yt_dlp/extractor/xminus.py

   1 import re
   2 import time
   3
   4 from .common import InfoExtractor
   5 from ..compat import (
   6     compat_ord,
   7 )
   8 from ..utils import (
   9     int_or_none,
  10     parse_duration,
  11 )
  12
  13
  14 class XMinusIE(InfoExtractor):
  15     _WORKING = False
  16     _VALID_URL = r'https?://(?:www\.)?x-minus\.org/track/(?P<id>[0-9]+)'
  17     _TEST = {
  18         'url': 'http://x-minus.org/track/4542/%D0%BF%D0%B5%D1%81%D0%B5%D0%BD%D0%BA%D0%B0-%D1%88%D0%BE%D1%84%D0%B5%D1%80%D0%B0.html',
  19         'md5': '401a15f2d2dcf6d592cb95528d72a2a8',
  20         'info_dict': {
  21             'id': '4542',
  22             'ext': 'mp3',
  23             'title': 'Леонид Агутин-Песенка шофёра',
  24             'duration': 156,
  25             'tbr': 320,
  26             'filesize_approx': 5900000,
  27             'view_count': int,
  28             'description': 'md5:03238c5b663810bc79cf42ef3c03e371',
  29         },
  30     }
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34         webpage = self._download_webpage(url, video_id)
  35
  36         artist = self._html_search_regex(
  37             r'<a[^>]+href="/artist/\d+">([^<]+)</a>', webpage, 'artist')
  38         title = artist + '-' + self._html_search_regex(
  39             r'<span[^>]+class="minustrack-full-title(?:\s+[^"]+)?"[^>]*>([^<]+)', webpage, 'title')
  40         duration = parse_duration(self._html_search_regex(
  41             r'<span[^>]+class="player-duration(?:\s+[^"]+)?"[^>]*>([^<]+)',
  42             webpage, 'duration', fatal=False))
  43         mobj = re.search(
  44             r'<div[^>]+class="dw-info(?:\s+[^"]+)?"[^>]*>(?P<tbr>\d+)\s*кбит/c\s+(?P<filesize>[0-9.]+)\s*мб</div>',
  45             webpage)
  46         tbr = filesize_approx = None
  47         if mobj:
  48             filesize_approx = float(mobj.group('filesize')) * 1000000
  49             tbr = float(mobj.group('tbr'))
  50         view_count = int_or_none(self._html_search_regex(
  51             r'<span><[^>]+class="icon-chart-bar".*?>(\d+)</span>',
  52             webpage, 'view count', fatal=False))
  53         description = self._html_search_regex(
  54             r'(?s)<pre[^>]+id="lyrics-original"[^>]*>(.*?)</pre>',
  55             webpage, 'song lyrics', fatal=False)
  56         if description:
  57             description = re.sub(' *\r *', '\n', description)
  58
  59         k = self._search_regex(
  60             r'<div[^>]+id="player-bottom"[^>]+data-k="([^"]+)">', webpage,
  61             'encoded data')
  62         h = time.time() / 3600
  63         a = sum(map(int, [compat_ord(c) for c in k])) + int(video_id) + h
  64         video_url = 'http://x-minus.me/dl/minus?id=%s&tkn2=%df%d' % (video_id, a, h)
  65
  66         return {
  67             'id': video_id,
  68             'title': title,
  69             'url': video_url,
  70             # The extension is unknown until actual downloading
  71             'ext': 'mp3',
  72             'duration': duration,
  73             'filesize_approx': filesize_approx,
  74             'tbr': tbr,
  75             'view_count': view_count,
  76             'description': description,
  77         }