youtube_dl/extractor/xminus.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import time
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_ord,
  10 )
  11 from ..utils import (
  12     int_or_none,
  13     parse_duration,
  14 )
  15
  16
  17 class XMinusIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:www\.)?x-minus\.org/track/(?P<id>[0-9]+)'
  19     _TEST = {
  20         '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',
  21         'md5': '401a15f2d2dcf6d592cb95528d72a2a8',
  22         'info_dict': {
  23             'id': '4542',
  24             'ext': 'mp3',
  25             'title': 'Леонид Агутин-Песенка шофёра',
  26             'duration': 156,
  27             'tbr': 320,
  28             'filesize_approx': 5900000,
  29             'view_count': int,
  30             'description': 'md5:03238c5b663810bc79cf42ef3c03e371',
  31         }
  32     }
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url)
  36         webpage = self._download_webpage(url, video_id)
  37
  38         artist = self._html_search_regex(
  39             r'<a[^>]+href="/artist/\d+">([^<]+)</a>', webpage, 'artist')
  40         title = artist + '-' + self._html_search_regex(
  41             r'<span[^>]+class="minustrack-full-title(?:\s+[^"]+)?"[^>]*>([^<]+)', webpage, 'title')
  42         duration = parse_duration(self._html_search_regex(
  43             r'<span[^>]+class="player-duration(?:\s+[^"]+)?"[^>]*>([^<]+)',
  44             webpage, 'duration', fatal=False))
  45         mobj = re.search(
  46             r'<div[^>]+class="dw-info(?:\s+[^"]+)?"[^>]*>(?P<tbr>\d+)\s*кбит/c\s+(?P<filesize>[0-9.]+)\s*мб</div>',
  47             webpage)
  48         tbr = filesize_approx = None
  49         if mobj:
  50             filesize_approx = float(mobj.group('filesize')) * 1000000
  51             tbr = float(mobj.group('tbr'))
  52         view_count = int_or_none(self._html_search_regex(
  53             r'<span><[^>]+class="icon-chart-bar".*?>(\d+)</span>',
  54             webpage, 'view count', fatal=False))
  55         description = self._html_search_regex(
  56             r'(?s)<pre[^>]+id="lyrics-original"[^>]*>(.*?)</pre>',
  57             webpage, 'song lyrics', fatal=False)
  58         if description:
  59             description = re.sub(' *\r *', '\n', description)
  60
  61         k = self._search_regex(
  62             r'<div[^>]+id="player-bottom"[^>]+data-k="([^"]+)">', webpage,
  63             'encoded data')
  64         h = time.time() / 3600
  65         a = sum(map(int, [compat_ord(c) for c in k])) + int(video_id) + h
  66         video_url = 'http://x-minus.me/dl/minus?id=%s&tkn2=%df%d' % (video_id, a, h)
  67
  68         return {
  69             'id': video_id,
  70             'title': title,
  71             'url': video_url,
  72             # The extension is unknown until actual downloading
  73             'ext': 'mp3',
  74             'duration': duration,
  75             'filesize_approx': filesize_approx,
  76             'tbr': tbr,
  77             'view_count': view_count,
  78             'description': description,
  79         }