git.bitcoin.ninja Git - youtube-dl/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': 'mp4',
  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
  27     def _real_extract(self, url):
  28         display_id = self._match_id(url)
  29
  30         webpage = self._download_webpage(url, display_id)
  31         video_id = self._search_regex(
  32             r"player\.loadRevision3Item\('video_id',\s*([0-9]+)\);",
  33             webpage, 'video ID')
  34
  35         all_info = self._download_json(
  36             'https://testtube.com/api/getPlaylist.json?api_key=ba9c741bce1b9d8e3defcc22193f3651b8867e62&codecs=h264,vp8,theora&video_id=%s' % video_id,
  37             video_id)
  38         info = all_info['items'][0]
  39
  40         formats = []
  41         for vcodec, fdatas in info['media'].items():
  42             for name, fdata in fdatas.items():
  43                 formats.append({
  44                     'format_id': '%s-%s' % (vcodec, name),
  45                     'url': fdata['url'],
  46                     'vcodec': vcodec,
  47                     'tbr': fdata.get('bitrate'),
  48                 })
  49         self._sort_formats(formats)
  50
  51         duration = int_or_none(info.get('duration'))
  52         images = info.get('images')
  53         thumbnails = None
  54         preference = qualities(['mini', 'small', 'medium', 'large'])
  55         if images:
  56             thumbnails = [{
  57                 'id': thumbnail_id,
  58                 'url': img_url,
  59                 'preference': preference(thumbnail_id)
  60             } for thumbnail_id, img_url in images.items()]
  61
  62         return {
  63             'id': video_id,
  64             'display_id': display_id,
  65             'title': info['title'],
  66             'description': info.get('summary'),
  67             'thumbnails': thumbnails,
  68             'uploader': info.get('show', {}).get('name'),
  69             'uploader_id': info.get('show', {}).get('slug'),
  70             'duration': duration,
  71             'formats': formats,
  72         }