yt_dlp/extractor/gfycat.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     float_or_none,
   5     qualities,
   6     ExtractorError,
   7 )
   8
   9
  10 class GfycatIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:(?:www|giant|thumbs)\.)?gfycat\.com/(?i:ru/|ifr/|gifs/detail/)?(?P<id>[^-/?#\."\']+)'
  12     _EMBED_REGEX = [rf'<(?:iframe|source)[^>]+\bsrc=["\'](?P<url>{_VALID_URL})']
  13     _TESTS = [{
  14         'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher',
  15         'info_dict': {
  16             'id': 'DeadlyDecisiveGermanpinscher',
  17             'ext': 'mp4',
  18             'title': 'Ghost in the Shell',
  19             'timestamp': 1410656006,
  20             'upload_date': '20140914',
  21             'uploader': 'anonymous',
  22             'duration': 10.4,
  23             'view_count': int,
  24             'like_count': int,
  25             'categories': list,
  26             'age_limit': 0,
  27             'uploader_id': 'anonymous',
  28             'description': '',
  29         }
  30     }, {
  31         'url': 'http://gfycat.com/ifr/JauntyTimelyAmazontreeboa',
  32         'info_dict': {
  33             'id': 'JauntyTimelyAmazontreeboa',
  34             'ext': 'mp4',
  35             'title': 'JauntyTimelyAmazontreeboa',
  36             'timestamp': 1411720126,
  37             'upload_date': '20140926',
  38             'uploader': 'anonymous',
  39             'duration': 3.52,
  40             'view_count': int,
  41             'like_count': int,
  42             'categories': list,
  43             'age_limit': 0,
  44             'uploader_id': 'anonymous',
  45             'description': '',
  46         }
  47     }, {
  48         'url': 'https://gfycat.com/alienatedsolidgreathornedowl',
  49         'info_dict': {
  50             'id': 'alienatedsolidgreathornedowl',
  51             'ext': 'mp4',
  52             'upload_date': '20211226',
  53             'uploader_id': 'reactions',
  54             'timestamp': 1640536930,
  55             'like_count': int,
  56             'description': '',
  57             'title': 'Ingrid Michaelson, Zooey Deschanel - Merry Christmas Happy New Year',
  58             'categories': list,
  59             'age_limit': 0,
  60             'duration': 2.9583333333333335,
  61             'uploader': 'Reaction GIFs',
  62             'view_count': int,
  63         }
  64     }, {
  65         'url': 'https://gfycat.com/ru/RemarkableDrearyAmurstarfish',
  66         'only_matching': True
  67     }, {
  68         'url': 'https://gfycat.com/gifs/detail/UnconsciousLankyIvorygull',
  69         'only_matching': True
  70     }, {
  71         'url': 'https://gfycat.com/acceptablehappygoluckyharborporpoise-baseball',
  72         'only_matching': True
  73     }, {
  74         'url': 'https://thumbs.gfycat.com/acceptablehappygoluckyharborporpoise-size_restricted.gif',
  75         'only_matching': True
  76     }, {
  77         'url': 'https://giant.gfycat.com/acceptablehappygoluckyharborporpoise.mp4',
  78         'only_matching': True
  79     }, {
  80         'url': 'http://gfycat.com/IFR/JauntyTimelyAmazontreeboa',
  81         'only_matching': True
  82     }]
  83
  84     def _real_extract(self, url):
  85         video_id = self._match_id(url)
  86
  87         gfy = self._download_json(
  88             'https://api.gfycat.com/v1/gfycats/%s' % video_id,
  89             video_id, 'Downloading video info')
  90         if 'error' in gfy:
  91             raise ExtractorError('Gfycat said: ' + gfy['error'], expected=True)
  92         gfy = gfy['gfyItem']
  93
  94         title = gfy.get('title') or gfy['gfyName']
  95         description = gfy.get('description')
  96         timestamp = int_or_none(gfy.get('createDate'))
  97         uploader = gfy.get('userName') or gfy.get('username')
  98         view_count = int_or_none(gfy.get('views'))
  99         like_count = int_or_none(gfy.get('likes'))
 100         dislike_count = int_or_none(gfy.get('dislikes'))
 101         age_limit = 18 if gfy.get('nsfw') == '1' else 0
 102
 103         width = int_or_none(gfy.get('width'))
 104         height = int_or_none(gfy.get('height'))
 105         fps = int_or_none(gfy.get('frameRate'))
 106         num_frames = int_or_none(gfy.get('numFrames'))
 107
 108         duration = float_or_none(num_frames, fps) if num_frames and fps else None
 109
 110         categories = gfy.get('tags') or gfy.get('extraLemmas') or []
 111
 112         FORMATS = ('gif', 'webm', 'mp4')
 113         quality = qualities(FORMATS)
 114
 115         formats = []
 116         for format_id in FORMATS:
 117             video_url = gfy.get('%sUrl' % format_id)
 118             if not video_url:
 119                 continue
 120             filesize = int_or_none(gfy.get('%sSize' % format_id))
 121             formats.append({
 122                 'url': video_url,
 123                 'format_id': format_id,
 124                 'width': width,
 125                 'height': height,
 126                 'fps': fps,
 127                 'filesize': filesize,
 128                 'quality': quality(format_id),
 129             })
 130         self._sort_formats(formats)
 131
 132         return {
 133             'id': video_id,
 134             'title': title,
 135             'description': description,
 136             'timestamp': timestamp,
 137             'uploader': gfy.get('userDisplayName') or uploader,
 138             'uploader_id': uploader,
 139             'duration': duration,
 140             'view_count': view_count,
 141             'like_count': like_count,
 142             'dislike_count': dislike_count,
 143             'categories': categories,
 144             'age_limit': age_limit,
 145             'formats': formats,
 146         }