youtube_dl/extractor/ustudio.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     int_or_none,
   8     unified_strdate,
   9     unescapeHTML,
  10 )
  11
  12
  13 class UstudioIE(InfoExtractor):
  14     IE_NAME = 'ustudio'
  15     _VALID_URL = r'https?://(?:(?:www|v1)\.)?ustudio\.com/video/(?P<id>[^/]+)/(?P<display_id>[^/?#&]+)'
  16     _TEST = {
  17         'url': 'http://ustudio.com/video/Uxu2my9bgSph/san_francisco_golden_gate_bridge',
  18         'md5': '58bbfca62125378742df01fc2abbdef6',
  19         'info_dict': {
  20             'id': 'Uxu2my9bgSph',
  21             'display_id': 'san_francisco_golden_gate_bridge',
  22             'ext': 'mp4',
  23             'title': 'San Francisco: Golden Gate Bridge',
  24             'description': 'md5:23925500697f2c6d4830e387ba51a9be',
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26             'upload_date': '20111107',
  27             'uploader': 'Tony Farley',
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         video_id, display_id = re.match(self._VALID_URL, url).groups()
  33
  34         config = self._download_xml(
  35             'http://v1.ustudio.com/embed/%s/ustudio/config.xml' % video_id,
  36             display_id)
  37
  38         def extract(kind):
  39             return [{
  40                 'url': unescapeHTML(item.attrib['url']),
  41                 'width': int_or_none(item.get('width')),
  42                 'height': int_or_none(item.get('height')),
  43             } for item in config.findall('./qualities/quality/%s' % kind) if item.get('url')]
  44
  45         formats = extract('video')
  46         self._sort_formats(formats)
  47
  48         webpage = self._download_webpage(url, display_id)
  49
  50         title = self._og_search_title(webpage)
  51         upload_date = unified_strdate(self._search_regex(
  52             r'(?s)Uploaded by\s*.+?\s*on\s*<span>([^<]+)</span>',
  53             webpage, 'upload date', fatal=False))
  54         uploader = self._search_regex(
  55             r'Uploaded by\s*<a[^>]*>([^<]+)<',
  56             webpage, 'uploader', fatal=False)
  57
  58         return {
  59             'id': video_id,
  60             'display_id': display_id,
  61             'title': title,
  62             'description': self._og_search_description(webpage),
  63             'thumbnails': extract('image'),
  64             'upload_date': upload_date,
  65             'uploader': uploader,
  66             'formats': formats,
  67         }
  68
  69
  70 class UstudioEmbedIE(InfoExtractor):
  71     IE_NAME = 'ustudio:embed'
  72     _VALID_URL = r'https?://(?:(?:app|embed)\.)?ustudio\.com/embed/(?P<uid>[^/]+)/(?P<id>[^/]+)'
  73     _TEST = {
  74         'url': 'http://app.ustudio.com/embed/DeN7VdYRDKhP/Uw7G1kMCe65T',
  75         'md5': '47c0be52a09b23a7f40de9469cec58f4',
  76         'info_dict': {
  77             'id': 'Uw7G1kMCe65T',
  78             'ext': 'mp4',
  79             'title': '5 Things IT Should Know About Video',
  80             'description': 'md5:93d32650884b500115e158c5677d25ad',
  81             'uploader_id': 'DeN7VdYRDKhP',
  82         }
  83     }
  84
  85     def _real_extract(self, url):
  86         uploader_id, video_id = re.match(self._VALID_URL, url).groups()
  87         video_data = self._download_json(
  88             'http://app.ustudio.com/embed/%s/%s/config.json' % (uploader_id, video_id),
  89             video_id)['videos'][0]
  90         title = video_data['name']
  91
  92         formats = []
  93         for ext, qualities in video_data.get('transcodes', {}).items():
  94             for quality in qualities:
  95                 quality_url = quality.get('url')
  96                 if not quality_url:
  97                     continue
  98                 height = int_or_none(quality.get('height'))
  99                 formats.append({
 100                     'format_id': '%s-%dp' % (ext, height) if height else ext,
 101                     'url': quality_url,
 102                     'width': int_or_none(quality.get('width')),
 103                     'height': height,
 104                 })
 105         self._sort_formats(formats)
 106
 107         thumbnails = []
 108         for image in video_data.get('images', []):
 109             image_url = image.get('url')
 110             if not image_url:
 111                 continue
 112             thumbnails.append({
 113                 'url': image_url,
 114             })
 115
 116         return {
 117             'id': video_id,
 118             'title': title,
 119             'description': video_data.get('description'),
 120             'duration': int_or_none(video_data.get('duration')),
 121             'uploader_id': uploader_id,
 122             'tags': video_data.get('keywords'),
 123             'thumbnails': thumbnails,
 124             'formats': formats,
 125         }