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