yt_dlp/extractor/gfycat.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     float_or_none,
   7     qualities,
   8     ExtractorError,
   9 )
  10
  11
  12 class GfycatIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:(?:www|giant|thumbs)\.)?gfycat\.com/(?i:ru/|ifr/|gifs/detail/)?(?P<id>[^-/?#\."\']+)'
  14     _TESTS = [{
  15         'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher',
  16         'info_dict': {
  17             'id': 'DeadlyDecisiveGermanpinscher',
  18             'ext': 'mp4',
  19             'title': 'Ghost in the Shell',
  20             'timestamp': 1410656006,
  21             'upload_date': '20140914',
  22             'uploader': 'anonymous',
  23             'duration': 10.4,
  24             'view_count': int,
  25             'like_count': int,
  26             'categories': list,
  27             'age_limit': 0,
  28             'uploader_id': 'anonymous',
  29             'description': '',
  30         }
  31     }, {
  32         'url': 'http://gfycat.com/ifr/JauntyTimelyAmazontreeboa',
  33         'info_dict': {
  34             'id': 'JauntyTimelyAmazontreeboa',
  35             'ext': 'mp4',
  36             'title': 'JauntyTimelyAmazontreeboa',
  37             'timestamp': 1411720126,
  38             'upload_date': '20140926',
  39             'uploader': 'anonymous',
  40             'duration': 3.52,
  41             'view_count': int,
  42             'like_count': int,
  43             'categories': list,
  44             'age_limit': 0,
  45             'uploader_id': 'anonymous',
  46             'description': '',
  47         }
  48     }, {
  49         'url': 'https://gfycat.com/alienatedsolidgreathornedowl',
  50         'info_dict': {
  51             'id': 'alienatedsolidgreathornedowl',
  52             'ext': 'mp4',
  53             'upload_date': '20211226',
  54             'uploader_id': 'reactions',
  55             'timestamp': 1640536930,
  56             'like_count': int,
  57             'description': '',
  58             'title': 'Ingrid Michaelson, Zooey Deschanel - Merry Christmas Happy New Year',
  59             'categories': list,
  60             'age_limit': 0,
  61             'duration': 2.9583333333333335,
  62             'uploader': 'Reaction GIFs',
  63             'view_count': int,
  64         }
  65     }, {
  66         'url': 'https://gfycat.com/ru/RemarkableDrearyAmurstarfish',
  67         'only_matching': True
  68     }, {
  69         'url': 'https://gfycat.com/gifs/detail/UnconsciousLankyIvorygull',
  70         'only_matching': True
  71     }, {
  72         'url': 'https://gfycat.com/acceptablehappygoluckyharborporpoise-baseball',
  73         'only_matching': True
  74     }, {
  75         'url': 'https://thumbs.gfycat.com/acceptablehappygoluckyharborporpoise-size_restricted.gif',
  76         'only_matching': True
  77     }, {
  78         'url': 'https://giant.gfycat.com/acceptablehappygoluckyharborporpoise.mp4',
  79         'only_matching': True
  80     }, {
  81         'url': 'http://gfycat.com/IFR/JauntyTimelyAmazontreeboa',
  82         'only_matching': True
  83     }]
  84
  85     @staticmethod
  86     def _extract_urls(webpage):
  87         return [
  88             mobj.group('url')
  89             for mobj in re.finditer(
  90                 r'<(?:iframe|source)[^>]+\bsrc=["\'](?P<url>%s)' % GfycatIE._VALID_URL,
  91                 webpage)]
  92
  93     def _real_extract(self, url):
  94         video_id = self._match_id(url)
  95
  96         gfy = self._download_json(
  97             'https://api.gfycat.com/v1/gfycats/%s' % video_id,
  98             video_id, 'Downloading video info')
  99         if 'error' in gfy:
 100             raise ExtractorError('Gfycat said: ' + gfy['error'], expected=True)
 101         gfy = gfy['gfyItem']
 102
 103         title = gfy.get('title') or gfy['gfyName']
 104         description = gfy.get('description')
 105         timestamp = int_or_none(gfy.get('createDate'))
 106         uploader = gfy.get('userName') or gfy.get('username')
 107         view_count = int_or_none(gfy.get('views'))
 108         like_count = int_or_none(gfy.get('likes'))
 109         dislike_count = int_or_none(gfy.get('dislikes'))
 110         age_limit = 18 if gfy.get('nsfw') == '1' else 0
 111
 112         width = int_or_none(gfy.get('width'))
 113         height = int_or_none(gfy.get('height'))
 114         fps = int_or_none(gfy.get('frameRate'))
 115         num_frames = int_or_none(gfy.get('numFrames'))
 116
 117         duration = float_or_none(num_frames, fps) if num_frames and fps else None
 118
 119         categories = gfy.get('tags') or gfy.get('extraLemmas') or []
 120
 121         FORMATS = ('gif', 'webm', 'mp4')
 122         quality = qualities(FORMATS)
 123
 124         formats = []
 125         for format_id in FORMATS:
 126             video_url = gfy.get('%sUrl' % format_id)
 127             if not video_url:
 128                 continue
 129             filesize = int_or_none(gfy.get('%sSize' % format_id))
 130             formats.append({
 131                 'url': video_url,
 132                 'format_id': format_id,
 133                 'width': width,
 134                 'height': height,
 135                 'fps': fps,
 136                 'filesize': filesize,
 137                 'quality': quality(format_id),
 138             })
 139         self._sort_formats(formats)
 140
 141         return {
 142             'id': video_id,
 143             'title': title,
 144             'description': description,
 145             'timestamp': timestamp,
 146             'uploader': gfy.get('userDisplayName') or uploader,
 147             'uploader_id': uploader,
 148             'duration': duration,
 149             'view_count': view_count,
 150             'like_count': like_count,
 151             'dislike_count': dislike_count,
 152             'categories': categories,
 153             'age_limit': age_limit,
 154             'formats': formats,
 155         }