video%s%s' % (kind, url_suffix))
  70                 if format_url:
  71                     return format_url
  72
  73         formats = []
  74         for quality, format_id in enumerate(('low', '', 'dash')):
  75             format_url = video_url(format_id.capitalize())
  76             if not format_url:
  77                 continue
  78             # DASH link returns plain mp4
  79             if format_id == 'dash' and determine_ext(format_url) == 'mpd':
  80                 formats.extend(self._extract_mpd_formats(
  81                     format_url, video_id, mpd_id='dash', fatal=False))
  82             else:
  83                 formats.append({
  84                     'url': format_url,
  85                     'format_id': format_id or 'standard',
  86                     'quality': quality,
  87                 })
  88         self._check_formats(formats, video_id)
  89         self._sort_formats(formats)
  90
  91         username = data.get('username')
  92
  93         alt_title = format_field(username, None, 'Vine by %s')
  94
  95         return {
  96             'id': video_id,
  97             'title': data.get('description') or alt_title or 'Vine video',
  98             'alt_title': alt_title,
  99             'thumbnail': data.get('thumbnailUrl'),
 100             'timestamp': unified_timestamp(data.get('created')),
 101             'uploader': username,
 102             'uploader_id': data.get('userIdStr'),
 103             'view_count': int_or_none(data.get('loops')),
 104             'like_count': int_or_none(data.get('likes')),
 105             'comment_count': int_or_none(data.get('comments')),
 106             'repost_count': int_or_none(data.get('reposts')),
 107             'formats': formats,
 108         }
 109
 110
 111 class VineUserIE(InfoExtractor):
 112     IE_NAME = 'vine:user'
 113     _VALID_URL = r'https?://vine\.co/(?P<u>u/)?(?P<user>[^/]+)'
 114     _VINE_BASE_URL = 'https://vine.co/'
 115     _TESTS = [{
 116         'url': 'https://vine.co/itsruthb',
 117         'info_dict': {
 118             'id': 'itsruthb',
 119             'title': 'Ruth B',
 120             'description': '| Instagram/Twitter: itsruthb | still a lost boy from neverland',
 121         },
 122         'playlist_mincount': 611,
 123     }, {
 124         'url': 'https://vine.co/u/942914934646415360',
 125         'only_matching': True,
 126     }]
 127
 128     @classmethod
 129     def suitable(cls, url):
 130         return False if VineIE.suitable(url) else super(VineUserIE, cls).suitable(url)
 131
 132     def _real_extract(self, url):
 133         mobj = self._match_valid_url(url)
 134         user = mobj.group('user')
 135         u = mobj.group('u')
 136
 137         profile_url = '%sapi/users/profiles/%s%s' % (
 138             self._VINE_BASE_URL, 'vanity/' if not u else '', user)
 139         profile_data = self._download_json(
 140             profile_url, user, note='Downloading user profile data')
 141
 142         data = profile_data['data']
 143         user_id = data.get('userId') or data['userIdStr']
 144         profile = self._download_json(
 145             'https://archive.vine.co/profiles/%s.json' % user_id, user_id)
 146         entries = [
 147             self.url_result(
 148                 'https://vine.co/v/%s' % post_id, ie='Vine', video_id=post_id)
 149             for post_id in profile['posts']
 150             if post_id and isinstance(post_id, compat_str)]
 151         return self.playlist_result(
 152             entries, user, profile.get('username'), profile.get('description'))