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|giant|thumbs)\.)?gfycat\.com/(?:ru/|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/ru/RemarkableDrearyAmurstarfish',
  49         'only_matching': True
  50     }, {
  51         'url': 'https://gfycat.com/gifs/detail/UnconsciousLankyIvorygull',
  52         'only_matching': True
  53     }, {
  54         'url': 'https://gfycat.com/acceptablehappygoluckyharborporpoise-baseball',
  55         'only_matching': True
  56     }, {
  57         'url': 'https://thumbs.gfycat.com/acceptablehappygoluckyharborporpoise-size_restricted.gif',
  58         'only_matching': True
  59     }, {
  60         'url': 'https://giant.gfycat.com/acceptablehappygoluckyharborporpoise.mp4',
  61         'only_matching': True
  62     }]
  63
  64     def _real_extract(self, url):
  65         video_id = self._match_id(url)
  66
  67         gfy = self._download_json(
  68             'https://api.gfycat.com/v1/gfycats/%s' % video_id,
  69             video_id, 'Downloading video info')
  70         if 'error' in gfy:
  71             raise ExtractorError('Gfycat said: ' + gfy['error'], expected=True)
  72         gfy = gfy['gfyItem']
  73
  74         title = gfy.get('title') or gfy['gfyName']
  75         description = gfy.get('description')
  76         timestamp = int_or_none(gfy.get('createDate'))
  77         uploader = gfy.get('userName')
  78         view_count = int_or_none(gfy.get('views'))
  79         like_count = int_or_none(gfy.get('likes'))
  80         dislike_count = int_or_none(gfy.get('dislikes'))
  81         age_limit = 18 if gfy.get('nsfw') == '1' else 0
  82
  83         width = int_or_none(gfy.get('width'))
  84         height = int_or_none(gfy.get('height'))
  85         fps = int_or_none(gfy.get('frameRate'))
  86         num_frames = int_or_none(gfy.get('numFrames'))
  87
  88         duration = float_or_none(num_frames, fps) if num_frames and fps else None
  89
  90         categories = gfy.get('tags') or gfy.get('extraLemmas') or []
  91
  92         FORMATS = ('gif', 'webm', 'mp4')
  93         quality = qualities(FORMATS)
  94
  95         formats = []
  96         for format_id in FORMATS:
  97             video_url = gfy.get('%sUrl' % format_id)
  98             if not video_url:
  99                 continue
 100             filesize = int_or_none(gfy.get('%sSize' % format_id))
 101             formats.append({
 102                 'url': video_url,
 103                 'format_id': format_id,
 104                 'width': width,
 105                 'height': height,
 106                 'fps': fps,
 107                 'filesize': filesize,
 108                 'quality': quality(format_id),
 109             })
 110         self._sort_formats(formats)
 111
 112         return {
 113             'id': video_id,
 114             'title': title,
 115             'description': description,
 116             'timestamp': timestamp,
 117             'uploader': uploader,
 118             'duration': duration,
 119             'view_count': view_count,
 120             'like_count': like_count,
 121             'dislike_count': dislike_count,
 122             'categories': categories,
 123             'age_limit': age_limit,
 124             'formats': formats,
 125         }