yt_dlp/extractor/presstv.py

   1 from .common import InfoExtractor
   2 from ..utils import remove_start
   3
   4
   5 class PressTVIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?presstv\.ir/[^/]+/(?P<y>\d+)/(?P<m>\d+)/(?P<d>\d+)/(?P<id>\d+)/(?P<display_id>[^/]+)?'
   7
   8     _TEST = {
   9         'url': 'http://www.presstv.ir/Detail/2016/04/09/459911/Australian-sewerage-treatment-facility-/',
  10         'md5': '5d7e3195a447cb13e9267e931d8dd5a5',
  11         'info_dict': {
  12             'id': '459911',
  13             'display_id': 'Australian-sewerage-treatment-facility-',
  14             'ext': 'mp4',
  15             'title': 'Organic mattresses used to clean waste water',
  16             'upload_date': '20160409',
  17             'thumbnail': r're:^https?://.*\.jpg',
  18             'description': 'md5:20002e654bbafb6908395a5c0cfcd125',
  19         },
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = self._match_valid_url(url)
  24         video_id = mobj.group('id')
  25         display_id = mobj.group('display_id') or video_id
  26
  27         webpage = self._download_webpage(url, display_id)
  28
  29         # extract video URL from webpage
  30         video_url = self._hidden_inputs(webpage)['inpPlayback']
  31
  32         # build list of available formats
  33         # specified in http://www.presstv.ir/Scripts/playback.js
  34         base_url = 'http://192.99.219.222:82/presstv'
  35         _formats = [
  36             (180, '_low200.mp4'),
  37             (360, '_low400.mp4'),
  38             (720, '_low800.mp4'),
  39             (1080, '.mp4'),
  40         ]
  41
  42         formats = [{
  43             'url': base_url + video_url[:-4] + extension,
  44             'format_id': f'{height}p',
  45             'height': height,
  46         } for height, extension in _formats]
  47
  48         # extract video metadata
  49         title = remove_start(
  50             self._html_search_meta('title', webpage, fatal=True), 'PressTV-')
  51
  52         thumbnail = self._og_search_thumbnail(webpage)
  53         description = self._og_search_description(webpage)
  54
  55         upload_date = '%04d%02d%02d' % (
  56             int(mobj.group('y')),
  57             int(mobj.group('m')),
  58             int(mobj.group('d')),
  59         )
  60
  61         return {
  62             'id': video_id,
  63             'display_id': display_id,
  64             'title': title,
  65             'formats': formats,
  66             'thumbnail': thumbnail,
  67             'upload_date': upload_date,
  68             'description': description,
  69         }