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