yt_dlp/extractor/vine.py

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