youtube_dl/extractor/musicplayon.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urlparse
   6 from ..utils import (
   7     int_or_none,
   8     js_to_json,
   9     mimetype2ext,
  10 )
  11
  12
  13 class MusicPlayOnIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:.+?\.)?musicplayon\.com/play(?:-touch)?\?(?:v|pl=\d+&play)=(?P<id>\d+)'
  15
  16     _TESTS = [{
  17         'url': 'http://en.musicplayon.com/play?v=433377',
  18         'md5': '00cdcdea1726abdf500d1e7fd6dd59bb',
  19         'info_dict': {
  20             'id': '433377',
  21             'ext': 'mp4',
  22             'title': 'Rick Ross - Interview On Chelsea Lately (2014)',
  23             'description': 'Rick Ross Interview On Chelsea Lately',
  24             'duration': 342,
  25             'uploader': 'ultrafish',
  26         },
  27     }, {
  28         'url': 'http://en.musicplayon.com/play?pl=102&play=442629',
  29         'only_matching': True,
  30     }]
  31
  32     _URL_TEMPLATE = 'http://en.musicplayon.com/play?v=%s'
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url)
  36         url = self._URL_TEMPLATE % video_id
  37
  38         page = self._download_webpage(url, video_id)
  39
  40         title = self._og_search_title(page)
  41         description = self._og_search_description(page)
  42         thumbnail = self._og_search_thumbnail(page)
  43         duration = self._html_search_meta('video:duration', page, 'duration', fatal=False)
  44         view_count = self._og_search_property('count', page, fatal=False)
  45         uploader = self._html_search_regex(
  46             r'<div>by&nbsp;<a href="[^"]+" class="purple">([^<]+)</a></div>', page, 'uploader', fatal=False)
  47
  48         sources = self._parse_json(
  49             self._search_regex(r'setup\[\'_sources\'\]\s*=\s*([^;]+);', page, 'video sources'),
  50             video_id, transform_source=js_to_json)
  51         formats = [{
  52             'url': compat_urlparse.urljoin(url, source['src']),
  53             'ext': mimetype2ext(source.get('type')),
  54             'format_note': source.get('data-res'),
  55         } for source in sources]
  56
  57         return {
  58             'id': video_id,
  59             'title': title,
  60             'description': description,
  61             'thumbnail': thumbnail,
  62             'uploader': uploader,
  63             'duration': int_or_none(duration),
  64             'view_count': int_or_none(view_count),
  65             'formats': formats,
  66         }