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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     qualities,
   8     unified_strdate,
   9     clean_html,
  10 )
  11
  12
  13 class UltimediaIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?ultimedia\.com/default/index/video[^/]+/id/(?P<id>[\d+a-z]+)'
  15     _TESTS = [{
  16         # news
  17         'url': 'https://www.ultimedia.com/default/index/videogeneric/id/s8uk0r',
  18         'md5': '276a0e49de58c7e85d32b057837952a2',
  19         'info_dict': {
  20             'id': 's8uk0r',
  21             'ext': 'mp4',
  22             'title': 'Loi sur la fin de vie: le texte prévoit un renforcement des directives anticipées',
  23             'description': 'md5:3e5c8fd65791487333dda5db8aed32af',
  24             'thumbnail': 're:^https?://.*\.jpg',
  25             'upload_date': '20150317',
  26         },
  27     }, {
  28         # music
  29         'url': 'https://www.ultimedia.com/default/index/videomusic/id/xvpfp8',
  30         'md5': '2ea3513813cf230605c7e2ffe7eca61c',
  31         'info_dict': {
  32             'id': 'xvpfp8',
  33             'ext': 'mp4',
  34             'title': "Two - C'est la vie (Clip)",
  35             'description': 'Two',
  36             'thumbnail': 're:^https?://.*\.jpg',
  37             'upload_date': '20150224',
  38         },
  39     }]
  40
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43
  44         webpage = self._download_webpage(url, video_id)
  45
  46         deliver_url = self._search_regex(
  47             r'<iframe[^>]+src="(https?://(?:www\.)?ultimedia\.com/deliver/[^"]+)"',
  48             webpage, 'deliver URL')
  49
  50         deliver_page = self._download_webpage(
  51             deliver_url, video_id, 'Downloading iframe page')
  52
  53         if '>This video is currently not available' in deliver_page:
  54             raise ExtractorError(
  55                 'Video %s is currently not available' % video_id, expected=True)
  56
  57         player = self._parse_json(
  58             self._search_regex(
  59                 r"jwplayer\('player(?:_temp)?'\)\.setup\(({.+?})\)\.on", deliver_page, 'player'),
  60             video_id)
  61
  62         quality = qualities(['flash', 'html5'])
  63
  64         formats = [{
  65             'url': mode['config']['file'],
  66             'format_id': mode.get('type'),
  67             'quality': quality(mode.get('type')),
  68         } for mode in player['modes']]
  69         self._sort_formats(formats)
  70
  71         thumbnail = player.get('image')
  72
  73         title = clean_html((
  74             self._html_search_regex(
  75                 r'(?s)<div\s+id="catArticle">.+?</div>(.+?)</h1>',
  76                 webpage, 'title', default=None)
  77             or self._search_regex(
  78                 r"var\s+nameVideo\s*=\s*'([^']+)'",
  79                 deliver_page, 'title')))
  80
  81         description = clean_html(self._html_search_regex(
  82             r'(?s)<span>Description</span>(.+?)</p>', webpage,
  83             'description', fatal=False))
  84
  85         upload_date = unified_strdate(self._search_regex(
  86             r'Ajouté le\s*<span>([^<]+)', webpage,
  87             'upload date', fatal=False))
  88
  89         return {
  90             'id': video_id,
  91             'title': title,
  92             'description': description,
  93             'thumbnail': thumbnail,
  94             'upload_date': upload_date,
  95             'formats': formats,
  96         }