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