yt_dlp/extractor/chirbit.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_b64decode
   5 from ..utils import parse_duration
   6
   7
   8 class ChirbitIE(InfoExtractor):
   9     IE_NAME = 'chirbit'
  10     _VALID_URL = r'https?://(?:www\.)?chirb\.it/(?:(?:wp|pl)/|fb_chirbit_player\.swf\?key=)?(?P<id>[\da-zA-Z]+)'
  11     _TESTS = [{
  12         'url': 'http://chirb.it/be2abG',
  13         'info_dict': {
  14             'id': 'be2abG',
  15             'ext': 'mp3',
  16             'title': 'md5:f542ea253f5255240be4da375c6a5d7e',
  17             'description': 'md5:f24a4e22a71763e32da5fed59e47c770',
  18             'duration': 306,
  19             'uploader': 'Gerryaudio',
  20         },
  21         'params': {
  22             'skip_download': True,
  23         }
  24     }, {
  25         'url': 'https://chirb.it/fb_chirbit_player.swf?key=PrIPv5',
  26         'only_matching': True,
  27     }, {
  28         'url': 'https://chirb.it/wp/MN58c2',
  29         'only_matching': True,
  30     }]
  31
  32     def _real_extract(self, url):
  33         audio_id = self._match_id(url)
  34
  35         webpage = self._download_webpage(
  36             'http://chirb.it/%s' % audio_id, audio_id)
  37
  38         data_fd = self._search_regex(
  39             r'data-fd=(["\'])(?P<url>(?:(?!\1).)+)\1',
  40             webpage, 'data fd', group='url')
  41
  42         # Reverse engineered from https://chirb.it/js/chirbit.player.js (look
  43         # for soundURL)
  44         audio_url = compat_b64decode(data_fd[::-1]).decode('utf-8')
  45
  46         title = self._search_regex(
  47             r'class=["\']chirbit-title["\'][^>]*>([^<]+)', webpage, 'title')
  48         description = self._search_regex(
  49             r'<h3>Description</h3>\s*<pre[^>]*>([^<]+)</pre>',
  50             webpage, 'description', default=None)
  51         duration = parse_duration(self._search_regex(
  52             r'class=["\']c-length["\'][^>]*>([^<]+)',
  53             webpage, 'duration', fatal=False))
  54         uploader = self._search_regex(
  55             r'id=["\']chirbit-username["\'][^>]*>([^<]+)',
  56             webpage, 'uploader', fatal=False)
  57
  58         return {
  59             'id': audio_id,
  60             'url': audio_url,
  61             'title': title,
  62             'description': description,
  63             'duration': duration,
  64             'uploader': uploader,
  65         }
  66
  67
  68 class ChirbitProfileIE(InfoExtractor):
  69     IE_NAME = 'chirbit:profile'
  70     _VALID_URL = r'https?://(?:www\.)?chirbit\.com/(?:rss/)?(?P<id>[^/]+)'
  71     _TEST = {
  72         'url': 'http://chirbit.com/ScarletBeauty',
  73         'info_dict': {
  74             'id': 'ScarletBeauty',
  75         },
  76         'playlist_mincount': 3,
  77     }
  78
  79     def _real_extract(self, url):
  80         profile_id = self._match_id(url)
  81
  82         webpage = self._download_webpage(url, profile_id)
  83
  84         entries = [
  85             self.url_result(self._proto_relative_url('//chirb.it/' + video_id))
  86             for _, video_id in re.findall(r'<input[^>]+id=([\'"])copy-btn-(?P<id>[0-9a-zA-Z]+)\1', webpage)]
  87
  88         return self.playlist_result(entries, profile_id)