yt_dlp/extractor/clippit.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     parse_iso8601,
   6     qualities,
   7 )
   8
   9
  10 class ClippitIE(InfoExtractor):
  11
  12     _VALID_URL = r'https?://(?:www\.)?clippituser\.tv/c/(?P<id>[a-z]+)'
  13     _TEST = {
  14         'url': 'https://www.clippituser.tv/c/evmgm',
  15         'md5': '963ae7a59a2ec4572ab8bf2f2d2c5f09',
  16         'info_dict': {
  17             'id': 'evmgm',
  18             'ext': 'mp4',
  19             'title': 'Bye bye Brutus. #BattleBots  - Clippit',
  20             'uploader': 'lizllove',
  21             'uploader_url': 'https://www.clippituser.tv/p/lizllove',
  22             'timestamp': 1472183818,
  23             'upload_date': '20160826',
  24             'description': 'BattleBots | ABC',
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26         },
  27     }
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31         webpage = self._download_webpage(url, video_id)
  32
  33         title = self._html_search_regex(r'<title.*>(.+?)</title>', webpage, 'title')
  34
  35         FORMATS = ('sd', 'hd')
  36         quality = qualities(FORMATS)
  37         formats = []
  38         for format_id in FORMATS:
  39             url = self._html_search_regex(rf'data-{format_id}-file="(.+?)"',
  40                                           webpage, 'url', fatal=False)
  41             if not url:
  42                 continue
  43             match = re.search(r'/(?P<height>\d+)\.mp4', url)
  44             formats.append({
  45                 'url': url,
  46                 'format_id': format_id,
  47                 'quality': quality(format_id),
  48                 'height': int(match.group('height')) if match else None,
  49             })
  50
  51         uploader = self._html_search_regex(r'class="username".*>\s+(.+?)\n',
  52                                            webpage, 'uploader', fatal=False)
  53         uploader_url = ('https://www.clippituser.tv/p/' + uploader
  54                         if uploader else None)
  55
  56         timestamp = self._html_search_regex(r'datetime="(.+?)"',
  57                                             webpage, 'date', fatal=False)
  58         thumbnail = self._html_search_regex(r'data-image="(.+?)"',
  59                                             webpage, 'thumbnail', fatal=False)
  60
  61         return {
  62             'id': video_id,
  63             'title': title,
  64             'formats': formats,
  65             'uploader': uploader,
  66             'uploader_url': uploader_url,
  67             'timestamp': parse_iso8601(timestamp),
  68             'description': self._og_search_description(webpage),
  69             'thumbnail': thumbnail,
  70         }