Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/testtube.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     qualities,
   7 )
   8
   9
  10 class TestTubeIE(InfoExtractor):
  11     _VALID_URL = r'https?://testtube\.com/[^/?#]+/(?P<id>[^/?#]+)'
  12     _TESTS = [{
  13         'url': 'https://testtube.com/dnews/5-weird-ways-plants-can-eat-animals?utm_source=FB&utm_medium=DNews&utm_campaign=DNewsSocial',
  14         'info_dict': {
  15             'id': '60163',
  16             'display_id': '5-weird-ways-plants-can-eat-animals',
  17             'duration': 275,
  18             'ext': 'webm',
  19             'title': '5 Weird Ways Plants Can Eat Animals',
  20             'description': 'Why have some plants evolved to eat meat?',
  21             'thumbnail': 're:^https?://.*\.jpg$',
  22             'uploader': 'DNews',
  23             'uploader_id': 'dnews',
  24         },
  25     }, {
  26         'url': 'https://testtube.com/iflscience/insane-jet-ski-flipping',
  27         'info_dict': {
  28             'id': 'fAGfJ4YjVus',
  29             'ext': 'mp4',
  30             'title': 'Flipping Jet-Ski Skills | Outrageous Acts of Science',
  31             'uploader': 'Science Channel',
  32             'uploader_id': 'ScienceChannel',
  33             'upload_date': '20150203',
  34             'description': 'md5:e61374030015bae1d2e22f096d4769d6',
  35         }
  36     }]
  37
  38     def _real_extract(self, url):
  39         display_id = self._match_id(url)
  40
  41         webpage = self._download_webpage(url, display_id)
  42
  43         youtube_url = self._html_search_regex(
  44             r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
  45             webpage, 'youtube iframe', default=None)
  46         if youtube_url:
  47             return self.url_result(youtube_url, 'Youtube', video_id=display_id)
  48
  49         video_id = self._search_regex(
  50             r"player\.loadRevision3Item\('video_id',\s*([0-9]+)\);",
  51             webpage, 'video ID')
  52
  53         all_info = self._download_json(
  54             'https://testtube.com/api/getPlaylist.json?api_key=ba9c741bce1b9d8e3defcc22193f3651b8867e62&codecs=h264,vp8,theora&video_id=%s' % video_id,
  55             video_id)
  56         info = all_info['items'][0]
  57
  58         formats = []
  59         for vcodec, fdatas in info['media'].items():
  60             for name, fdata in fdatas.items():
  61                 formats.append({
  62                     'format_id': '%s-%s' % (vcodec, name),
  63                     'url': fdata['url'],
  64                     'vcodec': vcodec,
  65                     'tbr': fdata.get('bitrate'),
  66                 })
  67         self._sort_formats(formats)
  68
  69         duration = int_or_none(info.get('duration'))
  70         images = info.get('images')
  71         thumbnails = None
  72         preference = qualities(['mini', 'small', 'medium', 'large'])
  73         if images:
  74             thumbnails = [{
  75                 'id': thumbnail_id,
  76                 'url': img_url,
  77                 'preference': preference(thumbnail_id)
  78             } for thumbnail_id, img_url in images.items()]
  79
  80         return {
  81             'id': video_id,
  82             'display_id': display_id,
  83             'title': info['title'],
  84             'description': info.get('summary'),
  85             'thumbnails': thumbnails,
  86             'uploader': info.get('show', {}).get('name'),
  87             'uploader_id': info.get('show', {}).get('slug'),
  88             'duration': duration,
  89             'formats': formats,
  90         }