youtube_dl/extractor/trilulilu.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     int_or_none,
   8     parse_iso8601,
   9 )
  10
  11
  12 class TriluliluIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:(?:www|m)\.)?trilulilu\.ro/(?:[^/]+/)?(?P<id>[^/#\?]+)'
  14     _TESTS = [{
  15         'url': 'http://www.trilulilu.ro/big-buck-bunny-1',
  16         'md5': '68da087b676a6196a413549212f60cc6',
  17         'info_dict': {
  18             'id': 'ae2899e124140b',
  19             'ext': 'mp4',
  20             'title': 'Big Buck Bunny',
  21             'description': ':) pentru copilul din noi',
  22             'uploader_id': 'chipy',
  23             'upload_date': '20120304',
  24             'timestamp': 1330830647,
  25             'uploader': 'chipy',
  26             'view_count': int,
  27             'like_count': int,
  28             'comment_count': int,
  29         },
  30     }, {
  31         'url': 'http://www.trilulilu.ro/adena-ft-morreti-inocenta',
  32         'md5': '929dfb8729dc71750463af88bbbbf4a4',
  33         'info_dict': {
  34             'id': 'f299710e3c91c5',
  35             'ext': 'mp4',
  36             'title': 'Adena ft. Morreti - Inocenta',
  37             'description': 'pop music',
  38             'uploader_id': 'VEVOmixt',
  39             'upload_date': '20151204',
  40             'uploader': 'VEVOmixt',
  41             'timestamp': 1449187937,
  42             'view_count': int,
  43             'like_count': int,
  44             'comment_count': int,
  45         },
  46     }]
  47
  48     def _real_extract(self, url):
  49         display_id = self._match_id(url)
  50         media_info = self._download_json('http://m.trilulilu.ro/%s?format=json' % display_id, display_id)
  51         user = media_info.get('user', {})
  52
  53         thumbnail = media_info.get('cover_url')
  54         if thumbnail:
  55             thumbnail.format(width='1600', height='1200')
  56
  57         media_class = media_info.get('class')
  58         if media_class in ('video', 'audio'):
  59             # TODO: get correct ext for audio files
  60             stream_type = media_info.get('stream_type')
  61             formats = [{
  62                 'url': media_info['href'],
  63                 'ext': stream_type,
  64             }]
  65             if media_info.get('is_hd'):
  66                 formats.append({
  67                     'url': media_info['hrefhd'],
  68                     'ext': stream_type,
  69                 })
  70         else:
  71             raise ExtractorError('not a video or an audio')
  72
  73         if media_class == 'audio':
  74             formats[0]['vcodec'] = 'none'
  75
  76         return {
  77             'id': media_info['identifier'].split('|')[1],
  78             'display_id': display_id,
  79             'formats': formats,
  80             'title': media_info['title'],
  81             'description': media_info.get('description'),
  82             'thumbnail': thumbnail,
  83             'uploader_id': user.get('username'),
  84             'uploader': user.get('fullname'),
  85             'timestamp': parse_iso8601(media_info.get('published'), ' '),
  86             'duration': int_or_none(media_info.get('duration')),
  87             'view_count': int_or_none(media_info.get('count_views')),
  88             'like_count': int_or_none(media_info.get('count_likes')),
  89             'comment_count': int_or_none(media_info.get('count_comments')),
  90         }