Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/gfycat.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     float_or_none,
   8     qualities,
   9     ExtractorError,
  10 )
  11
  12
  13 class GfycatIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?:ifr/|gifs/detail/)?(?P<id>[^-/?#]+)'
  15     _TESTS = [{
  16         'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher',
  17         'info_dict': {
  18             'id': 'DeadlyDecisiveGermanpinscher',
  19             'ext': 'mp4',
  20             'title': 'Ghost in the Shell',
  21             'timestamp': 1410656006,
  22             'upload_date': '20140914',
  23             'uploader': 'anonymous',
  24             'duration': 10.4,
  25             'view_count': int,
  26             'like_count': int,
  27             'dislike_count': int,
  28             'categories': list,
  29             'age_limit': 0,
  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             'dislike_count': int,
  44             'categories': list,
  45             'age_limit': 0,
  46         }
  47     }, {
  48         'url': 'https://gfycat.com/gifs/detail/UnconsciousLankyIvorygull',
  49         'only_matching': True
  50     }, {
  51         'url': 'https://gfycat.com/acceptablehappygoluckyharborporpoise-baseball',
  52         'only_matching': True
  53     }]
  54
  55     def _real_extract(self, url):
  56         video_id = self._match_id(url)
  57
  58         gfy = self._download_json(
  59             'https://api.gfycat.com/v1/gfycats/%s' % video_id,
  60             video_id, 'Downloading video info')
  61         if 'error' in gfy:
  62             raise ExtractorError('Gfycat said: ' + gfy['error'], expected=True)
  63         gfy = gfy['gfyItem']
  64
  65         title = gfy.get('title') or gfy['gfyName']
  66         description = gfy.get('description')
  67         timestamp = int_or_none(gfy.get('createDate'))
  68         uploader = gfy.get('userName')
  69         view_count = int_or_none(gfy.get('views'))
  70         like_count = int_or_none(gfy.get('likes'))
  71         dislike_count = int_or_none(gfy.get('dislikes'))
  72         age_limit = 18 if gfy.get('nsfw') == '1' else 0
  73
  74         width = int_or_none(gfy.get('width'))
  75         height = int_or_none(gfy.get('height'))
  76         fps = int_or_none(gfy.get('frameRate'))
  77         num_frames = int_or_none(gfy.get('numFrames'))
  78
  79         duration = float_or_none(num_frames, fps) if num_frames and fps else None
  80
  81         categories = gfy.get('tags') or gfy.get('extraLemmas') or []
  82
  83         FORMATS = ('gif', 'webm', 'mp4')
  84         quality = qualities(FORMATS)
  85
  86         formats = []
  87         for format_id in FORMATS:
  88             video_url = gfy.get('%sUrl' % format_id)
  89             if not video_url:
  90                 continue
  91             filesize = int_or_none(gfy.get('%sSize' % format_id))
  92             formats.append({
  93                 'url': video_url,
  94                 'format_id': format_id,
  95                 'width': width,
  96                 'height': height,
  97                 'fps': fps,
  98                 'filesize': filesize,
  99                 'quality': quality(format_id),
 100             })
 101         self._sort_formats(formats)
 102
 103         return {
 104             'id': video_id,
 105             'title': title,
 106             'description': description,
 107             'timestamp': timestamp,
 108             'uploader': uploader,
 109             'duration': duration,
 110             'view_count': view_count,
 111             'like_count': like_count,
 112             'dislike_count': dislike_count,
 113             'categories': categories,
 114             'age_limit': age_limit,
 115             'formats': formats,
 116         }