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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import int_or_none
   5
   6
   7 class NewgroundsIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>[0-9]+)'
   9     _TESTS = [{
  10         'url': 'https://www.newgrounds.com/audio/listen/549479',
  11         'md5': 'fe6033d297591288fa1c1f780386f07a',
  12         'info_dict': {
  13             'id': '549479',
  14             'ext': 'mp3',
  15             'title': 'B7 - BusMode',
  16             'uploader': 'Burn7',
  17         }
  18     }, {
  19         'url': 'https://www.newgrounds.com/portal/view/673111',
  20         'md5': '3394735822aab2478c31b1004fe5e5bc',
  21         'info_dict': {
  22             'id': '673111',
  23             'ext': 'mp4',
  24             'title': 'Dancin',
  25             'uploader': 'Squirrelman82',
  26         },
  27     }, {
  28         # source format unavailable, additional mp4 formats
  29         'url': 'http://www.newgrounds.com/portal/view/689400',
  30         'info_dict': {
  31             'id': '689400',
  32             'ext': 'mp4',
  33             'title': 'ZTV News Episode 8',
  34             'uploader': 'BennettTheSage',
  35         },
  36         'params': {
  37             'skip_download': True,
  38         },
  39     }]
  40
  41     def _real_extract(self, url):
  42         media_id = self._match_id(url)
  43
  44         webpage = self._download_webpage(url, media_id)
  45
  46         title = self._html_search_regex(
  47             r'<title>([^>]+)</title>', webpage, 'title')
  48
  49         video_url = self._parse_json(self._search_regex(
  50             r'"url"\s*:\s*("[^"]+"),', webpage, ''), media_id)
  51
  52         formats = [{
  53             'url': video_url,
  54             'format_id': 'source',
  55             'quality': 1,
  56         }]
  57
  58         max_resolution = int_or_none(self._search_regex(
  59             r'max_resolution["\']\s*:\s*(\d+)', webpage, 'max resolution',
  60             default=None))
  61         if max_resolution:
  62             url_base = video_url.rpartition('.')[0]
  63             for resolution in (360, 720, 1080):
  64                 if resolution > max_resolution:
  65                     break
  66                 formats.append({
  67                     'url': '%s.%dp.mp4' % (url_base, resolution),
  68                     'format_id': '%dp' % resolution,
  69                     'height': resolution,
  70                 })
  71
  72         self._check_formats(formats, media_id)
  73         self._sort_formats(formats)
  74
  75         uploader = self._html_search_regex(
  76             r'(?:Author|Writer)\s*<a[^>]+>([^<]+)', webpage, 'uploader',
  77             fatal=False)
  78
  79         return {
  80             'id': media_id,
  81             'title': title,
  82             'uploader': uploader,
  83             'formats': formats,
  84         }