_ Git - youtube-dl/blob - youtube_dl/extractor/ultimedia.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_urllib_parse_urlparse
   8 from ..utils import (
   9     ExtractorError,
  10     qualities,
  11     unified_strdate,
  12     clean_html,
  13 )
  14
  15
  16 class UltimediaIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?ultimedia\.com/default/index/video[^/]+/id/(?P<id>[\d+a-z]+)'
  18     _TESTS = [{
  19         # news
  20         'url': 'https://www.ultimedia.com/default/index/videogeneric/id/s8uk0r',
  21         'md5': '276a0e49de58c7e85d32b057837952a2',
  22         'info_dict': {
  23             'id': 's8uk0r',
  24             'ext': 'mp4',
  25             'title': 'Loi sur la fin de vie: le texte prévoit un renforcement des directives anticipées',
  26             'description': 'md5:3e5c8fd65791487333dda5db8aed32af',
  27             'thumbnail': 're:^https?://.*\.jpg',
  28             'upload_date': '20150317',
  29         },
  30     }, {
  31         # music
  32         'url': 'https://www.ultimedia.com/default/index/videomusic/id/xvpfp8',
  33         'md5': '2ea3513813cf230605c7e2ffe7eca61c',
  34         'info_dict': {
  35             'id': 'xvpfp8',
  36             'ext': 'mp4',
  37             'title': "Two - C'est la vie (Clip)",
  38             'description': 'Two',
  39             'thumbnail': 're:^https?://.*\.jpg',
  40             'upload_date': '20150224',
  41         },
  42     }]
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46         webpage = self._download_webpage(url, video_id)
  47
  48         deliver_url = self._proto_relative_url(self._search_regex(
  49             r'<iframe[^>]+src="((?:https?:)?//(?:www\.)?ultimedia\.com/deliver/[^"]+)"',
  50             webpage, 'deliver URL'), compat_urllib_parse_urlparse(url).scheme + ':')
  51
  52         deliver_page = self._download_webpage(
  53             deliver_url, video_id, 'Downloading iframe page')
  54
  55         if '>This video is currently not available' in deliver_page:
  56             raise ExtractorError(
  57                 'Video %s is currently not available' % video_id, expected=True)
  58
  59         player = self._parse_json(
  60             self._search_regex(
  61                 r"jwplayer\('player(?:_temp)?'\)\.setup\(({.+?})\)\.on",
  62                 deliver_page, 'player'),
  63             video_id)
  64
  65         quality = qualities(['flash', 'html5'])
  66         formats = []
  67         for mode in player['modes']:
  68             video_url = mode.get('config', {}).get('file')
  69             if not video_url:
  70                 continue
  71             if re.match(r'https?://www\.youtube\.com/.+?', video_url):
  72                 return self.url_result(video_url, 'Youtube')
  73             formats.append({
  74                 'url': video_url,
  75                 'format_id': mode.get('type'),
  76                 'quality': quality(mode.get('type')),
  77             })
  78         self._sort_formats(formats)
  79
  80         thumbnail = player.get('image')
  81
  82         title = clean_html((
  83             self._html_search_regex(
  84                 r'(?s)<div\s+id="catArticle">.+?</div>(.+?)</h1>',
  85                 webpage, 'title', default=None) or
  86             self._search_regex(
  87                 r"var\s+nameVideo\s*=\s*'([^']+)'",
  88                 deliver_page, 'title')))
  89
  90         description = clean_html(self._html_search_regex(
  91             r'(?s)<span>Description</span>(.+?)</p>', webpage,
  92             'description', fatal=False))
  93
  94         upload_date = unified_strdate(self._search_regex(
  95             r'Ajouté le\s*<span>([^<]+)', webpage,
  96             'upload date', fatal=False))
  97
  98         return {
  99             'id': video_id,
 100             'title': title,
 101             'description': description,
 102             'thumbnail': thumbnail,
 103             'upload_date': upload_date,
 104             'formats': formats,
 105         }