Raphaël G. Git Repositories - youtubedl/blob - 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
  52         age_limit = 0
  53         errors = media_info.get('errors', {})
  54         if errors.get('friends'):
  55             raise ExtractorError('This video is private.', expected=True)
  56         elif errors.get('geoblock'):
  57             raise ExtractorError('This video is not available in your country.', expected=True)
  58         elif errors.get('xxx_unlogged'):
  59             age_limit = 18
  60
  61         media_class = media_info.get('class')
  62         if media_class not in ('video', 'audio'):
  63             raise ExtractorError('not a video or an audio')
  64
  65         user = media_info.get('user', {})
  66
  67         thumbnail = media_info.get('cover_url')
  68         if thumbnail:
  69             thumbnail.format(width='1600', height='1200')
  70
  71         # TODO: get correct ext for audio files
  72         stream_type = media_info.get('stream_type')
  73         formats = [{
  74             'url': media_info['href'],
  75             'ext': stream_type,
  76         }]
  77         if media_info.get('is_hd'):
  78             formats.append({
  79                 'format_id': 'hd',
  80                 'url': media_info['hrefhd'],
  81                 'ext': stream_type,
  82             })
  83         if media_class == 'audio':
  84             formats[0]['vcodec'] = 'none'
  85         else:
  86             formats[0]['format_id'] = 'sd'
  87
  88         return {
  89             'id': media_info['identifier'].split('|')[1],
  90             'display_id': display_id,
  91             'formats': formats,
  92             'title': media_info['title'],
  93             'description': media_info.get('description'),
  94             'thumbnail': thumbnail,
  95             'uploader_id': user.get('username'),
  96             'uploader': user.get('fullname'),
  97             'timestamp': parse_iso8601(media_info.get('published'), ' '),
  98             'duration': int_or_none(media_info.get('duration')),
  99             'view_count': int_or_none(media_info.get('count_views')),
 100             'like_count': int_or_none(media_info.get('count_likes')),
 101             'comment_count': int_or_none(media_info.get('count_comments')),
 102             'age_limit': age_limit,
 103         }