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 )
  10
  11
  12 class GfycatIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?P<id>[^/?#]+)'
  14     _TEST = {
  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             'dislike_count': int,
  27             'categories': list,
  28             'age_limit': 0,
  29         }
  30     }
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34
  35         gfy = self._download_json(
  36             'http://gfycat.com/cajax/get/%s' % video_id,
  37             video_id, 'Downloading video info')['gfyItem']
  38
  39         title = gfy.get('title') or gfy['gfyName']
  40         description = gfy.get('description')
  41         timestamp = int_or_none(gfy.get('createDate'))
  42         uploader = gfy.get('userName')
  43         view_count = int_or_none(gfy.get('views'))
  44         like_count = int_or_none(gfy.get('likes'))
  45         dislike_count = int_or_none(gfy.get('dislikes'))
  46         age_limit = 18 if gfy.get('nsfw') == '1' else 0
  47
  48         width = int_or_none(gfy.get('width'))
  49         height = int_or_none(gfy.get('height'))
  50         fps = int_or_none(gfy.get('frameRate'))
  51         num_frames = int_or_none(gfy.get('numFrames'))
  52
  53         duration = float_or_none(num_frames, fps) if num_frames and fps else None
  54
  55         categories = gfy.get('tags') or gfy.get('extraLemmas') or []
  56
  57         FORMATS = ('gif', 'webm', 'mp4')
  58         quality = qualities(FORMATS)
  59
  60         formats = []
  61         for format_id in FORMATS:
  62             video_url = gfy.get('%sUrl' % format_id)
  63             if not video_url:
  64                 continue
  65             filesize = gfy.get('%sSize' % format_id)
  66             formats.append({
  67                 'url': video_url,
  68                 'format_id': format_id,
  69                 'width': width,
  70                 'height': height,
  71                 'fps': fps,
  72                 'filesize': filesize,
  73                 'quality': quality(format_id),
  74             })
  75         self._sort_formats(formats)
  76
  77         return {
  78             'id': video_id,
  79             'title': title,
  80             'description': description,
  81             'timestamp': timestamp,
  82             'uploader': uploader,
  83             'duration': duration,
  84             'view_count': view_count,
  85             'like_count': like_count,
  86             'dislike_count': dislike_count,
  87             'categories': categories,
  88             'age_limit': age_limit,
  89             'formats': formats,
  90         }