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