yt_dlp/extractor/vine.py

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