_ Git - youtube-dl/blob - youtube_dl/extractor/xminus.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import (
   6     compat_chr,
   7     compat_ord,
   8 )
   9 from ..utils import (
  10     int_or_none,
  11     parse_filesize,
  12 )
  13
  14
  15 class XMinusIE(InfoExtractor):
  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 шофера',
  24             'duration': 156,
  25             'tbr': 320,
  26             'filesize_approx': 5900000,
  27             'view_count': int,
  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'minus_track\.artist="(.+?)"', webpage, 'artist')
  37         title = artist + '-' + self._html_search_regex(
  38             r'minus_track\.title="(.+?)"', webpage, 'title')
  39         duration = int_or_none(self._html_search_regex(
  40             r'minus_track\.dur_sec=\'([0-9]*?)\'',
  41             webpage, 'duration', fatal=False))
  42         filesize_approx = parse_filesize(self._html_search_regex(
  43             r'<div class="filesize[^"]*"></div>\s*([0-9.]+\s*[a-zA-Z][bB])',
  44             webpage, 'approximate filesize', fatal=False))
  45         tbr = int_or_none(self._html_search_regex(
  46             r'<div class="quality[^"]*"></div>\s*([0-9]+)\s*kbps',
  47             webpage, 'bitrate', fatal=False))
  48         view_count = int_or_none(self._html_search_regex(
  49             r'<div class="quality.*?► ([0-9]+)',
  50             webpage, 'view count', fatal=False))
  51
  52         enc_token = self._html_search_regex(
  53             r'data-mt="(.*?)"', webpage, 'enc_token')
  54         token = ''.join(
  55             c if pos == 3 else compat_chr(compat_ord(c) - 1)
  56             for pos, c in enumerate(reversed(enc_token)))
  57         video_url = 'http://x-minus.org/dwlf/%s/%s.mp3' % (video_id, token)
  58
  59         return {
  60             'id': video_id,
  61             'title': title,
  62             'url': video_url,
  63             'duration': duration,
  64             'filesize_approx': filesize_approx,
  65             'tbr': tbr,
  66             'view_count': view_count,
  67         }