Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/xminus.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_chr,
   9     compat_ord,
  10 )
  11 from ..utils import (
  12     int_or_none,
  13     parse_filesize,
  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 шофера',
  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'minus_track\.artist="(.+?)"', webpage, 'artist')
  40         title = artist + '-' + self._html_search_regex(
  41             r'minus_track\.title="(.+?)"', webpage, 'title')
  42         duration = int_or_none(self._html_search_regex(
  43             r'minus_track\.dur_sec=\'([0-9]*?)\'',
  44             webpage, 'duration', fatal=False))
  45         filesize_approx = parse_filesize(self._html_search_regex(
  46             r'<div id="finfo"[^>]*>\s*↓\s*([0-9.]+\s*[a-zA-Z][bB])',
  47             webpage, 'approximate filesize', fatal=False))
  48         tbr = int_or_none(self._html_search_regex(
  49             r'<div class="quality[^"]*"></div>\s*([0-9]+)\s*kbps',
  50             webpage, 'bitrate', fatal=False))
  51         view_count = int_or_none(self._html_search_regex(
  52             r'<div class="quality.*?► ([0-9]+)',
  53             webpage, 'view count', fatal=False))
  54         description = self._html_search_regex(
  55             r'(?s)<div id="song_texts">(.*?)</div><br',
  56             webpage, 'song lyrics', fatal=False)
  57         if description:
  58             description = re.sub(' *\r *', '\n', description)
  59
  60         enc_token = self._html_search_regex(
  61             r'minus_track\.s?tkn="(.+?)"', webpage, 'enc_token')
  62         token = ''.join(
  63             c if pos == 3 else compat_chr(compat_ord(c) - 1)
  64             for pos, c in enumerate(reversed(enc_token)))
  65         video_url = 'http://x-minus.org/dwlf/%s/%s.mp3' % (video_id, token)
  66
  67         return {
  68             'id': video_id,
  69             'title': title,
  70             'url': video_url,
  71             'duration': duration,
  72             'filesize_approx': filesize_approx,
  73             'tbr': tbr,
  74             'view_count': view_count,
  75             'description': description,
  76         }