yt_dlp/extractor/turbo.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_str
   5 from ..utils import (
   6     ExtractorError,
   7     int_or_none,
   8     qualities,
   9     xpath_text,
  10 )
  11
  12
  13 class TurboIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?turbo\.fr/videos-voiture/(?P<id>[0-9]+)-'
  15     _API_URL = 'http://www.turbo.fr/api/tv/xml.php?player_generique=player_generique&id={0:}'
  16     _TEST = {
  17         'url': 'http://www.turbo.fr/videos-voiture/454443-turbo-du-07-09-2014-renault-twingo-3-bentley-continental-gt-speed-ces-guide-achat-dacia.html',
  18         'md5': '33f4b91099b36b5d5a91f84b5bcba600',
  19         'info_dict': {
  20             'id': '454443',
  21             'ext': 'mp4',
  22             'duration': 3715,
  23             'title': 'Turbo du 07/09/2014 : Renault Twingo 3, Bentley Continental GT Speed, CES, Guide Achat Dacia... ',
  24             'description': 'Turbo du 07/09/2014 : Renault Twingo 3, Bentley Continental GT Speed, CES, Guide Achat Dacia...',
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         mobj = self._match_valid_url(url)
  31         video_id = mobj.group('id')
  32
  33         webpage = self._download_webpage(url, video_id)
  34
  35         playlist = self._download_xml(self._API_URL.format(video_id), video_id)
  36         item = playlist.find('./channel/item')
  37         if item is None:
  38             raise ExtractorError('Playlist item was not found', expected=True)
  39
  40         title = xpath_text(item, './title', 'title')
  41         duration = int_or_none(xpath_text(item, './durate', 'duration'))
  42         thumbnail = xpath_text(item, './visuel_clip', 'thumbnail')
  43         description = self._html_search_meta('description', webpage)
  44
  45         formats = []
  46         get_quality = qualities(['3g', 'sd', 'hq'])
  47         for child in item:
  48             m = re.search(r'url_video_(?P<quality>.+)', child.tag)
  49             if m:
  50                 quality = compat_str(m.group('quality'))
  51                 formats.append({
  52                     'format_id': quality,
  53                     'url': child.text,
  54                     'quality': get_quality(quality),
  55                 })
  56
  57         return {
  58             'id': video_id,
  59             'title': title,
  60             'duration': duration,
  61             'thumbnail': thumbnail,
  62             'description': description,
  63             'formats': formats,
  64         }