youtube_dl/extractor/turbo.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 compat_str
   8 from ..utils import (
   9     ExtractorError,
  10     int_or_none,
  11     qualities,
  12     xpath_text,
  13 )
  14
  15
  16 class TurboIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?turbo\.fr/videos-voiture/(?P<id>[0-9]+)-'
  18     _API_URL = 'http://www.turbo.fr/api/tv/xml.php?player_generique=player_generique&id={0:}'
  19     _TEST = {
  20         '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',
  21         'md5': '33f4b91099b36b5d5a91f84b5bcba600',
  22         'info_dict': {
  23             'id': '454443',
  24             'ext': 'mp4',
  25             'duration': 3715,
  26             'title': 'Turbo du 07/09/2014 : Renault Twingo 3, Bentley Continental GT Speed, CES, Guide Achat Dacia... ',
  27             'description': 'Turbo du 07/09/2014 : Renault Twingo 3, Bentley Continental GT Speed, CES, Guide Achat Dacia...',
  28             'thumbnail': r're:^https?://.*\.jpg$',
  29         }
  30     }
  31
  32     def _real_extract(self, url):
  33         mobj = re.match(self._VALID_URL, url)
  34         video_id = mobj.group('id')
  35
  36         webpage = self._download_webpage(url, video_id)
  37
  38         playlist = self._download_xml(self._API_URL.format(video_id), video_id)
  39         item = playlist.find('./channel/item')
  40         if item is None:
  41             raise ExtractorError('Playlist item was not found', expected=True)
  42
  43         title = xpath_text(item, './title', 'title')
  44         duration = int_or_none(xpath_text(item, './durate', 'duration'))
  45         thumbnail = xpath_text(item, './visuel_clip', 'thumbnail')
  46         description = self._html_search_meta('description', webpage)
  47
  48         formats = []
  49         get_quality = qualities(['3g', 'sd', 'hq'])
  50         for child in item:
  51             m = re.search(r'url_video_(?P<quality>.+)', child.tag)
  52             if m:
  53                 quality = compat_str(m.group('quality'))
  54                 formats.append({
  55                     'format_id': quality,
  56                     'url': child.text,
  57                     'quality': get_quality(quality),
  58                 })
  59         self._sort_formats(formats)
  60
  61         return {
  62             'id': video_id,
  63             'title': title,
  64             'duration': duration,
  65             'thumbnail': thumbnail,
  66             'description': description,
  67             'formats': formats,
  68         }