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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import int_or_none
   6
   7
   8 class UstudioIE(InfoExtractor):
   9     IE_NAME = 'uStudio'
  10     _VALID_URL = r'http://(?:www\.|v1\.)?ustudio.com/video/(?P<id>[\w\d]+)/.+'
  11     _TESTS = [
  12         {
  13             'url': 'http://ustudio.com/video/Uxu2my9bgSph/san_francisco_golden_gate_bridge',
  14             'md5': '58bbfca62125378742df01fc2abbdef6',
  15             'info_dict': {
  16                 'id': 'Uxu2my9bgSph',
  17                 'ext': 'mp4',
  18                 'title': 'San Francisco: Golden Gate Bridge',
  19                 'thumbnail': 're:^https?://.*\.jpg$',
  20                 'description': 'md5:23925500697f2c6d4830e387ba51a9be',
  21                 'uploader': 'Tony Farley',
  22             }
  23         },
  24     ]
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28
  29         webpage = self._download_webpage(url, video_id)
  30
  31         doc = self._download_xml(
  32             'http://v1.ustudio.com/embed/{0}/ustudio/config.xml'.format(
  33                 video_id),
  34             video_id,
  35             note='Downloading video info',
  36             errnote='Failed to download video info')
  37
  38         formats = [
  39             {
  40                 'url': quality.attrib['url'],
  41                 'width': int_or_none(quality.attrib.get('width')),
  42                 'height': int_or_none(quality.attrib.get('height')),
  43             } for quality in doc.findall('./qualities/quality/video')
  44         ]
  45         self._sort_formats(formats)
  46
  47         return {
  48             'id': video_id,
  49             'title': self._og_search_title(webpage),
  50             'thumbnail': self._og_search_thumbnail(webpage),
  51             'formats': formats,
  52             'description': self._og_search_description(webpage),
  53             'uploader': self._html_search_regex(
  54                 r'<a href=".*/user/.+">(.+)</a> on',
  55                 webpage,
  56                 'uploader',
  57                 fatal=False),
  58         }