yt_dlp/extractor/dtube.py

   1 import json
   2 from socket import timeout
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     parse_iso8601,
   8 )
   9
  10
  11 class DTubeIE(InfoExtractor):
  12     _WORKING = False
  13     _VALID_URL = r'https?://(?:www\.)?d\.tube/(?:#!/)?v/(?P<uploader_id>[0-9a-z.-]+)/(?P<id>[0-9a-z]{8})'
  14     _TEST = {
  15         'url': 'https://d.tube/#!/v/broncnutz/x380jtr1',
  16         'md5': '9f29088fa08d699a7565ee983f56a06e',
  17         'info_dict': {
  18             'id': 'x380jtr1',
  19             'ext': 'mp4',
  20             'title': 'Lefty 3-Rings is Back Baby!! NCAA Picks',
  21             'description': 'md5:60be222088183be3a42f196f34235776',
  22             'uploader_id': 'broncnutz',
  23             'upload_date': '20190107',
  24             'timestamp': 1546854054,
  25         },
  26         'params': {
  27             'format': '480p',
  28         },
  29     }
  30
  31     def _real_extract(self, url):
  32         uploader_id, video_id = self._match_valid_url(url).groups()
  33         result = self._download_json('https://api.steemit.com/', video_id, data=json.dumps({
  34             'jsonrpc': '2.0',
  35             'method': 'get_content',
  36             'params': [uploader_id, video_id],
  37         }).encode())['result']
  38
  39         metadata = json.loads(result['json_metadata'])
  40         video = metadata['video']
  41         content = video['content']
  42         info = video.get('info', {})
  43         title = info.get('title') or result['title']
  44
  45         def canonical_url(h):
  46             if not h:
  47                 return None
  48             return 'https://video.dtube.top/ipfs/' + h
  49
  50         formats = []
  51         for q in ('240', '480', '720', '1080', ''):
  52             video_url = canonical_url(content.get('video%shash' % q))
  53             if not video_url:
  54                 continue
  55             format_id = (q + 'p') if q else 'Source'
  56             try:
  57                 self.to_screen('%s: Checking %s video format URL' % (video_id, format_id))
  58                 self._downloader._opener.open(video_url, timeout=5).close()
  59             except timeout:
  60                 self.to_screen(
  61                     '%s: %s URL is invalid, skipping' % (video_id, format_id))
  62                 continue
  63             formats.append({
  64                 'format_id': format_id,
  65                 'url': video_url,
  66                 'height': int_or_none(q),
  67                 'ext': 'mp4',
  68             })
  69
  70         return {
  71             'id': video_id,
  72             'title': title,
  73             'description': content.get('description'),
  74             'thumbnail': canonical_url(info.get('snaphash')),
  75             'tags': content.get('tags') or metadata.get('tags'),
  76             'duration': info.get('duration'),
  77             'formats': formats,
  78             'timestamp': parse_iso8601(result.get('created')),
  79             'uploader_id': uploader_id,
  80         }