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/)?(?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
  49     def _real_extract(self, url):
  50         video_id = self._match_id(url)
  51
  52         gfy = self._download_json(
  53             'http://gfycat.com/cajax/get/%s' % video_id,
  54             video_id, 'Downloading video info')
  55         if 'error' in gfy:
  56             raise ExtractorError('Gfycat said: ' + gfy['error'], expected=True)
  57         gfy = gfy['gfyItem']
  58
  59         title = gfy.get('title') or gfy['gfyName']
  60         description = gfy.get('description')
  61         timestamp = int_or_none(gfy.get('createDate'))
  62         uploader = gfy.get('userName')
  63         view_count = int_or_none(gfy.get('views'))
  64         like_count = int_or_none(gfy.get('likes'))
  65         dislike_count = int_or_none(gfy.get('dislikes'))
  66         age_limit = 18 if gfy.get('nsfw') == '1' else 0
  67
  68         width = int_or_none(gfy.get('width'))
  69         height = int_or_none(gfy.get('height'))
  70         fps = int_or_none(gfy.get('frameRate'))
  71         num_frames = int_or_none(gfy.get('numFrames'))
  72
  73         duration = float_or_none(num_frames, fps) if num_frames and fps else None
  74
  75         categories = gfy.get('tags') or gfy.get('extraLemmas') or []
  76
  77         FORMATS = ('gif', 'webm', 'mp4')
  78         quality = qualities(FORMATS)
  79
  80         formats = []
  81         for format_id in FORMATS:
  82             video_url = gfy.get('%sUrl' % format_id)
  83             if not video_url:
  84                 continue
  85             filesize = gfy.get('%sSize' % format_id)
  86             formats.append({
  87                 'url': video_url,
  88                 'format_id': format_id,
  89                 'width': width,
  90                 'height': height,
  91                 'fps': fps,
  92                 'filesize': filesize,
  93                 'quality': quality(format_id),
  94             })
  95         self._sort_formats(formats)
  96
  97         return {
  98             'id': video_id,
  99             'title': title,
 100             'description': description,
 101             'timestamp': timestamp,
 102             'uploader': uploader,
 103             'duration': duration,
 104             'view_count': view_count,
 105             'like_count': like_count,
 106             'dislike_count': dislike_count,
 107             'categories': categories,
 108             'age_limit': age_limit,
 109             'formats': formats,
 110         }